Unsupervised pathology detection in medical images using learning-based methods

Hristina Uzunova*, Heinz Handels, Jan Ehrhardt

*Corresponding author for this work


Detecting pathologies automatically is challenging because of their big variability. As the usual supervised machine learning approaches would only be able to detect one type of pathologies, in this work we pursue an unsupervised approach: learn the entire variability of healthy data and detect pathologies by their differences to the learned norm. Two methods have been developed based on this principle: A modified PatchMatch algorithm shows plausible results on contrasting brain tumors, but bad generalization ability for other types of data. A CVAE-based method on the other hand performs significantly better and ca. 17 times faster on the brain data and can be generalized to other pathologies, e.g. lung tumors. Not only is the achieved Dice coefficient of 0.55 comparable to other supervised methods on this data, moreover this method reliably detects different pathology types and needs no groundtruth.

Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2018
EditorsA. Maier, T.M. Deserno, H. Handels, K.H. Maier-Hein, C. Palm, T. Tolxdorff
Number of pages6
PublisherSpringer Vieweg, Berlin Heidelberg
Publication date01.01.2018
ISBN (Print)978-3-662-56537-7
ISBN (Electronic)978-3-662-56536-0
Publication statusPublished - 01.01.2018
EventBildverarbeitung für die Medizin 2018 - Lehrstuhl für Mustererkennung, Erlangen, Germany
Duration: 11.03.201813.03.2018


Dive into the research topics of 'Unsupervised pathology detection in medical images using learning-based methods'. Together they form a unique fingerprint.

Cite this