0000000000433721
AUTHOR
Stephan A. Meier
Segmentierung von Hepatozellulären Karzinomen mit Fuzzy-Connectedness
Die Segmentierung von hepatozellularen Karzinomen nach Chemoembolisation stellt eine grose Herausforderung an die Bildverarbeitung dar. CT-Aufnahmen sechs Wochen nach dieser Therapie sind die Grundlage fur die angestrebte Volumetrie der Raumforderungen. In diesen Bildern stellen sich die mit Lipiodol und Mitomycin behandelten Tumore als inhomogene, kraftig kontrastierte Herde dar, wahrend gleichzeitig neue Metastasen mit nur geringer Kontrastierung entstanden sein konnen. Ein neuer, auf Basis der Fuzzy-Connectedness beruhender Algorithmus zeigt in einer ersten Studie durch seine Fahigkeit, Grauwertinformationen mit Kriterien zu lokalen Zusammenhangen zu kombinieren, gute Ergebnisse. Verglei…
Evaluation eines neuen Softwareassistenten zur automatischen Volumenbestimmung von intrahepatischen Tumoren
Purpose: Computed tomography has become the preferred method in detecting liver carcinomas. The introduction of spiral CT added volumetric assessment of intrahepatic tumors, which was unattainable in the clinical routine with incremental CT due to complex planimetric revisions and excessive computing time. In an ongoing clinical study, a new software tool was tested for the automatic detection of tumor volume and the time needed for this procedure. Materials and Methods: We analyzed patients suffering from hepatocellular carcinoma (HCC). All patients underwent treatment with repeated transcatheter chemoembolization of the hepatic arteria. The volumes of the HCC lesions detected in CT were m…
3D contour based local manual correction of tumor segmentations in CT scans
Segmentation is an essential task in medical image analysis. For example measuring tumor growth in consecutive CT scans based on the volume of the tumor requires a good segmentation. Since manual segmentation takes too much time in clinical routine automatic segmentation algorithms are typically used. However there are always cases where an automatic segmentation fails to provide an acceptable segmentation for example due to low contrast, noise or structures of the same density lying close to the lesion. These erroneous segmentation masks need to be manually corrected. We present a novel method for fast three-dimensional local manual correction of segmentation masks. The user needs to draw …