ArticlePDF Available

Liver contrast-enhanced sonography: Computer-assisted differentiation between focal nodular hyperplasia and inflammatory hepatocellular adenoma by reference to microbubble transport patterns


Abstract and Figures

ObjectiveA new computer tool is proposed to distinguish between focal nodular hyperplasia (FNH) and an inflammatory hepatocellular adenoma (I-HCA) using contrast-enhanced ultrasound (CEUS). The new method was compared with the usual qualitative analysis.Methods The proposed tool embeds an “optical flow” algorithm, designed to mimic the human visual perception of object transport in image series, to quantitatively analyse apparent microbubble transport parameters visible on CEUS. Qualitative (visual) and quantitative (computer-assisted) CEUS data were compared in a cohort of adult patients with either FNH or I-HCA based on pathological and radiological results. For quantitative analysis, several computer-assisted classification models were tested and subjected to cross-validation. The accuracies, area under the receiver-operating characteristic curve (AUROC), sensitivity and specificity, positive predictive values (PPVs), negative predictive values (NPVs), false predictive rate (FPRs) and false negative rate (FNRs) were recorded.ResultsForty-six patients with FNH (n = 29) or I-HCA (n = 17) with 47 tumours (one patient with 2 I-HCA) were analysed. The qualitative diagnostic parameters were accuracy = 93.6%, AUROC = 0.94, sensitivity = 94.4%, specificity = 93.1%, PPV = 89.5%, NPV = 96.4%, FPR = 6.9% and FNR = 5.6%. The quantitative diagnostic parameters were accuracy = 95.9%, AUROC = 0.97, sensitivity = 93.4%, specificity = 97.6%, PPV = 95.3%, NPV = 96.7%, FPR = 2.4% and FNR = 6.6%.Conclusions Microbubble transport patterns evident on CEUS are valuable diagnostic indicators. Machine-learning algorithms analysing such data facilitate the diagnosis of FNH and I-HCA tumours.Key Points • Distinguishing between focal nodular hyperplasia and an inflammatory hepatocellular adenoma using dynamic contrast-enhanced ultrasound is sometimes difficult. • Microbubble transport patterns evident on contrast-enhanced sonography are valuable diagnostic indicators. • Machine-learning algorithms analysing microbubble transport patterns facilitate the diagnosis of FNH and I-HCA.
Content may be subject to copyright.
HAL Id: hal-03006999
Submitted on 16 Nov 2020
HAL is a multi-disciplinary open access
archive for the deposit and dissemination of sci-
entic research documents, whether they are pub-
lished or not. The documents may come from
teaching and research institutions in France or
abroad, or from public or private research centers.
L’archive ouverte pluridisciplinaire HAL, est
destinée au dépôt et à la diusion de documents
scientiques de niveau recherche, publiés ou non,
émanant des établissements d’enseignement et de
recherche français ou étrangers, des laboratoires
publics ou privés.
Liver contrast-enhanced sonography: Computer-assisted
dierentiation between focal nodular hyperplasia and
inammatory hepatocellular adenoma by reference to
microbubble transport patterns
Baudouin Denis de Senneville, Nora Frulio, Hervé Laumonier, Cécile Salut,
Luc Latte, Hervé Trillaud
To cite this version:
Baudouin Denis de Senneville, Nora Frulio, Hervé Laumonier, Cécile Salut, Luc Latte, et al.. Liver
contrast-enhanced sonography: Computer-assisted dierentiation between focal nodular hyperplasia
and inammatory hepatocellular adenoma by reference to microbubble transport patterns. European
Radiology, Springer Verlag, 2020, �10.1007/s00330-019-06566-1�. �hal-03006999�
Liver contrast-enhanced sonography: Computer-assisted
differentiation between focal nodular hyperplasia and
inflammatory hepatocellular adenoma by reference to
microbubble transport patterns
Baudouin Denis de Senneville1, PhD,
Nora Frulio2, MD,
Hervé Laumonier2, PhD,
Cécile Salut2, MD,
Luc Lafitte1, MD,
Hervé Trillaud2,3, PhD,
1Institut de Mathématiques de Bordeaux (IMB), UMR 5251 CNRS/Université de Bordeaux, 351
cours de la Libération, F-33405, Talence, France
2CHU de Bordeaux, Service d’imagerie diagnostique et Interventionnelle Magellan/Saint André, F-
33000 Bordeaux, France
3EA IMOTION (Imagerie moléculaire et thérapies innovantes en oncologie), Université de
Bordeaux, F-33000 Bordeaux, France
Corresponding Author:
Baudouin Denis de Senneville
Address: Institut de Mathématiques de Bordeaux (IMB), UMR 5251 CNRS/Université de
Bordeaux, 351 cours de la Libération, F-33405, Talence, France
Phone: (+33) (0)5 40 00 25 92
Fax: (+33) (0)5 40 00 21 23
Objective: A new computer tool is proposed to distinguish between focal nodular hyperplasia
(FNH) and an inflammatory hepatocellular adenoma (I-HCA) using contrast-enhanced ultrasound
(CEUS). The new method was compared with the usual qualitative analysis.
Methods: The proposed tool embeds an "optical flow" algorithm, designed to mimic the
human visual perception of object transport in image series, to quantitatively analyse
apparent microbubble transport parameters visible on CEUS. Qualitative (visual) and
quantitative (computer-assisted) CEUS data were compared in a cohort of adult patients with either
FNH or I-HCA based on pathological and radiological results. For quantitative analysis, several
computer-assisted classification models were tested and subjected to cross-validation. The
accuracies, area under the receiver-operating characteristic curve (AUROC), sensitivity and
specificity, positive predictive values (PPVs), negative predictive values (NPVs), false predictive
rate (FPRs) and false negative rate (FNRs) were recorded.
Results: Forty-six patients with FNH (n = 29) or I-HCA (n = 17) with 47 tumors (one patient with 2
I-HCA) were analysed. The qualitative diagnostic parameters were: accuracy = 93.6%,
AUROC=0.94, sensitivity = 94.4%, specificity = 93.1%, PPV = 89.5% and NPV = 96.4%, FPR =
6.9%, FNR = 5.6%. The quantitative diagnostic parameters were: accuracy = 95.9%, AUROC =
0.97, sensitivity = 93.4%, specificity = 97.6%, PPV = 95.3%, and NPV = 96.7%, FPR = 2.4%, FNR
= 6.6%.
Conclusions: Microbubble transport patterns evident on CEUS are valuable diagnostic indicators.
Machine-learning algorithms analysing such data facilitate the diagnosis of FNH and I-HCA
Key Points:
- Distinguishing between focal nodular hyperplasia and an inflammatory hepatocellular
adenoma using dynamic contrast-enhanced ultrasound is sometimes difficult.
- Microbubble transport patterns evident on contrast-enhanced sonography are valuable
diagnostic indicators.
- Machine-learning algorithms analysing microbubble transport patterns facilitate the
diagnosis of FNH and I-HCA.
- The technique offers a potential future means for accurately characterizing other hepatic
lesions, potentially obviating the need for biopsy or surgical resection.
Keywords: Ultrasound Imaging ; Adenoma ; Perfusion imaging ; Computer-Assisted Diagnosis ;
Retrospective studies.
Abbreviations and acronyms:
US: Ultrasound
CEUS: contrast-enhanced ultrasound
FNH: Focal nodular hyperplasias
HCA: Hepatocellular adenomas
I-HCA: Inflammatory hepatocellular adenoma
CT: Computed tomography
MRI: Magnetic resonance imaging
T: Tesla
CNIL: National Commission on Informatics and Liberty
RF: Random forest
KNN: k-nearest neighbour
SVM: Support vector machine
LR: Logistic regression
PPV: Positive predictive value
NPV: Negative predictive value
AUC: Area under the curve
ROC: Receiver-Operating-Characteristic
GB: Gigabit
RAM: Random access memory
Benign hepatocellular tumours are rare, constituting 10% of all hepatic tumours (1). Two large
groups of benign hepatocellular tumours can be distinguished: reactive regenerative lesions (focal
nodular hyperplasias [FNHs]), and tumoural lesions (hepatocellular adenomas [HCAs]). Both
lesions are most common in young females (1). Diagnostic imaging is essential to guide treatment
decisions, which range from no treatment to surgical resection or confirmatory biopsy.
Traditionally, multiphase computed tomography (CT) or magnetic resonance imaging (MRI) has
been used for detailed evaluation of hepatic lesions. However, the high-level radiation associated
with multiphase CT and the limited accessibility of MRI have rendered dynamic contrast
agent-enhanced ultrasound (CEUS) an attractive, safe, non-invasive, accurate, and economic tool
for evaluating hepatic lesions (2)(6). Although the appearance is not always typical in some cases,
both FNH and HCA demonstrate typical, reproducible, arterial phase enhancement patterns on
CEUS in most cases. The diagnostic criteria for FNH are a hyper-enhancing lesion in the arterial
phase with rapid centrifugal filling from a central vessel, and radial vascular branches (the “spoke
and wheel sign) (2)(5) and also sustained enhancement in portal and late phase (7). HCAs
constitute a heterogeneous group of tumours exhibiting multiple histological subtypes
(inflammatory, with FNH1A or catenin gene mutations, or unclassified) (8). On CEUS, HCAs are
hyper-enhancing in the arterial phase; the enhancement pattern commences peripherally and
exhibits rapid centripetal filling; this pattern is characteristic of 8690% of all inflammatory HCAs
(I-HCAs). Other HCA subtypes exhibit iso-vascularity or moderate hyper-vascularity, with mixed
filling patterns in the arterial phase (2)(9). In clinical practice, it is essential to distinguish FNH
from adenoma to ensure appropriate management. Confirmed FNHs are managed conservatively
(with regular follow-up); HCAs require cessation of oral contraceptive use, (commonly) biopsy, and
either surgery or (at least) follow-up imaging. I-HCA show the most important hypervascularity and
10-15% of I-HCA are also found to be β-catenin activated with a risk for malignant transformation.
Distinguishing between FNH and I-HCA using CEUS is sometimes difficult because both lesions
evidence hyper-enhancement during the arterial phase and it can be challenging to qualitatively
differentiate centrifugal from centripetal tumour filling, particularly for larger nodules. Computer-
assisted methods are thus required for quantitative spatiotemporal assessment of organ perfusion.
Such techniques must be faster and more reproducible than visual analysis, and must lack learning
curves. Efforts have been made to quantify enhancement parameters in vascular compartments as
indicators of several pathological conditions (1014). In particular, transport equations have been
recently derived to estimate microbubble velocity at the time of bolus contrast arrival (15). In
practice, a so-called "optical flow" algorithm is employed to mimic the human visual perception of
microbubble transport in CEUS (16-18). Here, we use this approach to quantitatively distinguish
between FNH and I-HCA. We quantify divergence (sources and sinks), curling (shearing),
amplitudes, and convergence towards the centre of tumour (centrifugal/centripetal nature) in dense
transport fields (16); these are very simple indicators of displacement vector directions, orientations,
and magnitudes. In turn, these serve as inputs to a binary FNH/I-HCA classifier.
The purpose was to compare, as a preliminary study, the original concept of computer-assisted
method with the usual qualitative analysis for the diagnosis of two benign hepatocellular tumours
(FNH and I-HCA) with hypervascularity during the arterial phase of the CEUS.
Study design and population
In this retrospective single-centre study conducted from July 2005 to July 2018, we identified
images from patients who underwent CEUS and were (otherwise) definitively diagnosed with FNH
or I-HCA. We included I-HCA patients who had been histologically diagnosed (6) and FNH
patients diagnosed based on commonly accepted MRI criteria (3), imaging follow-up, or
histologically. All MRIs were performed using a 1.5-T machine running a published imaging
protocol (19)(20). The study adhered to all local regulations and data protection agency
recommendations (the National Commission on Informatics and Liberty (CNIL) dictates). Patients
have been informed for the use of their data anonymously.
Demographic characteristics
We enrolled 46 patients (Table 1) with the inclusion criteria, 29 had FNH and 17 I-HCA (18 I-HCA
tumours were analysed because one patient had two tumours). Of 29 FNH patients, 23 (79%) were
female and the median age was 44 (2161) years; of 17 I-HCA patients, 16 (94%) were female and
the median age was 40.5 (2166) years. The median diameters of FNH and I-HCA lesions were
respectively 2.9 (310) and 6.9 (3.412) cm. Histological data of the 18 I-HCA tumours were
available for 15 surgical specimens and 3 percutaneous biopsies Histological data on 7/29 FNH
tumours (24%) were available (percutaneous biopsy, six samples; one surgical sample); imaging
follow-up data were available for 15/22 patients without histological diagnosis (68%) with a median
follow-up of 12 (484) months ; CEUS was performed using Sequoia (n = 37), S2000 (n = 4), and
S3000 (n = 5) instruments.
Histological analysis
Histological samples were obtained by biopsy or during surgical resection; for ethical reasons, no
samples were taken purely for the purpose of this study; clinical indications were required. All
analyses were performed as previously described (8)(9)(19), in the same laboratory.
CEUS protocol
CEUS was performed by abdominal radiologists who had 5-10 years of experience. Each patient
received a bolus injection of ultrasound contrast agent (SonoVue, Bracco). Contrast-enhanced
sequences were obtained using dedicated, low mechanical index (MI) contrast-imaging software
(MI < 0.2) employing one of three US machines (Sequoia, S2000 and S3000; a Siemens Medical
Solution instrument featuring Cadence Contrast Pulse Sequencing [CPS]; and a Convex Array 4C1-
S probe). Standard pre-settings were used, but it was possible to adjust settings for individual
patients. SonoVue was injected intravenously as a bolus of 2.4 mL via a 20-gauge cannula into the
antecubital vein, followed by flushing with 5 mL normal saline. Digital cine clips showing dynamic
contrast enhancement within the lesion and surrounding liver tissue were continuously recorded,
commencing 5 s before SonoVue injection and covering the arterial (1045 s post-injection), portal
(6090 s), and late (120150 s) phases. Injection was repeated using the same dose (2.4 mL
SonoVue) if the data were of poor quality. All sequences were digitally stored. Intra-tumoural
vascular geometry and lesional enhancement patterns were evaluated.
CEUS analysis of lesional type
Qualitative visual analysis
Data were reviewed in consensus by two abdominal radiologists blinded to pathological and MRI
diagnoses. Each lesion was classified using pre-defined criteria for FNH and I-HCA. For FNH,
these were hyper-enhancement in the arterial phase, with rapid centrifugal filling; (usually) an
obvious central vessel and radial vascular branches (especially in larger lesions; the spoke and
wheel sign); and iso- or hyper-enhancement in the portal and venous phases, without washout. For
I-HCA, the criteria were hyper-enhancement in the arterial phase, frequently accompanied by rapid
centripetal filling; no radial vascular structure; and iso- or hyper-enhancement in the portal and
venous phases, without washout (3) (9) (21).
Computer-assisted quantitative analysis using a transport equation model
Microbubble transport fields in lesions were estimated (using a transport equation) on a pixel-by-
pixel basis employing the so-called optical flow process (15). The “optical flow” problem has
long been studied by vision scientists in efforts to analyse general visual motion in images of a
moving target (16)(17). For each lesion, the absolute changes in four image-based displacement
indicators were calculated: (i) the divergence δ (reflecting the presence of sources and sinks); (ii)
the curl ρ (reflecting local vortices); (iii) the amplitude γ (reflecting the magnitude of apparent
displacement); and, (iv) the centripetal nature τ (reflecting the flow field convergence towards the
centre of tumour). The analysis was restricted to a region of interest, manually drawn on a high
contrast CEUS image, encompassing the tumour. The analytical window size was fixed at 2 s
commencing at the bolus arrival time, and thus covered the filling phase. The reader is referred to
Appendix A for additional information on numerical resolution and implementation. All computer-
assisted analyses were blinded to pathological data.
Statistical analysis
The accuracies, area under the ROC curve (AUROC), sensitivity, specificity, positive predictive
values (PPVs), negative predictive values (NPVs), false predictive rate (FPRs) and false negative
rate (FNRs) of qualitative and quantitative analyses were recorded (we considered the diagnostic of
an adenoma as a “positive case” in the scope of this study).
For quantitative analyses, using one of the four microbubble displacement indicators (δ, ρ, γ or τ) as
an input feature, we developed machine learning models to differentiate between FNH and I-HCA.
For this binary classification task, the following four machine learning algorithms were applied
using the commercial software Matlab (©1994-2019 The MathWorks, Inc.)/“Statistics and Machine
Learning” toolbox: random forest (RF), k-nearest neighbour (KNN), support vector machine
(SVM), and logistic regression (LR). Default hyperparameters in Matlab implementations were
employed. We refer the interested reader to (22) (23) for additional information about above-
mentioned computer-assisted classification algorithms. We evaluated the diagnostic performances
through self-validation (the complete 47-tumours set was used for both train and test samples) and
through 10-fold-stratified cross-validation (the 47-tumours set was randomly partitioned into
complementary 90%-training and 10%-test subsets). The cross-validation steps were repeated 100
times with shuffling of the folds and test metric averages calculated. We also compared the medians
and interquartile ranges of all four indicators using the unpaired MannWhitney U-test. A p-value <
0.025 was considered to reflect statistical significance.
Qualitative CEUS analysis
FNH and I-HCA were correctly identified via qualitative CEUS in 27/29 and 17/18 tumours,
respectively (accuracy = 93.6%, AUROC=0.94, sensitivity = 94.4%, specificity = 93.1%, PPV =
89.5%, NPV = 96.4%, FPR = 6.9%, FNR = 5.6%; Table 2, first row).
Quantitative CEUS analysis
Figures 1 and 2 show typical microbubble transport fields as revealed by dynamic contrast imaging;
one clip (Fig. 1) is from an FNH patient and the other (Fig. 2) from an I-HCA patient. Of the four
tested transport indicators, divergence and centripetal indicators differed most significantly between
the two populations (MannWhitney test, p-value = 2 × 104 for divergence, and 1 × 107 for
centripetal indicator) (Figs. 3 and 4). The centripetal indicator served as a valuable binary classifier
in all tested machine learning systems (Table 2). In particular, using the naïve Bayes classifier
applied on the centripetal indicator, the diagnostic parameters were: accuracy = 95.9%, AUROC =
0.97, sensitivity = 93.4%, specificity = 97.6%, PPV = 95.3%, NPV = 96.7%, FPR = 2.4%, FNR =
6.6% (in average over the 100 cross-validation steps, FNH and I-HCA were thus correctly identified
in 28.3/29 and 16.8/18 tumours, respectively).
We show that the dense transport fields provide valuable kinetic information in CEUS time series;
the results are more accurate than those of qualitative visual analysis. Using the qualitative analysis,
one false negative case and two false positive cases were to deplore. Concerning the false negative
case, the filling direction was difficult to determine visually. Concerning the two false positive
cases, one tumour (44 mm) presented two feeding pedicles, and one (22 mm) underwent a too fast
filling. For both FNH tumours it was also difficult to appreciate visually the centrifugal filling. A
quantitative approach delivers reproducible results and minimises operator dependency, as visual
interpretation of CEUS images lacks a learning curve when the process is automated. Our method
deals with the intrinsic variations in spatio-temporal greys that are inevitable during dynamic
imaging. This allows numerical access to visual perceptions of microbubble trajectories. We used
four simple indicators (δ, ρ, γ, and τ) of transport field direction/orientation and amplitude. The
amplitude and curl indicators were not useful (Figs. 4b, c), whereas the divergence and centripetal
indicators were (Fig. 4a, d). Best results were obtained using the indicator τ which best fits the
initial centrifugal/centripetal tumour filling hypothesis (Figs. 4d). For its part, the divergence
operator gave decent results. In theory, the divergence of any vector field is positive for sources
(centrifugal trajectories) and negative for sinks (centripetal trajectories). The divergence operators
were positive for both FNH and I-HCA data; bolus arrival manifested as one or several sources of
microbubbles. However, for I-HCA lesions, the divergence operator was modulated by centripetal
filling, whereas the divergence operator was enhanced by centrifugal filling in FNH patients.
Using our quantitative method, diagnosis is near-instantaneous once the region of interest
(encompassing the tumour) is delineated. Although the duration of the temporal window for the
analysis must be sufficient to cover the filling phase, 2 s was adequate; this is a great advantage,
eliminating all long-term bias imparted by probe motion, and respiratory and other motion artefacts
Several limitations of our work must be mentioned, particularly the small sample size. This was a
single-centre retrospective study lacking an external validation cohort. Considering that only two
categories of focal liver lesions were examined (FNH and I-HCA), an inherent overestimation of
both qualitative and quantitative analysis has to be taken into account. Also, mean tumour diameter
was significantly smaller in the FNH group, associated with recruitment bias: only patients with
histological diagnoses obtained after surgical resection or via percutaneous biopsy were included in
the I-HCA group. However, in our centre, when an I-HCA tumour is identified using MRI (26) or
CEUS, a pathological analysis is performed only when the tumour diameter is > 3 cm. Thus, the I-
HCA group featured only tumours that met this criterion, unlike the FNH group, for which tumours
of all diameters (including small tumours) were evaluated. Also, the fact that any US artefacts can
intrinsically be interpreted as “false” motions by the transport equation constitutes a major source of
uncertainty. This may bias the microbubble estimations in transport fields, in turn affecting all four
image-based indicators. This is also of concern when brief US “shadow” artefacts develop in obese
patients (one of our cohort was obese and was constantly miss-classified by our quantitative
approach due to poor image quality). Similarly, in-plane and/or out-of-plane organ motion within
the image field-of-view must be no more than moderate. Please note that when organ motions are
large or complex, it is possible to pop microbubbles on-line to virtually repeat the imaging
session. Alternatively, image post-processing strategies may be valuable (24)(28) (Appendix A).
Finally, manually drawn masks encompassing lesions must exclude adjacent feeding arterials;
otherwise, the estimated displacement is likely to be calculated from the border to the centre of the
tumour, compromising FNH diagnosis.
In conclusion, this proof-of-concept study indicates that microbubble displacements evident on
CEUS can be used to efficiently diagnose FNH/I-HCA lesions. Machine learning allows for
computer-assisted diagnoses. In the future, we will optimise the model (28), enrol larger patient
cohorts, include other lesional features, and study other pathologies.
1. Cherqui D, Rahmouni A, Charlotte Fet al (1995) Management of focal nodular hyperplasia
and hepatocellular adenoma in young women: a series of 41 patients with clinical,
radiological, and pathological correlations. Hepatology 22(6):167481.
2. Burrowes DP, Medellin A, Harris AC, Milot L, Wilson SR (2017) Contrast-enhanced US
Approach to the Diagnosis of Focal Liver Masses. RadioGraphics 37(5):1388400.
3. Dioguardi Burgio M, Ronot M, Salvaggio G, Vilgrain V, Brancatelli G (2016) Imaging of
Hepatic Focal Nodular Hyperplasia: Pictorial Review and Diagnostic Strategy. Semin
Ultrasound CT MR 37(6):51124.
4. Trillaud H, Bruel JM, Valette PJ et al (2009) Characterization of focal liver lesions with
SonoVue-enhanced sonography: international multicenter-study in comparison to CT and
MRI. World J Gastroenterol 15(30):374856.
5. Baranes L, Chiaradia M, Pigneur F et al (2013) Imaging benign hepatocellular tumors: atypical
forms and diagnostic traps. Diagn Interv Imaging 94(78):67795.
6. Onofrio M, Crosara S, DeRobertis R, Canestrini S, Pozzi Mucelli R (2015) Contrast Enhanced
Ultrasound of Focal Liver Lesions. AJR 2015 205:5666.
7. Bartolotta TV, Taibbi A, Matranga D, Malizia G, Lagalla R, Midiri M (2010) Hepatic focal
nodular hyperplasia:contrast-enhanced ultrasound findings with emphasis on lesion size, depth
and liver echogenicity. Eur Radiol 20:2248-2256.
8. Bioulac-Sage P, Rebouissou S, Thomas C, et al (2007) Hepatocellular adenoma subtype
classification using molecular markers and immunohistochemistry. Hepatol Baltim Md
9. Laumonier H, Cailliez H, Balabaud C et al (2012) Role of contrast-enhanced sonography in
differentiation of subtypes of hepatocellular adenoma: correlation with MRI findings. AJR Am
J Roentgenol 199(2):3418.
10. Tranquart F, Mercier L, Frinking P, Gaud E, Arditi M (2012) Perfusion quantification in
contrast-enhanced ultrasound (CEUS)ready for research projects and routine clinical use.
Ultraschall Med. 33(1):S31-8.
11. Rognin NG, Arditi M, Mercier L, et al (2009) Parametric imaging of dynamic vascular
patterns of focal liver lesions in contrast-enhanced ultra-sound. IEEE Ultrasonics Symp Proc
12. Dietrich CF, Averkiou MA, Correas JM, Lasau N, Leen E, Piscaglia F (2012) An EFSUMB
introduction into dynamic contrast-enhanced ultrasound (DCE-US) for quantification of
tumour perfusion. Ultraschall in Med 33:344-351.
13. Strouthos C, Lampaksis M, Sboros V, McNeilly A, Averkiou M (2010) Indicator dilution
models for the quantification of microvascular blood flow with bolus administration of
ultrasound contrast agents. IEEE UFFC 57(6):1296-1310.
14. Mischi M, Kuenen MPJ, Wijkstra H (2012) Angiogenesis imaging by spatiotemporal analysis
of ultrasound contrast agent dispersion kinetics. IEEE Transactions on Ultrasonics,
Ferroelectrics, and Frequency Control 59(4):621-629.
15. Denis de Senneville B, Novell A, Arthuis C et al (2018) Development of a fluid dynamic
model for quantitative contrast-enhanced ultrasound imaging, IEEE Transactions on Medical
Imaging 37(2):372-383.
16. Corpetti E, Mémin E, Pérez P (2002) Dense estimation of fluid flows. IEEE Transactions on
Pattern Analysis and Machine Intelligence 24(3):365-380.
17. Horn B, Schunk B (1981) Determining optical flow. Artificial Intelligence 17:185-203.
18. Zachiu C, Papadakis N, Ries M, Moonen CTW, Denis de Senneville B (2015) An improved
optical flow tracking technique for real-time MR-guided beam therapies in moving organs.
Physics in Medicine and Biology 60(23):9003.
19. Laumonier H, Bioulac-Sage P, Laurent C, Zucman-Rossi J, Balabaud C, Trillaud H (2008)
Hepatocellular adenomas: magnetic resonance imaging features as a function of molecular
pathological classification. Hepatol Baltim Md 48(3):80818.
20. van Aalten SM, Thomeer MGJ, Terkivatan T et al (2011) Hepatocellular adenomas:
correlation of MR imaging findings with pathologic subtype classification. Radiology
21. Quaia E, Calliada F, Bertolotto M et al (2004) Characterization of focal liver lesions with
contrast-specific US modes and a sulfur hexafluoride-filled microbubble contrast agent:
diagnostic performance and confidence. Radiology 232(2):42030.
22. Kohavi R (1995) A Study of Cross-Validation and Bootstrap for Accuracy Estimation and
Model Selection, Morgan Kaufmann, 1137-1143.
23. Cantor, SB, Kattan, MW (2000) Determining the Area under the ROC Curve for a Binary
Diagnostic Test. Medical Decision Making 20(4), 468470.
24. De Luca V, Székely G, Tanner C (2015) Estimation of large-scale organ motion in B-mode
ultrasound image sequences: A survey. Ultrasound Med Biol 41(12):3044-3062.
25. Pratikakis I, Barillot C, Hellier P, Memin E (2003) Robust multiscale deformable registration
of 3d ultrasound images. International Journal of Image and Graphics 3(4):547-565.
26. Bise S, Frulio N, Hocquelet A et al (2018) New MRI features improve subtype classification
of hepatocellular adenoma. European Radiology,
27. Cifor A, Risser L, Chung D, Anderson EM, Schnabel JA (2013) Hybrid feature-based
diffeomorphic registration for tumor tracking in 2-D liver ultrasound images, IEEE Trans Med
Imaging 32( 9):16471656.
28. Ackermann D, Schmitz G (2016) Detection and tracking of multiple microbubbles in
ultrasound b-mode images. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency
Control 63(1):72-82.
29. Shapiro LG, Stockman GC (2001) Computer Vision. Prentice Hall 137-150.
30. Marquardt D (1963) An algorithm for least squares estimation on nonlinear parameters. SIAM
Journal on Applied Mathematics. 11:431-441.
Statistical significance
44 ± 11
40.5 ± 11
42 ± 11
Tumor size
29 ± 16
60.5 ± 29
36 ± 28
Histological data
(available/not available)
Table 1. Demographic characteristics. Median values of age and tumor size are shown with
standard deviations and minimum-maximum intervals in parentheses. Statistical comparison of age
and tumor size between FNH and I-HCA groups were performed using an unpaired MannWhitney
U-test (last column), a p-value < 0.025 was considered to reflect statistical significance.
Qualitative analysis
Divergence (δ)
Logistic Regression
86.6 ± 14.9
0.82 ± 0.23
74.1 ± 35.1
94.3 ± 16.5
81.7 ± 34.7
87.9 ± 16.5
Support Vector
86.9 ± 14.6
0.82 ± 0.21
75.5 ± 33.8
94.1 ± 16.4
83.1 ± 33.0
88.6 ± 15.7
Naive Bayes
86.6 ± 14.8
0.81 ± 0.23
74.9 ± 34.6
94.1 ± 16.2
82.0 ± 34.0
88.1 ± 16.5
Random Forest
85.4 ± 14.5
0.75 ± 0.25
67.5 ± 33.9
96.6 ± 15.0
84.5 ± 34.1
83.9 ± 17.4
Curl (ρ)
Logistic Regression
77.2 ± 16.0
0.68 ± 0.25
60.1 ± 40.3
87.9 ± 24.5
64.4 ± 41.7
80.1 ± 20.8
Support Vector
67.4 ± 15.0
0.52 ± 0.28
42.0 ± 43.9
84.3 ± 31.0
39.6 ± 42.7
68.0 ± 25.2
Naive Bayes
76.7 ± 16.3
0.69 ± 0.25
60.2 ± 41.5
87.0 ± 24.8
61.7 ± 41.9
80.4 ± 21.0
Random Forest
64.6 ± 12.9
0.40 ± 0.26
33.9 ± 41.6
84.2 ± 31.5
31.8 ± 40.0
64.3 ± 23.8
Amplitude (γ)
Logistic Regression
72.2 ± 15.9
0.56 ± 0.28
48.8 ± 42.4
86.9 ± 27.4
52.5 ± 44.4
74.1 ± 22.7
Support Vector
67.2 ± 14.7
0.52 ± 0.27
40.6 ± 44.1
83.9 ± 31.0
37.8 ± 41.9
68.5 ± 25.0
Naive Bayes
70.3 ± 15.4
0.54 ± 0.28
48.6 ± 43.3
83.8 ± 29.8
49.0 ± 43.3
73.5 ± 23.9
Random Forest
80.2 ± 16.2
0.70 ± 0.28
61.6 ± 38.6
91.9 ± 20.9
71.4 ± 40.7
80.8 ± 20.0
Centripetal indicator (γ)
Logistic Regression
95.7 ± 10.1
0.97 ± 0.09
93.5 ± 19.6
97.1 ± 11.2
94.9 ± 17.7
96.8 ± 10.3
Support Vector
95.8 ± 10.0
0.97 ± 0.09
92.8 ± 21.3
97.5 ± 9.4
94.6 ± 19.1
96.7 ± 9.9
Naive Bayes
95.9 ± 9.8
0.97 ± 0.08
93.4 ± 19.8
97.6 ± 10.0
95.3 ± 17.5
96.7 ± 10.4
Random Forest
91.8 ± 11.9
0.92 ± 0.13
83.4 ± 28.0
97.0 ± 10.5
91.5 ± 24.3
92.4 ± 12.6
Table 2. Diagnostic performances of the various classifiers. Qualitative (i.e., visual) and
quantitative scores are given; the latter were derived via evaluation of divergence δ, curl ρ,
amplitude γ, and centripetal indicator τ (after 10-fold cross-validation) by various machine-learning
algorithms. AUROC: area under the ROC curve; PPV: positive predictive value; NPV: negative
predictive value. Accuracies, sensitivities, specificities, PPVs, and NPVs are shown in percentages.
Quantitative indicators are shown with standard deviations and 95% confidence intervals in
Fig. 1. Typical results obtained when evaluating an FNH lesion. Data obtained at different CEUS
timepoints are shown: 0.5 s (left column), 1 s (middle column), and 1.5 s (right column) after bolus
arrival. The manually drawn mask encompassing the lesion is shown in (a). Contrast images (top
row) and estimated, apparent transport vector fields (bottom row). The flow field exhibits fast
centrifugal filling of the lesion from a central vessel and radial vascular branches. The pixel-wise
centripetal indicator is shown in the insets of the bottom row (note the large negative values,
attributable to centrifugal filling of the lesion, and the small positive values attributable to the
tumour feeding arterial).
Fig. 2. Typical results from a patient with an I-HCA lesion. The manually drawn mask
encompassing the lesion is shown in (a). Data obtained at different times during CEUS are shown:
0.5 s (left column), 1 s (middle column), and 1.5 s (right column) after bolus arrival. Contrast
images (top row) and estimated, apparent vector transport fields (bottom row). The flow field is
hyper-enhanced in the arterial phase (enhancement commences peripherally) and exhibits rapid
centripetal filling. The pixel-wise centripetal indicator is shown as insets in the bottom row (note
the large positive values, attributable to centripetal filling of the lesion).
Fig. 3. Boxplots of indicators of the four dense transport fields (divergence δ [a], curl ρ [b],
amplitude γ [c], and centripetal indicator τ [d]) for both patient populations (FNH vs. I-HCA self-
validations). The medians are shown by the central marks, the first and third quartiles are the edges
of the boxes, the whiskers extend to the most extreme timepoints not considered to be outliers, and
the outliers are individually marked in red.
Fig. 4. ROC curves obtained using the four quantitative indicators (divergence δ [a], curl ρ [b],
amplitude γ [c], and centripetal indicator τ [d]) as binary classifiers (naive Bayes) for the two
populations (i.e., FNH vs. I-HCA) after 10-fold cross-validation.
APPENDIX 1: Estimation of apparent microbubble displacement during CEUS
This appendix deals with numerical implementation of the algorithm estimating microbubble
displacement during CEUS. For each CEUS clip, the lesion was first manually delineated on a
hyper-enhanced image. A binary mask was then constructed (this is termed Γ below). We then
proceeded as follows:
Estimation of CEUS dense transport fields
We used the transport equation to estimate the apparent microbubble transport field (
), as
suggested in (15):
where I denotes the grey level intensity on CEUS images and It the partial temporal derivative of I.
Practically, the desired transport field V was estimated between two points in time (t and t + δt,
respectively) on a pixel-by-pixel basis using the so-called optical flow process (17). The
algorithm yields the displacement between two images when the following function is optimised
 
where  is the image-coordinate domain,  the estimated pixel-wise transport vector
components, and    the spatial location. All slices were re-sampled via bi-cubic interpolation to
obtain a common isotropic, in-plane, 0.25 × 0.25-mm2 pixel representation. A spatial low-pass filter
was then applied (29) (the cut-off frequency was the proportional pixel fraction of the original
image, divided by 16, as suggested by (15)) to mitigate the impact of US speckles on the transport
equation. An in-house developed, freely available, software provided 2D transport fields using the
optical flow metric of Eq. (2) ( The reader is referred to
(15) for additional details on the numerical implementation of Eq. (2).
Note that possible periodic, spontaneous, and drift displacements of tissue must be initially
compensated for (24)(25), because they may change image intensities over time; Eq. 1 would
(erroneously) attribute such changes to microbubble transport. As proposed in (15), B-mode
images, which are not prone to contrast enhancement, are used to this end. We estimated
translational displacements restricted to the binary mask Γ. We used a gradient-driven descent
algorithm maximising the inter-correlation coefficients. This translation was used to compensate for
displacement of imaged tissues on CEUS images prior to microbubble transport estimation
employing Eq. (2).
Pixel-wise analysis of dense flow fields
We next calculated a pixel-wise understanding of flow directions/orientations and amplitude, as
Maps of sources and sinks: Sources and sinks in the transport were analysed using the divergence
operator. Mathematically, the divergence of a two-dimensional vector
  is expressed as:
 
 
 (3)
The final, discrete divergence operator employed in numerical implementation was:
)i,j,t     (4)
where    denotes the pixel coordinates and t the frame acquisition time. We emphasise that
positive and negative values are associated with pixels located near sources and sinks, respectively.
Vortex maps: Local vortices in the estimated transport vectors were analysed with the aid of the
curl operator. Mathematically, the curl of
is expressed as:
 
 
 (5)
The resulting discrete curl operator is:
)i,j,t     (6)
Amplitude maps: The amplitudes of estimated transport vectors were calculated as Euclidian
distances. Mathematically, the magnitude of
is expressed by:
Centripetal indicator maps: The convergence of estimated transport vectors towards the centre of
tumour were calculated with the aid of the scalar product. The cosine of the angle formed by two
is expressed by:
 
In our study,
is any vector of the estimated flow field, and
has the same origin as
, but the
extremity located at the gravity centre of tumour (i.e, the centre of mass of the binary mask Γ). That
way, the cosine of the angle 
lies in intervals [-1,0] and [0,1] for centrifugal and centripetal
, respectively.
Quantitative analysis of dense flow fields
As described above, we created four sets of pixel-wise maps (of divergence, curl, amplitude and
convergence towards the centre of tumour). Each set was then simplified to a single parameter as
follows. The spatiotemporal averages of each map were individually computed under a mask
defining the imaged tissue (i.e., Γ) within the relevant time window. The duration spanned by that
window is termed ΔT below and commenced at the bolus arrival time t0. Spatiotemporal averaging
was weighted by the grey level intensity in CEUS image I; thus, the values for scenarios exhibiting
identical microbubble transport behaviours were identical irrespective of the numbers of pixels
evidencing microbubbles. The divergence and curl operators were termed δ and ρ, respectively. We
measured the absolute value of curl; thus, the direction of vortex rotation didn’t affected analysis.
The centripetal indicator was termed τ.
  
 (9)
  
  (10)
  
 (11)
   
  (12)
  
   (13)
Determination of the temporal window
The temporal window of analysis was of duration ΔT and commenced at the bolus arrival time t0;
this was determined individually for each patient. To this end, we used a published time intensity
curve (TIC) widely employed to determine time constants (10). The average US image intensity
over Γ (termed ) was analysed as a function of time using a two-compartment model, as
   (14)
where I is the asymptotic US signal enhancement, and k the uptake rate. I, t0, and k were
computed using the LevenbergMarquardt least-square fit (30) employing all images of the US
sequence. The use of a simple two-compartment model was motivated by the fact that only the rise
step was screened. The goodness-of-fit was considered acceptable when the Pearson correlation
coefficient (r2) was > 0.95. In such cases, the t0 values chosen earlier served as the start times for
the temporal windows.
Hardware and implementation
Our test platform was an Intel 2.5 GHz i7 workstation (eight cores) with 32 GB of RAM. The
implementation was performed in C++ and parallelised via multi-threading.
The English in this document has been checked by at least two professional editors, both native
speakers of English. For a certificate, please see:
... In the DEGUM study, CEUS correctly diagnosed 57.9% of the adenomas [57]. Computer-assisted diagnosis can also be used to improve the accuracy of differential diagnosis by CEUS between FNH and adenoma [102]. ...
This is my Habilitation thesis, describing all my scientific achievements and contributions.
... The used tool embeds an "optical flow" algorithm [13,14] designed to mimic the human visual perception of object transport in image series. We quantify divergence (sources and sinks) and amplitudes in obtained dense transport fields, which provided very simple indicators of displacement vector orientations and magnitudes [15]. ...
Full-text available
Physical activity is increasingly recognized as a strategy able to improve cancer patient outcome, and its potential to enhance treatment response is promising, despite being unclear. In our study we used a preclinical model of prostate cancer to investigate whether voluntary wheel running (VWR) could improve tumor perfusion and enhance radiotherapy (RT) efficiency. Nude athymic mice were injected with PC-3 cancer cells and either remained inactive or were housed with running wheels. Apparent microbubble transport was enhanced with VWR, which we hypothesized could improve the RT response. When repeating the experiments and adding RT, however, we observed that VWR did not influence RT efficiency. These findings contrasted with previous results and prompted us to evaluate if the lack of effects observed on tumor growth could be attributable to the physical activity modality used. Using PC-3 and PPC-1 xenografts, we randomized mice to either inactive controls, VWR, or treadmill running (TR). In both models, TR (but not VWR) slowed down tumor growth, suggesting that the anti-cancer effects of physical activity are dependent on its modalities. Providing a better understanding of which activity type should be recommended to cancer patients thus appears essential to improve treatment outcomes.
... Moreover, the precision approach can also be used for preventive and surveillance measures of diseases. treatment efficiency and real time monitoring of drugs [39,40]. Microbubbles loaded with drug are guided carriers that deliver medicine to targeted sites [2,30,41]. ...
Full-text available
Microbubbles are nanosized gas-filled bubbles. They are used in clinical diagnostics, in medical imaging, as contrast agents in ultrasound imaging, and as transporters for targeted drug delivery. They can also be used to treat thrombosis, neoplastic diseases, open arteries and vascular plaques and for localized transport of chemotherapies in cancer patients. Microbubbles can be filled with any type of therapeutics, cure agents, growth factors, extracellular vesicles, exosomes, miRNAs, and drugs. Microbubbles protect their cargo from immune attack because of their specialized encapsulated shell composed of lipid and protein. Filled with curative medicine, they could effectively circulate through the whole body safely and efficiently to reach the target area. The advanced bubble-based drug-delivery system, integrated with artificial intelligence for guidance, holds great promise for the targeted delivery of drugs and medicines.
... In the DEGUM study, CEUS correctly diagnosed 57.9% of the adenomas [13]. Computer-assisted diagnosis can also be used to improve the accuracy of differential diagnosis by CEUS between FNH and adenoma [30]. ...
Full-text available
Aim: Contrast-enhanced ultrasound (CEUS) has become a relevant imaging method for the evaluation of focal liver le-sions (FLL). The aim of this study was to evaluate the performance of CEUS for the assessment of focal nodular hyperplasia (FNH) in a large study group. Material and methods: We performed a multicentre prospective observational study, which included successive CEUS examinations from fourteen Romanian centres. CEUS examinations were performed in de novo FLL, using low mechanical index ultrasound, following an intravenous bolus of 2.4 ml SonoVue. CEUS was considered conclusive for FNH if a typical pattern was present following contrast (rapid "spoke-wheel" enhancement during the arterial phase, hyperenhanced lesion during venous phase, hyper- or isoenhanced in the late phase). In all cases a reference method was available (contrast enhanced CT or MRI or biopsy). The trial was registered in (Identifier NCT01329458). Results: During the 6 years study, 2062 "de novo" FLL were evaluated by CEUS. From this cohort, 94/2062 (4.5%) had a typical enhancing pattern for FNH as described in the EFSUMB guidelines. Contrast enhanced CT/MRI and biopsy diagnosed additional 15 FNH. From the 94 cases diagnosed as FNH by CEUS, in nine the final diagnosis was different (five of them adenomas). CEUS had 85% sensitivity, 99.5% specificity, 90.4% positive predictive value, 99.2% negative predictive value and 98.8% diagnostic accuracy for the diagnosis of FNH. Conclusions: CEUS is a sensitive and very specific method for the diagnosis of FNH.
... To avoid radiation exposure, we replaced ERAR with CEUS in this study. CEUS is a developing modality that supersedes standard vascular ultrasound imaging and complements other modalities such as computed topography and magnetic resonance angiograms [22,23]. Administered intravenously, the contrast is microbubbles filled with gas, surrounded by a stabilizing shell. ...
Full-text available
Background Endoscopic retrograde appendicitis therapy (ERAT) is an emerging endoscopic treatment modality for acute uncomplicated appendicitis (AUA) supported by several case series. However, to date, systematic studies have not been conducted in children and the prospective comparative data are lacking. Moreover, due to a concern for future malignancy risk in children from ionizing radiation, we used contrast-enhanced ultrasound (CEUS) instead of endoscopic retrograde appendiceal radiography (ERAR). Therefore, we conducted a prospective, randomized control clinical trial to compare the modified ERAT (mERAT) to antibiotic therapy in children with AUA. The aim of this study was to evaluate the safety and feasibility and of mERAT in the treatment of hospitalized children with AUA. Methods Children with AUA, confirmed by ultrasonography and or abdominal computed tomography, were consecutively enrolled from October 2018 to February, 2020. They were randomly assigned to receive mERAT or routine antibiotic treatment. Patients were followed until May, 2020. Th primary outcome variable was the duration of relief of the abdominal pain after treatment. We collected patient’s demographics, ultrasonic imaging findings, colonoscopy findings, and treatment outcomes of the mERAT and adverse even associated with mERAT. Results A total of 83 children were enrolled. 36 were randomized to mERAT and 47 to antibiotics treatment. All children in the mERAT group had endoscopic confirmed acute uncomplicated appendicitis, and there were no significant complications. However, 9 of patients in antibiotic group were poor responsive to treatment and switched to mERAT. The overall success rate of treatment with mERAT (100%) was significantly higher than that of antibiotics (80.9%) (P = 0.004). The median time to discharge was significantly shorter in mERAT group than in antibiotics treatment group [6.0 ± 1.76 days] (P = 0.004). Conclusions mERAT provide a new alternative therapeutic option for childhood with AUA, especially for families who are reluctant to undergo an appendectomy.
Purpose: To investigate the differential diagnostic value of computer-aided color parametric imaging (CPI) and contrast-enhanced ultrasound (CEUS) in hepatocellular adenoma (HCA) and well-differentiated hepatocellular carcinoma (wHCC). Method: A total of 38 patients who underwent CEUS and were pathologically diagnosed with HCA (10 cases) and wHCC (28 cases) were reviewed retrospectively. The differences between the radiological features of HCA and wHCC were compared by two readers, blinded to the final diagnosis. Results: (a) Sonographic features: on gray-scale ultrasound, halo sign was more common in wHCC than in HCA (60.7% vs. 10.0%, p = 0.009). On CEUS, hyper- or isoenhancement was more common in HCA in the portal phase (90.0% vs. 50.0%; p = 0.022). On CPI mode, HCA was inclined toward centripetal enhancement (60.0% vs. 14.3% p = 0.010). HCA was characterized by the presence of pseudocapsule enhancement (50.0% vs. 14.3%; p = 0.036). Quantitative analysis showed that the arrival time of HCA was earlier than that of wHCC (12.4 ± 3.7 s vs. 15.9 ± 3.2 s; p = 0.006). (b) Interobserver agreement was improved by using CPI compared with CEUS. The diagnostic sensitivity, specificity, and accuracy of the combination were 80.0%, 85.7%, and 84.2%, respectively. Conclusions: CEUS combined with CPI can provide effective information for the differential diagnosis of HCA and wHCC, especially for the non-experienced radiologists.
Objective: Our aim was to determine independent risk factors of clinical bleeding of hepatocellular adenoma (HCA) in order to define a better management strategy. Summary background data: HCA is a rare benign liver tumor with severe complications: malignant transformation which is rare (5-8%) and more often, hemorrhage (20-27%). To date, only size > 5 cm and histological subtype (possibly sonic hedgehog) are associated with bleeding, but these criteria are not clearly established. Methods: We retrospectively collected data from a cohort of 268 patients with HCA managed in our tertiary center, from 1984 to 2020 and focused on clinical bleeding. Hemorrhage was considered as severe when it required intensive care and moderate when bleeding symptoms required a hospitalization. We included 261 patients, of which 130 (49.8%) had multiple HCAs or liver adenomatosis. All surgical specimen and liver biopsy were reviewed by an experienced liver pathologist and reclassified in the light of the current immunohistochemistry. Mean duration of follow-up was 93.3 months (range 1-363). We analyzed type, frequency, consequences of bleeding and risk factors among clinical data and HCA characteristics. Results: Eighty-three HCA (31.8%) were hemorrhagic. There were 4 pregnant women with one newborn death. One patient died before treatment. Surgery was performed in 78 (94.0%) patients. Mortality was nil and severe complications occurred in 11.5%. Multivariate analysis identified size (OR 1.02 [1.01-1.02], p < 0.001), shHCA (OR 21.02 [5.05-87.52], p < 0.001), b-catenin mutation on exon 7/8 (OR 6.47 [1.78-23.55], p = 0.0046), chronic alcohol consumption (OR 9.16 [2.47-34.01], p < 0.001) as independent risk factors of clinical bleeding. Conclusions: This series, focused on the hemorrhagic risk of HCA, shows that size, but rather more molecular subtype is determinant in the natural history of HCA.
The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies.
Contrast enhanced ultrasound (CEUS) with dynamic real-time depiction of tumor perfusion and the fact that it is a purely intravascular agent, accurately reflecting tumoral and inflammatory blood flow. When using special external software, dynamic perfusion parameters can be recorded using motion correction. The most common parameters of a dynamic perfusion analysis are time to peak (TTP) and area under the curve (AUC), the mean transit time (mTT), the wash in and wash out rate, and the peak enhancement. With the wash in and wash out kinetics of the CEUS perfusion, different malignant or benign liver tumors can be possible. CEUS Perfusion can also be very helpful in assessing early treatment response to malignant liver lesions. CEUS is gaining ever-increasing acceptance in the preoperative and postoperative evaluation of liver-transplanted patients.
Fusion imaging opens up new possibilities for intervention planning, implementation, and control, but also offers the opportunity to better assess remission or progress in the follow-up of liver tumor treatment. Contrast enhanced ultrasound (CEUS) with image fusion enables the experienced radiological examiner to dynamically record the tumor microvascularization down to the capillary level. It can facilitate the diagnosis and therapy control after liver interventions. In addition to the primary applications of image fusion in the diagnosis and treatment of liver lesions, further useful indications can be integrated into the daily work routine.
Full-text available
Focal liver lesions are commonly encountered and often demonstrate nonspecific findings at initial imaging. Although most incidentally discovered liver lesions are benign, their noninvasive diagnosis is necessary, especially if they are large or atypical. Imaging characterization of focal liver lesions and exclusion of malignancy are of prime importance, particularly in high-risk populations. Contrast agent-enhanced ultrasonography of liver lesions is both accurate and reproducible for evaluation of benign and malignant liver tumors. Use of an imaging algorithm and a controlled sonographic technique, including dedicated arterial phase cine imaging and imaging every 30 seconds in the portal venous phase and the delayed (or late) phase, is essential for accurate characterization. This algorithmic analysis of focal liver lesions focuses first on the determination of malignancy by imaging the portal venous phase and the late phase; washout in these phases correlates with a malignant tumor, and sustained enhancement in these phases is suggestive that a lesion is benign. In addition, the timing and the intensity of washout differentiate hepatocellular malignancies from nonhepatocellular malignancies. Nonhepatocellular tumors demonstrate early and strong washout, whereas hepatocellular malignancies show delayed and weak washout. Subsequent analysis of dynamic real-time enhancement patterns in the arterial phase demonstrates specific enhancement patterns of common benign and malignant focal liver lesions. Hemangiomas show classic peripheral nodular enhancement, and spoke-wheel centrifugal enhancement is suggestive of focal nodular hyperplasia. Hepatic adenomas may show centripetal filling. However, arterial phase enhancement in malignancy has less specificity. Online supplemental material is available for this article. ©RSNA, 2017 •.
Full-text available
The purpose of this article is to discuss the use of contrast-enhanced ultra-sound (CEUS) in focal liver lesions. Focal liver lesions are usually detected incidentally during abdominal ultrasound. The injection of microbubble ultrasound contrast agents improves the characterization of focal liver lesions that are indeterminate on conventional ultrasound. The use of CEUS is recommended in official guidelines and suggested as a second diagnostic step after ultrasound detection of indeterminate focal liver lesions to immediately establish the diagnosis, especially for benign liver lesions, such as hemangiomas, avoiding further and more expensive examinations.
Conference Paper
Full-text available
We review accuracy estimation methods and compare the two most common methods: crossvalidation and bootstrap. Recent experimental results on arti cial data and theoretical results in restricted settings have shown that for selecting a good classi er from a set of classiers (model selection), ten-fold cross-validation may be better than the more expensive leaveone-out cross-validation. We report on a largescale experiment|over half a million runs of C4.5 and a Naive-Bayes algorithm|to estimate the e ects of di erent parameters on these algorithms on real-world datasets. For crossvalidation, we vary the number of folds and whether the folds are strati ed or not � for bootstrap, we vary the number of bootstrap samples. Our results indicate that for real-word datasets similar to ours, the best method to use for model selection is ten-fold strati ed cross validation, even if computation power allows using more folds. 1
Objective MRI is crucial for the classification of hepatocellular adenomas (HCA) into subtypes. Our objective was to review and increase MRI criteria for subtype classification and define the limits. Methods Pathological and radiological data of 116 HCAs were retrospectively analyzed to investigate MRI features of HCA pathological subtypes. Risk for complication was also evaluated with regard to subtype and tumor size. Results 38/43 (88%) HNF1α-mutated HCAs (H-HCAs) were discriminated by (i) fatty component (homogeneous or heterogeneous) and (ii) hypovascular pattern, with a sensitivity of 88% and a specificity of 97%. 51/58 (88%) inflammatory HCAs (IHCAs) displayed features of sinusoidal dilatation (SD) including three different patterns (global SD, atoll sign, and a new “crescent sign” corresponding to a partial peripheral rim, hyperintense on T2W and/or arterial phase with persistent delayed enhancement). Sensitivity was 88% and specificity 100%. However, some HCA remained unclassifiable by MRI: HCA remodeled by necrotic/hemorrhagic changes covering > 50% of the lesion, H-HCAs without steatosis, IHCAs without SD, β-catenin-mutated and unclassified HCAs. Regarding malignant transformation (5/116) and bleeding (24/116), none was observed when the HCA diameter was smaller than 5.2 cm and 4.2 cm, respectively. Conclusion Based on the largest series evaluated until now, we identified several non-described MRI features and propose new highly sensitive and specific MRI criteria. With the addition of these new features, 88% of the two main HCA subtypes could be identified. Key Points • HNF1α-mutated hepatocellular adenomas (H-HCA) are characterized by the presence of fat and hypovascular pattern in MRI. • Inflammatory hepatocellular adenomas (I-HCA) are characterized by different patterns translating sinusoidal dilatation including the newly described crescent sign. • No MRI specific pattern was identified for β-catenin-mutated HCA (b-HCA).
Contrast-enhanced ultrasound (CEUS) is a noninvasive imaging technique extensively used for blood perfusion imaging of various organs. This modality is based on the acoustic detection of gas-filled microbubble contrast agents used as intravascular flow tracers. Recent efforts aim at quantifying parameters related to the enhancement in the vascular compartment using time-intensity curve (TIC), and at using these latter as indicators for several pathological conditions. However, this quantification is mainly hampered by two reasons: first, the quantification intrinsically solely relies on temporal intensity variation, the explicit spatial transport of the contrast agent being left out. Second, the exact relationship between the acquired US-signal and the local microbubble concentration is hardly accessible. The current study introduces the use of a fluid dynamic model for the analysis of dynamic CEUS (DCEUS), in order to circumvent the two above mentioned limitations. A new kinetic analysis is proposed in order to quantify the velocity amplitude of the bolus arrival. The efficiency of proposed methodology is evaluated both in-vitro, for the quantitative estimation of microbubble flow rates, and in-vivo, for the classification of placental insufficiency (control vs. ligature) of pregnant rats from DCEUS. Besides, for the in-vivo experimental setup, we demonstrated that the proposed approach outperforms the performance of existing TICbased methods.
Focal nodular hyperplasia (FNH) is the second most common benign solid liver lesion after hemangioma, occurring more frequently in young women. The prime differential diagnoses include hepatocellular adenoma, hepatocellular carcinoma, and hypervascular metastasis. As the management of FNH is typically conservative, imaging plays a key role in diagnostic pathway, and misdiagnosis may have a major clinical effect. In this article, we describe the ultrasound, computed tomography, and magnetic resonance imaging features of FNH, underlining the importance of typical radiological features that allow a specific noninvasive diagnosis. We present a large spectrum of a typical imaging findings that FNH may present and discuss the up-to-date diagnostic strategy.
The imaging of microvessels and the quantification of their blood flow is of particular interest in the characterization of tumor vasculature. The imaging resolution (50-200 μm) of high frequency ultrasound (20-50 MHz) is not sufficient to image microvessels (~10 μm) and Doppler sensitivity is not high enough to measure capillary blood flow (~1mm/s). For imaging of blood flow in microvessels our approach is to detect single microbubbles (MBs), track them over several frames and to estimate their velocity. First, positions of MBs will be detected by separating B-mode frames in a moving foreground and a static background. For the crucial task of association of these positions to tracks we implemented a modified Markov Chain Monte Carlo Data Association (MCMCDA) algorithm, which can handle a high number of MBs. False alarms, the detection, initiation and termination of MBs tracks are incorporated in the underlying model. To test the algorithms performance an ultrasound imaging simulation of a vessel tree with flowing MBs was set up (resolution 148 μm). The trajectories and flow velocity in the vessels with a lateral distance of 100 μm were reconstructed with super-resolution. In a phantom experiment, a suspension of MBs was pumped through a tube (diameter 0.4 mm) at speeds of 2.2, 4.2, 6.3 and 10.5 mm/s and was imaged with a Vevo2100 system (Visualsonics). The estimated MBs' mean speeds were 2.1, 4.7, 7 and 10.5 mm/s. To demonstrate the applicability for in vivo measurements, a tumor xenograft bearing mouse was imaged by this approach. The tumor vasculature was visualized with higher resolution than in a maximum intensity projection image and the velocity values were in the expected range of 0 to 1 mm/s.
Magnetic resonance (MR) guided high intensity focused ultrasound and external beam radiotherapy interventions, which we shall refer to as beam therapies/interventions, are promising techniques for the non-invasive ablation of tumours in abdominal organs. However, therapeutic energy delivery in these areas becomes challenging due to the continuous displacement of the organs with respiration. Previous studies have addressed this problem by coupling high-framerate MR-imaging with a tracking technique based on the algorithm proposed by Horn and Schunck (H and S), which was chosen due to its fast convergence rate and highly parallelisable numerical scheme. Such characteristics were shown to be indispensable for the real-time guidance of beam therapies. In its original form, however, the algorithm is sensitive to local grey-level intensity variations not attributed to motion such as those that occur, for example, in the proximity of pulsating arteries. In this study, an improved motion estimation strategy which reduces the impact of such effects is proposed. Displacements are estimated through the minimisation of a variation of the H and S functional for which the quadratic data fidelity term was replaced with a term based on the linear L¹norm, resulting in what we have called an L²–L¹ functional. The proposed method was tested in the livers and kidneys of two healthy volunteers under free-breathing conditions, on a data set comprising 3000 images equally divided between the volunteers. The results show that, compared to the existing approaches, our method demonstrates a greater robustness to local grey-level intensity variations introduced by arterial pulsations. Additionally, the computational time required by our implementation make it compatible with the work-flow of real-time MR-guided beam interventions. To the best of our knowledge this study was the first to analyse the behaviour of an L¹-based optical flow functional in an applicative context: real-time MR-guidance of beam therapies in moving organs.
Reviewed here are methods developed for following (i.e., tracking) structures in medical B-mode ultrasound time sequences during large-scale motion. The resulting motion estimation problem and its key components are defined. The main tracking approaches are described, and their strengths and weaknesses are discussed. Existing motion estimation methods, tested on multiple in vivo sequences, are categorized with respect to their clinical applications, namely, cardiac, respiratory and muscular motion. A large number of works in this field had to be discarded as thorough validation of the results was missing. The remaining relevant works identified indicate the possibility of reaching an average tracking accuracy up to 1-2 mm. Real-time performance can be achieved using several methods. Yet only very few of these have progressed to clinical practice. The latest trends include incorporation of complementary and prior information. Advances are expected from common evaluation databases and 4-D ultrasound scanning technologies.
Management of patients with a benign hepatocellular tumor relies largely on imaging data; the diagnosis of focal nodular hyperplasia (FNH) must be made with certainty using MRI, because no other clinical or laboratory data can help diagnosis. It is also essential to identify adenomas to manage them appropriately. The radiological report in these situations is therefore of major importance. However, there are diagnostic traps. The aim of this paper is to present the keys to the diagnosis of benign lesions and to warn of the main diagnostic pitfalls.