[show abstract][hide abstract] ABSTRACT: The European Society of Cardiology recommends that patients with >10% area of ischemia should receive revascularization. We investigated inter-observer variability for the extent of ischemic defects reported by different physicians and by different software tools, and if inter-observer variability was reduced when the physicians were provided with a computerized suggestion of the defects.
Twenty-five myocardial perfusion single photon emission computed tomography (SPECT) patients who were regarded as ischemic according to the final report were included. Eleven physicians in nuclear medicine delineated the extent of the ischemic defects. After at least two weeks, they delineated the defects again, and were this time provided a suggestion of the defect delineation by EXINI HeartTM (EXINI). Summed difference scores and ischemic extent values were obtained from four software programs.
The median extent values obtained from the 11 physicians varied between 8% and 34%, and between 9% and 16% for the software programs. For all 25 patients, mean extent obtained from EXINI was 17.0% (+/- standard deviation (SD) 14.6%). Mean extent for physicians was 22.6% (+/- 15.6%) for the first delineation and 19.1% (+/- 14.9%) for the evaluation where they were provided computerized suggestion. Intra-class correlation (ICC) increased from 0.56 (95% confidence interval (CI) 0.41-0.72) to 0.81 (95% CI 0.71-0.90) between the first and the second delineation, and SD between physicians were 7.8 (first) and 5.9 (second delineation).
There was large variability in the estimated ischemic defect size obtained both from different physicians and from different software packages. When the physicians were provided with a suggested delineation, the inter-observer variability decreased significantly.
BMC Medical Imaging 01/2014; 14(1):5. · 1.09 Impact Factor
[show abstract][hide abstract] ABSTRACT: The aim of this myocardial perfusion imaging (MPI) study was to compare the diagnostic performance of two computer-aided diagnosis (CAD) systems, EXINI Heart(TM) (EXINI), and PERFEX(TM) (PERFEX) Emory Cardiac Toolbox (ECT), and the summed stress score (SSS) values from both software packages.
We studied 1,052 consecutive patients who underwent 2-day stress/rest (99m)Tc-sestamibi MPI studies. The reference standard classifications for the MPI studies were obtained from three experienced physicians who separately classified all cases regarding the presence or absence of ischemia and/or infarction. Automatic processing was carried out using EXINI and PERFEX to obtain CAD results and SSS values based on the 17-segment model.
The three experts' classifications showed ischemia in 257 patients and abnormal studies, i.e., either ischemia or infarction or both, in 318 patients. Accuracy was significantly higher in EXINI than in PERFEX, regarding both the detection of ischemia (87.4 vs 77.6%; P < 0.0001) and the detection of abnormal studies (91.6 vs 67.9%; P < 0.0001). EXINI's CAD system showed a higher specificity than its SSS values (86.8 vs 73.6%; P < 0.0001) at the same level of sensitivity.
EXINI demonstrated greater diagnostic accuracy for detection of ischemia and abnormal studies than did PERFEX. EXINI CAD also outperformed its SSS analysis.
Journal of Nuclear Cardiology 01/2014; · 2.85 Impact Factor
[show abstract][hide abstract] ABSTRACT: Artificial neural network (ANN)-based bone scan index (BSI), a marker of the amount of bone metastasis, has been shown to enhance diagnostic accuracy and reproducibility but is potentially affected by training databases. The aims of this study were to revise the software using a large number of Japanese databases and to validate its diagnostic accuracy compared with the original Swedish training database.
The BSI was calculated with EXINIbone (EB; EXINI Diagnostics) using the Swedish training database (n = 789). The software using Japanese training databases from a single institution (BONENAVI version 1, BN1, n = 904) and the revised version from nine institutions (version 2, BN2, n = 1,532) were compared. The diagnostic accuracy was validated with another 503 multi-center bone scans including patients with prostate (n = 207), breast (n = 166), and other cancer types. The ANN value (probability of abnormality) and BSI were calculated. Receiver operating characteristic (ROC) and net reclassification improvement (NRI) analyses were performed.
The ROC analysis based on the ANN value showed significant improvement from EB to BN1 and BN2. In men (n = 296), the area under the curve (AUC) was 0.877 for EB, 0.912 for BN1 (p = not significant (ns) vs. EB) and 0.934 for BN2 (p = 0.007 vs. EB). In women (n = 207), the AUC was 0.831 for EB, 0.910 for BN1 (p = 0.016 vs. EB), and 0.932 for BN2 (p < 0.0001 vs. EB). The optimum sensitivity and specificity based on BN2 was 90% and 84% for men and 93% and 85% for women. In patients with prostate cancer, the AUC was equally high with EB, BN1, and BN2 (0.939, 0.949, and 0.957, p = ns). In patients with breast cancer, the AUC was improved from EB (0.847) to BN1 (0.910, p = ns) and BN2 (0.924, p = 0.039). The NRI using ANN between EB and BN1 was 17.7% (p = 0.0042), and that between EB and BN2 was 29.6% (p < 0.0001). With respect to BSI, the NRI analysis showed downward reclassification with total NRI of 31.9% (p < 0.0001).
In the software for calculating BSI, the multi-institutional database significantly improved identification of bone metastasis compared with the original database, indicating the importance of a sufficient number of training databases including various types of cancers.
[show abstract][hide abstract] ABSTRACT: The objective of this study was firstly to develop and evaluate an automated method for the detection of new lesions and changes in bone scan index (BSI) in serial bone scans and secondly to evaluate the prognostic value of the method in a group of patients receiving chemotherapy.
The automated method for detection of new lesions was evaluated in a group of 266 patients using the classifications by three experienced bone scan readers as a gold standard. The prognostic value of the method was assessed in a group of 31 metastatic hormone-refractory prostate cancer patients who were receiving docetaxel. Cox proportional hazards were used to investigate the association between percentage change in BSI, number of new lesions and overall survival. Kaplan-Meier estimates of the survival function were used to indicate a significant difference between patients with an increase/decrease in BSI or those with two or more new lesions or less than two new lesions.
The automated method detected progression defined as two or more new lesions with a sensitivity of 93% and a specificity of 87%. In the treatment group, both BSI changes and the number of new metastases were significantly associated with survival. Two-year survival for patients with increasing and decreasing BSI from baseline to follow-up scans were 18% and 57% (p = 0.03), respectively. Two-year survival for patients fulfilling and not fulfilling the criterion of two or more new lesions was 35% and 38% (n.s.), respectively.
An automated method can be used to calculate the number of new lesions and changes in BSI in serial bone scans. These imaging biomarkers contained prognostic information in a small group of patients with prostate cancer receiving chemotherapy.
[show abstract][hide abstract] ABSTRACT: Stress myocardial perfusion scintigraphy (MPS) is widely regarded as a useful imaging modality for diagnosing patients with suspected ischemic heart disease. Current European guidelines recommend stress study to be performed first since rest study can be omitted if stress study is interpreted as normal. Thus, a rest study should only be performed in patients with equivocal or abnormal studies. The aim of the present study was to investigate the prognosis of a normal stress-only MPS compared to a normal stress-rest MPS in a retrospective manner and also with regard to normal/abnormal left ventricular function data.
All 4,820 patients who underwent 99mTc MPS at Skane University Hospital in Malmo, Sweden, in 2004 to 2007, for suspected or management of known ischemic heart disease were considered. The physician in clinical charge of the investigation decided whether a rest study was necessary or not. Based on the final report according to clinical routine, only patients with a normal perfusion study (no infarction or inducible ischemia) were included. The endpoints were non-fatal acute coronary syndrome or death from ischemic cardiac origin.
A total of 3,426 patients with a normal perfusion study were included. Of these, 2,215 patients had a stress-only study and 1,211 patients had both stress and rest studies. Mean follow-up was 6.2 years. The lowest event rate was found in the normal stress-only group (0.56% for normal stress-only patients vs. 1.42% for normal stress-rest patients; p < 0.0001). When dividing patients according to sex and stress type, the best prognosis was also found in the normal stress-only group (p < 0.0001 for all comparisons). Regarding left ventricular function data, we did not find any significant difference in event rate between normal vs. abnormal ejection fraction (EF), normal vs. abnormal end-diastolic volume (EDV) or normal EF, and EDV vs. abnormal EF or EDV for either the normal stress-only patients or the normal stress-rest patients.
Patients with a normal stress-only study had an excellent prognosis over a mean follow-up time of 6 years. Thus, omitting the rest study if the stress study is normal is a safe procedure.
[show abstract][hide abstract] ABSTRACT: PURPOSE: In patients with a small heart, defined as an end-systolic volume (ESV) of ≤20 mL calculated using the Quantitative Gated SPECT (QGS) program, underestimation of ESV and overestimation of ejection fraction (EF) using gated myocardial perfusion imaging are considered errors caused by inappropriate delineation of the left ventricle (LV). The aim of this study was to develop a new method for delineation of the LV and to evaluate it in studies using a digital phantom, normal subjects and patients. METHODS: The active shape-based method for LV delineation, EXINI heart (ExH), was adjusted to more accurately process small hearts. In small hearts, due to the partial volume effect and the short distance to the opposite ventricular wall, the endocardial and the epicardial surfaces are shifted in the epicardial direction depending on the midventricular volume. The adjusted method was evaluated using digital XCAT phantoms with Monte Carlo simulation (8 virtual patients), a Japanese multicentre normal database (69 patients) and consecutive Japanese patients (116 patients). The LV volumes, EF and diastolic parameters derived from ExH and QGS were compared. RESULTS: The digital phantom studies showed a mean ESV of 87 % ± 9 % of the true volume calculated using ExH and 22 % ± 18 % calculated using QGS. In the normal database, QGS gave higher EFs in women than in men (71.4 ± 6.0 % vs. 67.2 ± 6.0 %, p = 0.0058), but ExH gave comparable EFs (70.7 ± 4.9 % and 71.4 ± 5 % in men and women, respectively, p = ns). QGS gave higher EFs in subjects with a small heart than in those with a normal-sized heart (74.5 ± 5.1 % vs. 66.1 ± 4.9 %), but ExH gave comparable values (70.0 ± 5.9 % vs. 71.6 ± 4.2 %, respectively, p = ns). In consecutive patients, the average EFs with QGS in patients with ESV >20 mL, 11-20 mL and ≤10 mL were 57.9 %, 71.9 % and 83.2 %, but with ExH the differences among these groups were smaller (65.2 %, 67.8 % and 71.5 %, respectively). CONCLUSION: The volume-dependent edge correction algorithm was able to effectively reduce the effects on ESV and EF of a small heart. The uniform normal values might be applicable to both men and women and to both small and normal-sized hearts.
European Journal of Nuclear Medicine 04/2013; · 4.53 Impact Factor
[show abstract][hide abstract] ABSTRACT: BACKGROUND: The American Society of Nuclear Cardiology and the Society of Nuclear Medicine conclude that incorporation of attenuation corrected (AC) images in myocardial perfusion scintigraphy (MPS) will improve diagnostic accuracy. The aim was to investigate the value of adding AC stress-only images for the decision whether a rest study is necessary or not. METHODS: 1,261 patients admitted to 99mTc MPS were studied. The stress studies were interpreted by two physicians who judged each study as "no rest study necessary" or "rest study necessary", by evaluating NC stress-only and NC + AC stress-only images. When there was disagreement between the two physicians, a third physician evaluated the studies. Thus, agreement between 2 out of 3 physicians was evaluated. RESULTS: The physicians assessed 214 more NC + AC images than NC images as "no rest study necessary" (17% of the study population). The number of no-rest-study-required was significantly higher for NC + AC studies compared to NC studies (859 vs 645 cases (p < 0.0001). In the final report according to clinical routine, ischemia or infarction was reported in 23 patients, assessed as "no rest study necessary" (22 NC + AC cases; 8 NC cases), (no statistically significant difference). In 11 of these, the final report stated "suspected/possible ischemia or infarction in a small area". CONCLUSIONS: Adding AC stress-only images to NC stress-only images reduce the number of unnecessary rest studies substantially.
BMC Medical Imaging 04/2013; 13(1):14. · 1.09 Impact Factor
[show abstract][hide abstract] ABSTRACT: BACKGROUND: Technetium-labeled agents, which are most often used for assessing myocardial perfusion in myocardial perfusion scintigraphy (MPS), are cleared by the liver and excreted by the biliary system. Spillover from extra-cardiac activity into the myocardium, especially the inferior wall, might conceal defects and lower the diagnostic accuracy of the study. The objective was to determine rules of thumb for when reacquisition is useful due to high extra-cardiac uptake, i.e., when interpretation of the studies was affected by poor image quality. METHODS: Patients admitted to MPS at any of the three study sites, who also underwent a reacquisition due to high extra-cardiac uptake were included. Image quality was assessed by ten technologists on a scale ranging from 1 to 5. Interpretations regarding the presence/absence of ischemia/infarction, including the certainty of the diagnosis, were made by three physicians. RESULTS: There was a statistically significant increase in image quality between the first and the repeated acquisition (1,256 cases of increased quality at the repeated study (66%), 134 cases of decreased quality at the repeated study (7%), 510 cases of unchanged quality (27%) P < 0.0001). The number of equivocal studies, interpreted by physicians, decreased when evaluating the repeated studies compared to the first studies for all physicians, both for the interpretations of ischemia and for infarction. Receiver operating characteristic analyses revealed that for both endpoints (ischemia, infarction) and all physicians, the optimal cutoff point for performing a reacquisition was between quality categories 2 and 3. CONCLUSION: This study indicates that repeat acquisition is useful when (1) the intensity of the extra-cardiac uptake is equal to or higher than the cardiac uptake when there is no separation between the extra-cardiac uptake and the inferior cardiac wall and (2) when the intensity of the extra-cardiac uptake is higher than the cardiac uptake when there is a separation between the extra-cardiac uptake and the inferior wall of less than one cardiac wall.
[show abstract][hide abstract] ABSTRACT: BACKGROUND: The objective of this study was to explore the prognostic value of the Bone Scan Index (BSI) obtained at the time of diagnosis in a group of high-risk prostate cancer patients receiving primary hormonal therapy. METHODS: This was a retrospective study based on 130 consecutive prostate cancer patients at high risk, based on clinical stage (T2c/T3/T4), Gleason score (8 to 10) and prostate-specific antigen (PSA) (>20 ng/mL), who had undergone whole-body bone scans <3 months after diagnosis and who received primary hormonal therapy. BSI was calculated using an automated method. Cox proportional-hazards regression models were used to investigate the association between clinical stage, Gleason score, PSA, BSI and survival. Discrimination between prognostic models was assessed using the concordance index (C-index). RESULTS: In a multivariate analysis, Gleason score (p = 0.01) and BSI (p < 0.001) were associated with survival, but clinical stage (p = 0.29) and PSA (p = 0.57) were not prognostic. The C-index increased from 0.66 to 0.71 when adding BSI to a model including clinical stage, Gleason score and PSA. The 5-year probability of survival was 55% for patients without metastases, 42% for patients with BSI < 1, 31% for patients with BSI = 1 to 5, and 0% for patients with BSI > 5. CONCLUSIONS: BSI can be used as a complement to PSA to risk-stratify high-risk prostate cancer patients at the time of diagnosis. This imaging biomarker, reflecting the extent of metastatic disease, can be of value both in clinical trials and in patient management when deciding on treatment.
[show abstract][hide abstract] ABSTRACT: Commercial normal stress databases in myocardial perfusion scintigraphy (MPS) commonly consist of 30-40 individuals. The aim of the study was to determine how many subjects are needed.
Four normal stress databases were developed using patients who underwent 99mTc MPS: non-corrected images (NC) for male, NC for female, attenuation-corrected images (AC) for male and AC for female subjects. 126 male and 205 female subjects were included. The normal database was created by alternatingly computing the mean of all normal subjects and normalizing the subjects with respect to this mean, until convergence. Coefficients of variation (CV) were created for increasing number of included patients in the four different normal stress databases.
Normal stress databases with < 35 subjects had a high CV. Mean CV -2 standard deviations (SD) decreased with 28% between two and five included subjects, 71% between two and 35 subjects and 83% between two and 100 included subjects for NC man.
We conclude that the commonly used 30-40 individuals for making a normal stress database might not be enough due to the high CV. We propose that normal stress databases should consist of more than 30-40 individuals, preferably more than 50 individuals, both for NC and AC studies.
[show abstract][hide abstract] ABSTRACT: In myocardial perfusion scintigraphy (MPS), typically a stress and a rest study is performed. If the stress study is considered normal, there is no need for a subsequent rest study. The aim of the study was to determine whether nuclear medicine technologists are able to assess the necessity of a rest study.
Gated MPS using a 2-day 99mTc protocol for 121 consecutive patients were studied. Visual interpretation by 3 physicians was used as gold standard for determining the need for a rest study based on the stress images. All nuclear medicine technologists performing MPS had to review 82 training cases of stress MPS images with comments regarding the need for rest studies, and thereafter a test consisting of 20 stress MPS images. After passing this test, the nuclear medicine technologists in charge of a stress MPS study assessed whether a rest study was needed or not or if he/she was uncertain and wanted to consult a physician. After that, the physician in charge interpreted the images and decided whether a rest study was required or not.
The nuclear medicine technologists and the physicians in clinical routine agreed in 103 of the 107 cases (96%) for which the technologists felt certain regarding the need for a rest study. In the remaining 14 cases the technologists were uncertain, i.e. wanted to consult a physician. The agreement between the technologists and the physicians in clinical routine was very good, resulting in a kappa value of 0.92. There was no statistically significant difference in the evaluations made by technicians and physicians (P = 0.617).
The nuclear medicine technologists were able to accurately determine whether a rest study was necessary. There was very good agreement between nuclear medicine technologists and physicians in the assessment of the need for a rest study. If the technologists can make this decision, the effectiveness of the nuclear medicine department will improve.
BMC Medical Informatics and Decision Making 09/2012; 12:97. · 1.60 Impact Factor
[show abstract][hide abstract] ABSTRACT: Automated segmentation of the skeleton is the first step for quantitative analysis and computer-aided diagnosis (CAD) of whole-body bone scans. The purpose of this study was to examine the influence of differences in skeletal atlas on the automated segmentation of skeletons in a Japanese patient group.
The study was based on a bone scan CAD system that included a skeletal atlas obtained using 10 normal bone scans from European patients and 23 normal bone scans from Japanese patients. These were incorporated into the CAD system. The performance of the skeletal segmentation, based on either the European or the Japanese Atlas, was evaluated independently by three observers in a group of 50 randomly selected bone scans from Japanese patients.
The skeletal segmentation was classified as correct in 41-44 of the 50 cases by the three observers using the Japanese atlas. The corresponding results were 15-18 of the 50 cases using the European atlas, and this difference was statistically significant (P<0.001). The anatomical areas most commonly classified as not correct were the skull, cervical vertebrae, and ribs.
Automated segmentation of the skeleton in a Japanese patient group was more successful when the CAD system based on a Japanese atlas was used than when the corresponding system based on a European atlas was used. The results of this study indicate that it is of value to use a skeletal atlas based on normal Japanese bone scans in a CAD system for Japanese patients.
Nuclear Medicine Communications 07/2012; 33(9):947-53. · 1.38 Impact Factor
[show abstract][hide abstract] ABSTRACT: Computer-aided diagnosis (CAD) software for bone scintigrams have recently been introduced as a clinical quality assurance tool. The purpose of this study was to compare the diagnostic accuracy of two CAD systems, one based on a European and one on a Japanese training database, in a group of bone scans from Japanese patients.
The two CAD software are trained to interpret bone scans using training databases consisting of bone scans with the desired interpretation, metastatic disease or not. One software was trained using 795 bone scans from European patients and the other with 904 bone scans from Japanese patients. The two CAD softwares were evaluated using the same group of 257 Japanese patients, who underwent bone scintigraphy because of suspected metastases of malignant tumors in 2009. The final diagnostic results made by clinicians were used as gold standard.
The Japanese CAD software showed a higher specificity and accuracy compared to the European CAD software [81 vs. 57 % (p < 0.05) and 82 vs. 61 % (p < 0.05), respectively]. The sensitivity was 90 % for the Japanese CAD software and 83 % for the European CAD software (n.s).
The CAD software trained with a Japanese database showed significantly higher performance than the corresponding CAD software trained with a European database for the analysis of bone scans from Japanese patients. These results could at least partly be caused by the physical differences between Japanese and European patients resulting in less influence of attenuation in Japanese patients and possible different judgement of count intensities of hot spots.
Annals of Nuclear Medicine 06/2012; 26(8):622-6. · 1.41 Impact Factor
[show abstract][hide abstract] ABSTRACT: It is important that referring physicians and other treating clinicians properly understand the final reports from diagnostic tests. The aim of the study was to investigate whether referring physicians interpret a final report for a myocardial perfusion scintigraphy (MPS) test in the same way that the reading nuclear medicine physician intended.
After viewing final reports containing only typical clinical verbiage and images, physicians in nuclear medicine and referring physicians (physicians in cardiology, internal medicine, and general practitioners) independently classified 60 MPS tests for the presence versus absence of ischemia/infarction according to objective grades of 1-5 (1 = No ischemia/infarction, 2 = Probably no ischemia/infarction 3 = Equivocal, 4 = Probable ischemia/infarction, and 5 = Certain ischemia/infarction). When ischemia and/or infarction were thought to be present in the left ventricle, all physicians were also asked to mark the involved segments based on the 17-segment model.
There was good diagnostic agreement between physicians in nuclear medicine and referring physicians when assessing the general presence versus absence of both ischemia and infarction (median squared kappa coefficient of 0.92 for both). However, when using the 17-segment model, compared to the physicians in nuclear medicine, 12 of 23 referring physicians underestimated the extent of ischemic area while 6 underestimated and 1 overestimated the extent of infarcted area.
Whereas referring physicians gain a good understanding of the general presence versus absence of ischemia and infarction from MPS test reports, they often underestimate the extent of any ischemic or infarcted areas. This may have adverse clinical consequences and thus the language in final reports from MPS tests might be further improved and standardized.
[show abstract][hide abstract] ABSTRACT: Changes in maximum standardised uptake values (SUVmax) between serial PET/CT studies are used to determine disease progression or regression in oncologic patients. To measure these changes manually can be time consuming in a clinical routine. A semi-automatic method for calculation of SUVmax in serial PET/CT studies was developed and compared to a conventional manual method. The semi-automatic method first aligns the serial PET/CT studies based on the CT images. Thereafter, the reader selects an abnormal lesion in one of the PET studies. After this manual step, the program automatically detects the corresponding lesion in the other PET study, segments the two lesions and calculates the SUVmax in both studies as well as the difference between the SUVmax values. The results of the semi-automatic analysis were compared to that of a manual SUVmax analysis using a Philips PET/CT workstation. Three readers did the SUVmax readings in both methods. Sixteen patients with lung cancer or lymphoma who had undergone two PET/CT studies were included. There were a total of 26 lesions.
Linear regression analysis of changes in SUVmax show that intercepts and slopes are close to the line of identity for all readers (reader 1: intercept = 1.02, R2 = 0.96; reader 2: intercept = 0.97, R2 = 0.98; reader 3: intercept = 0.99, R2 = 0.98). Manual and semi-automatic method agreed in all cases whether SUVmax had increased or decreased between the serial studies. The average time to measure SUVmax changes in two serial PET/CT examinations was four to five times longer for the manual method compared to the semi-automatic method for all readers (reader 1: 53.7 vs. 10.5 s; reader 2: 27.3 vs. 6.9 s; reader 3: 47.5 vs. 9.5 s; p < 0.001 for all).
Good agreement was shown in assessment of SUVmax changes between manual and semi-automatic method. The semi-automatic analysis was four to five times faster to perform than the manual analysis. These findings show the feasibility of using semi-automatic methods for calculation of SUVmax in clinical routine and encourage further development of programs using this type of methods.
BMC Medical Imaging 04/2012; 12:6. · 1.09 Impact Factor
[show abstract][hide abstract] ABSTRACT: Most nuclear medicine clinicians use only visual assessment when interpreting regional cerebral blood flow (rCBF) from single-photon emission computed tomography (SPECT) images in clinical practice. The aims of this study were to develop a new, easy to use, automated method for quantification of rCBF-SPECT and to create normal values by using the method on a normal population. We developed a 3-dimensional method based on a brain-shaped model and the active-shape algorithm. The method defines the surface shape of the brain and then projects the maximum counts 0-1.5 cm deep for designated surface points. These surface projection values are divided into cortical regions representing the different lobes and presented relative to the whole cortex, cerebellum or cerebellar maximum. (99m) Tc-hexa methyl propylene amine oxime (HMPAO) SPECT was performed on 30 healthy volunteers with a mean age of 74 years (range 64-98). The ability of the active-shape algorithm to define the shape of the brain was satisfactory when visually scrutinized. The results of the quantification show rCBF values in the frontal, temporal and parietal lobes of 87-88% using cerebellum as the reference. There were no significant differences in normal rCBF values between male and female subjects and only a weak relation between rCBF and age. In conclusion, our new automated method was able to quantify rCBF-SPECT images and create normal values in ranges as expected. Further studies are needed to assess the clinical value of this method and the normal values.
[show abstract][hide abstract] ABSTRACT: There is little consensus on a standard approach to analysing bone scan images. The Bone Scan Index (BSI) is predictive of survival in patients with progressive prostate cancer (PCa), but the popularity of this metric is hampered by the tedium of the manual calculation.
Develop a fully automated method of quantifying the BSI and determining the clinical value of automated BSI measurements beyond conventional clinical and pathologic features.
We conditioned a computer-assisted diagnosis system identifying metastatic lesions on a bone scan to automatically compute BSI measurements. A training group of 795 bone scans was used in the conditioning process. Independent validation of the method used bone scans obtained ≤3 mo from diagnosis of 384 PCa cases in two large population-based cohorts. An experienced analyser (blinded to case identity, prior BSI, and outcome) scored the BSI measurements twice. We measured prediction of outcome using pretreatment Gleason score, clinical stage, and prostate-specific antigen with models that also incorporated either manual or automated BSI measurements.
The agreement between methods was evaluated using Pearson's correlation coefficient. Discrimination between prognostic models was assessed using the concordance index (C-index).
Manual and automated BSI measurements were strongly correlated (ρ=0.80), correlated more closely (ρ=0.93) when excluding cases with BSI scores≥10 (1.8%), and were independently associated with PCa death (p<0.0001 for each) when added to the prediction model. Predictive accuracy of the base model (C-index: 0.768; 95% confidence interval [CI], 0.702-0.837) increased to 0.794 (95% CI, 0.727-0.860) by adding manual BSI scoring, and increased to 0.825 (95% CI, 0.754-0.881) by adding automated BSI scoring to the base model.
Automated BSI scoring, with its 100% reproducibility, reduces turnaround time, eliminates operator-dependent subjectivity, and provides important clinical information comparable to that of manual BSI scoring.
European Urology 01/2012; 62(1):78-84. · 10.48 Impact Factor
[show abstract][hide abstract] ABSTRACT: Pre-hospital electrocardiogram (ECG) transmission to an expert for interpretation and triage reduces time to acute percutaneous coronary intervention (PCI) in patients with ST elevation Myocardial Infarction (STEMI). In order to detect all STEMI patients, the ECG should be transmitted in all cases of suspected acute cardiac ischemia. The aim of this study was to examine the ability of an artificial neural network (ANN) to safely reduce the number of ECGs transmitted by identifying patients without STEMI and patients not needing acute PCI.
Five hundred and sixty ambulance ECGs transmitted to the coronary care unit (CCU) in routine care were prospectively collected. The ECG interpretation by the ANN was compared with the diagnosis (STEMI or not) and the need for an acute PCI (or not) as determined from the Swedish coronary angiography and angioplasty register. The CCU physician's real time ECG interpretation (STEMI or not) and triage decision (acute PCI or not) were registered for comparison.
The ANN sensitivity, specificity, positive and negative predictive values for STEMI was 95%, 68%, 18% and 99%, respectively, and for a need of acute PCI it was 97%, 68%, 17% and 100%. The area under the ANN's receiver operating characteristics curve for STEMI detection was 0.93 (95% CI 0.89-0.96) and for predicting the need of acute PCI 0.94 (95% CI 0.90-0.97). If ECGs where the ANN did not identify a STEMI or a need of acute PCI were theoretically to be withheld from transmission, the number of ECGs sent to the CCU could have been reduced by 64% without missing any case with STEMI or a need of immediate PCI.
Our ANN had an excellent ability to predict STEMI and the need of acute PCI in ambulance ECGs, and has a potential to safely reduce the number of ECG transmitted to the CCU by almost two thirds.
Scandinavian Journal of Trauma Resuscitation and Emergency Medicine 01/2012; 20:8. · 1.68 Impact Factor
[show abstract][hide abstract] ABSTRACT: The American Society of Nuclear Cardiology and the Society of Nuclear Medicine state that incorporation of attenuation-corrected (AC) images in myocardial perfusion scintigraphy (MPS) will improve image quality, interpretive certainty, and diagnostic accuracy. However, commonly used software packages for MPS usually include normal stress databases for non-attenuation corrected (NC) images but not for attenuation-corrected (AC) images. The aim of the study was to develop and compare different normal stress databases for MPS in relation to NC vs. AC images, male vs. female gender, and presence vs. absence of obesity. The principal hypothesis was that differences in mean count values between men and women would be smaller with AC than NC images, thereby allowing for construction and use of gender-independent AC stress database.
Normal stress perfusion databases were developed with data from 126 male and 205 female patients with normal MPS. The following comparisons were performed for all patients and separately for normal weight vs. obese patients: men vs. women for AC; men vs. women for NC; AC vs. NC for men; and AC vs. NC for women.
When comparing AC for men vs. women, only minor differences in mean count values were observed, and there were no differences for normal weight vs. obese patients. For all other analyses major differences were found, particularly for the inferior wall.
The results support the hypothesis that it is possible to use not only gender independent but also weight independent AC stress databases.
BMC Medical Imaging 10/2011; 11:18. · 1.09 Impact Factor
[show abstract][hide abstract] ABSTRACT: Time-resolved medical data has important applications in a large variety of medical applications. In this paper we study automatic
analysis of dynamical renal scintigraphies. The traditional analysis pipeline for dynamical renal scintigraphies is to use
manual or semiautomatic methods for segmentation of pixels into physical compartments, extract their corresponding time-activity
curves and then compute the parameters that are relevant for medical assessment. In this paper we present a fully automatic
system that incorporates spatial smoothing constraints, compartment modelling and positivity constraints to produce an interpretation
of the full time-resolved data. The method has been tested on renal dynamical scintigraphies with promising results. It is
shown that the method indeed produces more compact representations, while keeping the residual of fit low. The parameters
of the time activity curve, such as peak-time and time for half activity from peak, are compared between the previous semiautomatic
method and the method presented in this paper. It is also shown how to obtain new and clinically relevant features using our
KeywordsMedical image analysis–time-resolved–compartment modelling–dynamical renal scintigraphies–segmentation