TY - JOUR A1 - Rezaei, Mina A1 - Näppi, Janne J. A1 - Lippert, Christoph A1 - Meinel, Christoph A1 - Yoshida, Hiroyuki T1 - Generative multi-adversarial network for striking the right balance in abdominal image segmentation JF - International journal of computer assisted radiology and surgery N2 - Purpose: The identification of abnormalities that are relatively rare within otherwise normal anatomy is a major challenge for deep learning in the semantic segmentation of medical images. The small number of samples of the minority classes in the training data makes the learning of optimal classification challenging, while the more frequently occurring samples of the majority class hamper the generalization of the classification boundary between infrequently occurring target objects and classes. In this paper, we developed a novel generative multi-adversarial network, called Ensemble-GAN, for mitigating this class imbalance problem in the semantic segmentation of abdominal images. Method: The Ensemble-GAN framework is composed of a single-generator and a multi-discriminator variant for handling the class imbalance problem to provide a better generalization than existing approaches. The ensemble model aggregates the estimates of multiple models by training from different initializations and losses from various subsets of the training data. The single generator network analyzes the input image as a condition to predict a corresponding semantic segmentation image by use of feedback from the ensemble of discriminator networks. To evaluate the framework, we trained our framework on two public datasets, with different imbalance ratios and imaging modalities: the Chaos 2019 and the LiTS 2017. Result: In terms of the F1 score, the accuracies of the semantic segmentation of healthy spleen, liver, and left and right kidneys were 0.93, 0.96, 0.90 and 0.94, respectively. The overall F1 scores for simultaneous segmentation of the lesions and liver were 0.83 and 0.94, respectively. Conclusion: The proposed Ensemble-GAN framework demonstrated outstanding performance in the semantic segmentation of medical images in comparison with other approaches on popular abdominal imaging benchmarks. The Ensemble-GAN has the potential to segment abdominal images more accurately than human experts. KW - imbalanced learning KW - generative multi-discriminative networks KW - semantic KW - segmentation KW - abdominal imaging Y1 - 2020 U6 - https://doi.org/10.1007/s11548-020-02254-4 SN - 1861-6410 SN - 1861-6429 VL - 15 IS - 11 SP - 1847 EP - 1858 PB - Springer CY - Berlin ER - TY - JOUR A1 - Schröder, C. A1 - Höhle, Barbara T1 - Prosodic perception during early language acquisition JF - Sprache, Stimme, Gehör : Zeitschrift für Kommunikationsstörungen N2 - Prosody plays an important role in early language acquisition that in most children proceeds rapidly and easily. From birth on infants are able to perceive prosodic information in the speech signal. During the course of the first year of life prosodic perception abilities continue to develop. Cross-linguistic studies have shown that this development is already influenced by the native language. As prosodic and syntactic units occur often in correlation, prosodic cues in the continuous speech signal might help infants to derive information on how to segment their native language into syntactically relevant units. Indeed, infants use their prosodic perception and are able to detect word, phrase and clause boundaries using prosodic cues from the speech signal. Thus, during the first year of life when perceiving speech the processing of prosodic cues is focussed and allows for an efficient access to language acquisition. Future studies need to determine whether early prosodic perception abilities can provide markers for later language development and predict language impairment. KW - prosodic processing KW - early speech perception KW - segmentation KW - prosodic cues KW - prosody-syntax interface Y1 - 2011 U6 - https://doi.org/10.1055/s-0031-1284404 SN - 0342-0477 VL - 35 IS - 3 SP - E91 EP - E98 PB - Thieme CY - Stuttgart ER - TY - THES A1 - Jiang, Chunyan T1 - Multi-visualization and hybrid segmentation approaches within telemedicine framework T1 - Multi-Visualisierung und hybride Segmentierungsansätze auf dem Gebiet der Telemedizin N2 - The innovation of information techniques has changed many aspects of our life. In health care field, we can obtain, manage and communicate high-quality large volumetric image data by computer integrated devices, to support medical care. In this dissertation I propose several promising methods that could assist physicians in processing, observing and communicating the image data. They are included in my three research aspects: telemedicine integration, medical image visualization and image segmentation. And these methods are also demonstrated by the demo software that I developed. One of my research point focuses on medical information storage standard in telemedicine, for example DICOM, which is the predominant standard for the storage and communication of medical images. I propose a novel 3D image data storage method, which was lacking in current DICOM standard. I also created a mechanism to make use of the non-standard or private DICOM files. In this thesis I present several rendering techniques on medical image visualization to offer different display manners, both 2D and 3D, for example, cut through data volume in arbitrary degree, rendering the surface shell of the data, and rendering the semi-transparent volume of the data. A hybrid segmentation approach, designed for semi-automated segmentation of radiological image, such as CT, MRI, etc, is proposed in this thesis to get the organ or interested area from the image. This approach takes advantage of the region-based method and boundary-based methods. Three steps compose the hybrid approach: the first step gets coarse segmentation by fuzzy affinity and generates homogeneity operator; the second step divides the image by Voronoi Diagram and reclassifies the regions by the operator to refine segmentation from the previous step; the third step handles vague boundary by level set model. Topics for future research are mentioned in the end, including new supplement for DICOM standard for segmentation information storage, visualization of multimodal image information, and improvement of the segmentation approach to higher dimension. N2 - Innovative Informationstechnologien haben viele Bereiche unseres Lebens verändert. Im Gesundheitsbereich ist es mittels Computer möglich, qualitativ hochwertige und große volumetrische Bilddaten zu verwalten, zu verarbeiten und dadurch die medizinische Betreuung zu unterstützen. In dieser Dissertation stelle ich verschiedene Methoden vor, die Mediziner beim Prozess der Beobachtung, Verarbeitung und Nutzung von Bilddaten verstärkt unterstützten können. Meine Forschungsarbeit befasst sich mit drei Schwerpunktthemen: Telemedizinintegration, Visualisierung von medizinischen Bildern und Bildsegmentierung. Zur Demonstration der Machbarkeit der vorgeschlagenen Methoden implementierte ich zudem eine Anwendungssoftware. Das entwickelte System kann in punkto Telemedizinintegration nicht nur Dateien im DICOM Format lesen und schreiben, sondern auch nicht-standardisierte Dateien reparieren. In meiner Arbeit gebe ich außerdem einen Vorschlag für eine Erweiterung des DICOM Standards für die Speicherung von 3D Bildinformationen. Zur Darstellung der Bilddaten wurden in dem entwickelten System drei verschiedene Ansichten implementiert: Volumen Ansicht, Oberflächen Ansicht sowie Querschnitt Ansicht. Ein Großteil meiner Arbeit ist der Vorschlag eines neuen hybriden Bildsegmentierungsansatzes. Durch das neu vorgeschlagene Verfahren können komplexe neurale MRI Daten effizient und präzise segmentiert werden. Zusätzlich wird der manuelle Arbeitsaufwand der Experten drastisch verringert. KW - medizinisch KW - bild KW - Segmentierung KW - medical KW - image KW - segmentation Y1 - 2007 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus-12829 ER -