February 2021
·
100 Reads
·
7 Citations
This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
February 2021
·
100 Reads
·
7 Citations
November 2020
·
53 Reads
Current Directions in Biomedical Engineering
Proper treatment of prostate cancer is essential to increase the survival chance. In this sense, numerous studies show how important the communication between all stakeholders in the clinic is. This communication is difficult because of the lack of conventions while referring to the location where a biopsy for diagnosis was taken. This becomes even more challenging taking into account that experts of different fields work on the data and have different requirements. In this paper a web-based communication tool is proposed that incorporates a visualization of the prostate divided into 27 segments according to the PI-RADS protocol. The tool provides 2 working modes that consider the requirements of radiologist and pathologist while keeping it consistent. The tool comprises all relevant information given by pathologists and radiologists, such as, severity grades of the disease or tumor length. Everything is visualized using a colour code for better undestanding.
April 2018
·
64 Reads
Laryngo-Rhino-Otologie
April 2018
·
47 Reads
Laryngo-Rhino-Otologie
October 2017
·
123 Reads
·
16 Citations
September 2017
·
15 Reads
Lecture Notes in Computer Science
The localization and analysis of the sentinel lymph node for patients diagnosed with cancer, has significant influence on the prognosis, outcome and treatment of the disease. We present a fully automatic approach to localize the sentinel lymph node and additional active nodes and determine their lymph node level on SPECT-CT data. This is a crucial prerequisite for the planning of radiation therapy or a surgical neck dissection. Our approach was evaluated on 17 lymph nodes. The detection rate of the lymph nodes was 94%; and 88% of the lymph nodes were correctly assigned to their corresponding lymph node level. The proposed algorithm targets a very important topic in clinical practice. The first results are already very promising. The next step has to be the evaluation on a larger data set.
March 2017
·
453 Reads
·
266 Citations
Purpose: Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number and diversity of structures and the large variety of segmentation algorithms a consensus is lacking as to which automated segmentation method works best for certain applications. Segmentation challenges are a good approach for unbiased evaluation and comparison of segmentation algorithms. Methods: In this work we describe and present the results of the Head and Neck Auto-Segmentation Challenge 2015, a satellite event at the Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015 conference. Six teams participated in a challenge to segment nine structures in the head and neck region of CT images: brainstem, mandible, chiasm, bilateral optic nerves, bilateral parotid glands and bilateral submandibular glands. Results: This paper presents the quantitative results of this challenge using multiple established error metrics and a well-defined ranking system. The strengths and weaknesses of the different auto-segmentation approaches are analyzed and discussed. Conclusions: The Head and Neck Auto-Segmentation Challenge 2015 was a good opportunity to assess the current state-of-the-art in segmentation of organs at risk for radiotherapy treatment. Participating teams had the possibility to compare their approaches to other methods under unbiased and standardized circumstances. The results demonstrate a clear tendency towards more general-purpose and fewer structure-specific segmentation algorithms. This article is protected by copyright. All rights reserved.
March 2016
·
11 Reads
·
4 Citations
The common approach to do a fully automatic segmentation of multiple structures is an atlas or multi-atlas based solution. These already have proven to be suitable for the segmentation of structures in the head and neck area and provide very accurate segmentation results, but can struggle with challenging cases with unnatural postures, where the registration of the reference patient(s) is extremely difficult. Therefore, we propose an coupled shape model (CoSMo) algorithm for the segmentation relevant structures in parallel. The model adaptation to a test image is done with respect to the appearance of its items and the trained articulation space. Even on very challenging data sets with unnatural postures, which occur far more often than expected, the model adaptation algorithm succeeds. The approach is based on an articulated atlas , that is trained from a set of manually labeled training samples. Furthermore, we have combined the initial solution with statistical shape models to represent structures with high shape variation. CoSMo is not tailored to specific structures or regions. It can be trained from any set of given gold standard segmentations and makes it thereby very generic.
January 2016
·
34 Reads
Einleitung: Akustikusneurinome sind benigne Tumore des N. vestibularis im Bereich des Kleinhirnbrückenwinkels oder des inneren Gehörgangs. Bei langsamem Wachstum ist neben der operativen Entfernung oder der Strahlentherapie eine „wait and scan“-Strategie unter regelmäßigen MRT-Kontrollen möglich. Objektivierbare Tumorvolumenbestimmungen können mittels zeitaufwendiger Segmentierungen durchgeführt werden. Durch eine Automatisierung des Segmentierungsvorganges wird diese Methode schnell, genau und objektiv einsetzbar. Methode: Die Radial-Strahl-basierte 3D-Segmentierung sendet ausgehend von einem manuell vorgegebenen Saatpunktes, Strahlen radial in alle Richtungen und erzeugt unter Einbeziehung von Bildinformation und lokalem Formwissen eine Segmentierung. Innerhalb weniger Sekunden werden die Achsen und das Volumen des Tumors angezeigt. Innerhalb eines Projektes wurde die Methode spezifisch für Akustikusneurinome entwickelt und an unserem Patientengut validiert. Es wurden Messungen bei manueller und automatisierter Segmentierung durch verschiedene Untersucher durchgeführt, um die Reliabilität, Geschwindigkeit und Alltagstauglichkeit der Methode zu evaluieren. Ergebnisse: Das Volumen von Akustikusneurinomen kann auch durch unterschiedliche Untersucher reproduzierbar mit hoher Genauigkeit innerhalb weniger Sekunden automatisiert und somit schneller als manuell segmentiert werden. Schlussfolgerung: Die automatisierte Radial-Strahl-basierte 3D-Segmentierung ist eine gut geeignete Methode zur objektiven Volumenbestimmung von Akustikusneurinomen. Sie mindert die Inter-Observer-Variabilität und reduziert den Zeitaufwand der Bildbeurteilung. Insofern hat diese Methode ein gutes Potential, um v.a. bei der „‚wait and scan“-Methode in den klinischen Alltag eingeführt zu werden. Der Erstautor gibt keinen Interessenkonflikt an.
February 2015
·
13 Reads
Die Untersuchung von Größe und Aussehen eines Lymphknotens kann ein entscheidender Indikator für die Existenz eines Tumors sein und ist außerdem ein probates Mittel, um Verlaufsanalysen bei einem Patienten durchzuführen, welche wiederum maßgeblichen Einfluss auf die Behandlung haben können. Um die Größe und andere Parameter des Lymphknotens bestimmen zu können, ist zuerst eine Segmentierung vonnöten.Wir präsentieren ein neues Verfahren für die halbautomatische Segmentierung von Lymphknoten auf MR-Datensätzen. Unser Ansatz verwendet eine Wasserscheidentransformation als Grundlage und kombiniert diese mit einem Radialstrahlbasierten Verfahren, um eine möglichst akurate Segmentierung des Lymphknotens zu erhalten. Für die Evaluation wurden 95 Lymphknoten-Segmentierungen aus 17 verschiedenen, kontrastverstärkten T1-gewichteten Patientendatensätzen verwendet. Das durchschnittliche Dice ¨ Ahnlichkeitsmaß lag bei 0.69±0.15 und die mittlere Oberflächendistanz bei 0.65±0.54mm.
... Various methods other than deep learning have been proposed for automatic segmentation of OAR in the head and neck region. The approaches include, among others, (multi) atlas-based methods, 3-6 model-based methods, [7][8][9][10] or their combinations. 11,12 Some of the methods 6,[8][9][10][11] have been evaluated in the 2015 MICCAI challenge on head and neck autosegmentation, where the best mean Dice score on the parotid glands was 0.84. ...
March 2016
... This helps dentists with pre-treatment diagnosis and orthodontic treatment planning. A variety of emerging techniques have been introduced in related fields, including tooth segmentation [5,6], 3D tooth reconstruction [36,37], and 3D tooth arrangement [35]. In terms of orthodontic comparison photographs, Lingchen et al. [20] have introduced iOrthoPredictor which can synthesize an image of well-aligned teeth based on a patient's facial photograph and an additional input of the patient's 3D dental model. ...
February 2021
... For example, Raidou et al. [43] presented tools that enable detailed visual exploration and analysis of how variations in bladder shape impact the accuracy of dose delivery. Bannach et al. [5] combined medical image analysis with visual analytics of patient data to analyze patient cohorts. ...
October 2017
... Other studies exhibit biases in lesion size; for instance, in one study (16), the median lesion volume in the training set was 48 ml (using follow-up images), while the median lesion volume for MRI in the ISLES 2015 challenge was only 17 ml. However, lesion contrast-rather than size alone-appears to be the more significant challenge (17), as ischemic stroke lesions are often poorly contrasted with surrounding healthy tissue in CT images, making them difficult to distinguish. ...
March 2017
... T1w, T2w and T1wCont MRI were acquired using scanners with a field strength of 1.5 T and a turbo spin-echo pulse sequence. The contouring of the gross tumor volume was performed at the clinical centers using a semiautomatic segmentation software based on coupled shape modeling 20 . The region of interest (ROI), corresponding to the primary tumor, was segmented manually slice by slice by HNSCC expert radiologists (one for each center). ...
September 2014
Lecture Notes in Computer Science
... We compare our proposed ECONet with existing state-of-the-art methods in online likelihood inference, which are Histogram (Boykov and Jolly, 2001), Gaussian Mixture Model (GMM) (Rother et al., 2004) and DybaORF-Haar-Like (Wang et al., 2016). In addition, to show the effectiveness of learning features in ECONet, we define ECONet-Haar-Like that replaces the first convolution layer of ECONet with hand-crafted haar-like features (Jung et al., 2013) and learns the three fully-connected layers. Both DybaORF-Haar-Like and ECONet-Haar-Like utilize our GPU-based implementation of 3d haar-like features, available at: https://github.com/masadcv/PyTorchHaarFeatures. ...
February 2013
... Among the existing architectures, nn-UNet is commonly a top performer in prostate segmentation challenges and is considered as the de facto choice for the task [8,9]. Whilst a broad range of results have been presented for prostate WG segmentation trained on open-source and single-institution datasets [9,10], little is known about the impact of the MRI scanner characteristics and their degree of adherence to PI-RADS v2.1 technical standards on the inter-institutional transferability and longitudinal performance of the model after a successful deployment [11]. ...
March 2014
... In this study, we evaluate the proposed semi-supervised learning approach using two widely recognized 3D medical image datasets: the ACDC (Automated Cardiac Diagnosis Challenge) [24] dataset and the PROMISE12 [25] dataset. While both datasets originally consist of 3D images, we perform our experiments using their corresponding 2D slices for training and evaluation. ...
December 2013
Medical Image Analysis