Hristina Uzunova1, Sandra Schultz2, Heinz Handels2, Jan Ehrhardt2. 1. Institute of Medical Informatics, University of Lübeck, Lübeck, Germany. uzunova@imi.uni-luebeck.de. 2. Institute of Medical Informatics, University of Lübeck, Lübeck, Germany.
Abstract
PURPOSE: Pathology detection in medical image data is an important but a rather complicated task. In particular, the big variability of the pathologies is a challenge to automatic detection methods and even to machine learning methods. Supervised algorithms would usually learn the appearance of a single pathological structure based on a large annotated dataset. As such data is not usually available, especially in large amounts, in this work we pursue a different unsupervised approach. METHODS: Our method is based on learning the entire variability of healthy data and detect pathologies by their differences to the learned norm. For this purpose, we use conditional variational autoencoders which learn the reconstruction and encoding distribution of healthy images and also have the ability to integrate certain prior knowledge about the data (condition). RESULTS: Our experiments on different 2D and 3D datasets show that the approach is suitable for the detection of pathologies and deliver reasonable Dice coefficients and AUCs. Also this method can estimate missing correspondences in pathological images and thus can be used as a pre-step to a registration method. Our experiments show improving registration results on pathological data when using this approach. CONCLUSIONS: Overall the presented approach is suitable for a rough pathology detection in medical images and can be successfully used as a preprocessing step to other image processing methods.
PURPOSE: Pathology detection in medical image data is an important but a rather complicated task. In particular, the big variability of the pathologies is a challenge to automatic detection methods and even to machine learning methods. Supervised algorithms would usually learn the appearance of a single pathological structure based on a large annotated dataset. As such data is not usually available, especially in large amounts, in this work we pursue a different unsupervised approach. METHODS: Our method is based on learning the entire variability of healthy data and detect pathologies by their differences to the learned norm. For this purpose, we use conditional variational autoencoders which learn the reconstruction and encoding distribution of healthy images and also have the ability to integrate certain prior knowledge about the data (condition). RESULTS: Our experiments on different 2D and 3D datasets show that the approach is suitable for the detection of pathologies and deliver reasonable Dice coefficients and AUCs. Also this method can estimate missing correspondences in pathological images and thus can be used as a pre-step to a registration method. Our experiments show improving registration results on pathological data when using this approach. CONCLUSIONS: Overall the presented approach is suitable for a rough pathology detection in medical images and can be successfully used as a preprocessing step to other image processing methods.
Authors: Jhimli Mitra; Jianwei Qiu; Michael MacDonald; Prem Venugopal; Kirk Wallace; Hossam Abdou; Michael Richmond; Noha Elansary; Joseph Edwards; Neerav Patel; Jonathan Morrison; Luca Marinelli Journal: IEEE J Transl Eng Health Med Date: 2022-08-19
Authors: Xuxin Chen; Ximin Wang; Ke Zhang; Kar-Ming Fung; Theresa C Thai; Kathleen Moore; Robert S Mannel; Hong Liu; Bin Zheng; Yuchen Qiu Journal: Med Image Anal Date: 2022-04-04 Impact factor: 13.828
Authors: Jan U Becker; David Mayerich; Meghana Padmanabhan; Jonathan Barratt; Angela Ernst; Peter Boor; Pietro A Cicalese; Chandra Mohan; Hien V Nguyen; Badrinath Roysam Journal: Kidney Int Date: 2020-04-01 Impact factor: 10.612