Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders

Lesion detection in brain Magnetic Resonance Images (MRI) remains a challenging task. State-of-the-art approaches are mostly based on supervised learning making use of large annotated datasets. Human beings, on the other hand, even non-experts, can detect most abnormal lesions after seeing a handful of healthy brain images. Replicating this capability of using prior information on the appearance of healthy brain structure to detect lesions can help computers achieve human level abnormality detection, specifically reducing the need for numerous labeled examples and bettering generalization of previously unseen lesions. To this end, we study detection of lesion regions in an unsupervised manner by learning data distribution of brain MRI of healthy subjects using auto-encoder based methods. We hypothesize that one of the main limitations of the current models is the lack of consistency in latent representation. We propose a simple yet effective constraint that helps mapping of an image bearing lesion close to its corresponding healthy image in the latent space. We use the Human Connectome Project dataset to learn distribution of healthy-appearing brain MRI and report improved detection, in terms of AUC, of the lesions in the BRATS challenge dataset.

[1]  Mubarak Shah,et al.  Learning object motion patterns for anomaly detection and improved object detection , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Dong Hye Ye,et al.  Context-sensitive Classication Forests for Segmentation of Brain Tumor Tissues , 2012 .

[3]  Jonathan Lawry,et al.  Symbolic and Quantitative Approaches to Reasoning with Uncertainty , 2009 .

[4]  Murray Shanahan,et al.  Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders , 2016, ArXiv.

[5]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[6]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[7]  Yang Feng,et al.  Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications , 2018, WWW.

[8]  Nahla Ben Amor,et al.  Brain Tumor Segmentation Using Support Vector Machines , 2009, ECSQARU.

[9]  B. Ravi Kiran,et al.  An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos , 2018, J. Imaging.

[10]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[11]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[12]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[13]  Guido Gerig,et al.  A brain tumor segmentation framework based on outlier detection , 2004, Medical Image Anal..

[14]  Subutai Ahmad,et al.  Unsupervised real-time anomaly detection for streaming data , 2017, Neurocomputing.

[15]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[16]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[17]  Victor Alves,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2016, IEEE Transactions on Medical Imaging.

[18]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[19]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[20]  Daisuke Sato,et al.  A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes , 2018, Medical Imaging.