Unsupervised Lesion Detection via Image Restoration with a Normative Prior

Suhang You, Kerem C. Tezcan, Xiaoran Chen, Ender Konukoglu
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:540-556, 2019.

Abstract

While human experts excel in and rely on identifying an abnormal structure when assessing a medical scan, without necessarily specifying the type, current unsupervised abnormality detection methods are far from being practical. Recently proposed deep-learning (DL) based methods were initial attempts at showing the capabilities of this approach. In this work, we propose an outlier detection method combining image restoration with unsupervised learning based on DL. A normal anatomy prior is learned by training a Gaussian Mixture Variational Auto-Encoder (GMVAE) on images from healthy individuals. This prior is then used in a Maximum-A-Posteriori (MAP) restoration model to detect outliers. Abnormal lesions, not represented in the prior, are removed from the images during restoration to satisfy the prior and the difference between original and restored images form the detection of the method. We evaluated the proposed method on Magnetic Resonance Images (MRI) of patients with brain tumors and compared against previous baselines. Experimental results indicate that the method is capable of detecting lesions in the brain and achieves improvement over the current state of the art.

Cite this Paper


BibTeX
@InProceedings{pmlr-v102-you19a, title = {Unsupervised Lesion Detection via Image Restoration with a Normative Prior}, author = {You, Suhang and Tezcan, Kerem C. and Chen, Xiaoran and Konukoglu, Ender}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {540--556}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/you19a/you19a.pdf}, url = { http://proceedings.mlr.press/v102/you19a.html }, abstract = {While human experts excel in and rely on identifying an abnormal structure when assessing a medical scan, without necessarily specifying the type, current unsupervised abnormality detection methods are far from being practical. Recently proposed deep-learning (DL) based methods were initial attempts at showing the capabilities of this approach. In this work, we propose an outlier detection method combining image restoration with unsupervised learning based on DL. A normal anatomy prior is learned by training a Gaussian Mixture Variational Auto-Encoder (GMVAE) on images from healthy individuals. This prior is then used in a Maximum-A-Posteriori (MAP) restoration model to detect outliers. Abnormal lesions, not represented in the prior, are removed from the images during restoration to satisfy the prior and the difference between original and restored images form the detection of the method. We evaluated the proposed method on Magnetic Resonance Images (MRI) of patients with brain tumors and compared against previous baselines. Experimental results indicate that the method is capable of detecting lesions in the brain and achieves improvement over the current state of the art.} }
Endnote
%0 Conference Paper %T Unsupervised Lesion Detection via Image Restoration with a Normative Prior %A Suhang You %A Kerem C. Tezcan %A Xiaoran Chen %A Ender Konukoglu %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-you19a %I PMLR %P 540--556 %U http://proceedings.mlr.press/v102/you19a.html %V 102 %X While human experts excel in and rely on identifying an abnormal structure when assessing a medical scan, without necessarily specifying the type, current unsupervised abnormality detection methods are far from being practical. Recently proposed deep-learning (DL) based methods were initial attempts at showing the capabilities of this approach. In this work, we propose an outlier detection method combining image restoration with unsupervised learning based on DL. A normal anatomy prior is learned by training a Gaussian Mixture Variational Auto-Encoder (GMVAE) on images from healthy individuals. This prior is then used in a Maximum-A-Posteriori (MAP) restoration model to detect outliers. Abnormal lesions, not represented in the prior, are removed from the images during restoration to satisfy the prior and the difference between original and restored images form the detection of the method. We evaluated the proposed method on Magnetic Resonance Images (MRI) of patients with brain tumors and compared against previous baselines. Experimental results indicate that the method is capable of detecting lesions in the brain and achieves improvement over the current state of the art.
APA
You, S., Tezcan, K.C., Chen, X. & Konukoglu, E.. (2019). Unsupervised Lesion Detection via Image Restoration with a Normative Prior. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:540-556 Available from http://proceedings.mlr.press/v102/you19a.html .

Related Material