Investigating the impact of supervoxel segmentation for unsupervised abnormal brain asymmetry detection

Several brain disorders are associated with abnormal brain asymmetries (asymmetric anomalies). Several computer-based methods aim to detect such anomalies automatically. Recent advances in this area use automatic unsupervised techniques that extract pairs of symmetric supervoxels in the hemispheres, model normal brain asymmetries for each pair from healthy subjects, and treat outliers as anomalies. Yet, there is no deep understanding of the impact of the supervoxel segmentation quality for abnormal asymmetry detection, especially for small anomalies, nor of the added value of using a specialized model for each supervoxel pair instead of a single global appearance model. We aim to answer these questions by a detailed evaluation of different scenarios for supervoxel segmentation and classification for detecting abnormal brain asymmetries. Experimental results on 3D MR-T1 brain images of stroke patients confirm the importance of high-quality supervoxels fit anomalies and the use of a specific classifier for each supervoxel. Next, we present a refinement of the detection method that reduces the number of false-positive supervoxels, thereby making the detection method easier to use for visual inspection and analysis of the found anomalies.

[1]  Vilmundur Gudnason,et al.  Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder , 2018, Medical Imaging: Image Processing.

[2]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[3]  Fabiano Reis,et al.  A Supervoxel-Based Approach for Unsupervised Abnormal Asymmetry Detection in Mr Images of the Brain , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[4]  Chris Rorden,et al.  Automated lesion detection on MRI scans using combined unsupervised and supervised methods , 2015, BMC Medical Imaging.

[5]  Mei-Ling Shyu,et al.  A Survey on Deep Learning , 2018, ACM Comput. Surv..

[6]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[8]  Ender Konukoglu,et al.  Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders , 2018, ArXiv.

[9]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[10]  Cam-CAN Group,et al.  The Cambridge Centre for Ageing and Neuroscience (Cam-CAN) data repository: Structural and functional MRI, MEG, and cognitive data from a cross-sectional adult lifespan sample , 2017, NeuroImage.

[11]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[12]  Ben Glocker,et al.  Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging , 2018, ArXiv.

[13]  M. Miller,et al.  Statistical Analysis of Hippocampal Asymmetry in Schizophrenia , 2001, NeuroImage.

[14]  Vittorio Murino,et al.  Deep 2D Encoder-Decoder Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation in Brain MRI , 2018, BrainLes@MICCAI.

[15]  Alexandre X. Falcão,et al.  BADRESC: Brain Anomaly Detection based on Registration Errors and Supervoxel Classification , 2020, BIOIMAGING.

[16]  R. Summers,et al.  Abnormal Chest X-Ray Identification With Generative Adversarial One-Class Classifier , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[17]  Pierrick Coupé,et al.  volBrain: An Online MRI Brain Volumetry System , 2015, Front. Neuroinform..

[18]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[19]  C. Almli,et al.  Unbiased nonlinear average age-appropriate brain templates from birth to adulthood , 2009, NeuroImage.

[20]  Alexandre X. Falcão,et al.  Extending Supervoxel-based Abnormal Brain Asymmetry Detection to the Native Image Space , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[21]  Brian B. Avants,et al.  N4ITK: Improved N3 Bias Correction , 2010, IEEE Transactions on Medical Imaging.

[22]  Athanasios V. Vasilakos,et al.  Neural networks for computer-aided diagnosis in medicine: A review , 2016, Neurocomputing.

[23]  Nico Karssemeijer,et al.  Large scale deep learning for computer aided detection of mammographic lesions , 2017, Medical Image Anal..

[24]  Olivier Clatz,et al.  Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images , 2011, NeuroImage.

[25]  Qiegen Liu,et al.  X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies , 2019, MICCAI.

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

[27]  Martin Styner,et al.  Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure , 2018, Scientific Reports.

[28]  José V. Manjón,et al.  Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised Classification , 2015, PloS one.

[29]  Alexandre X. Falcão,et al.  Modeling normal brain asymmetry in MR images applied to anomaly detection without segmentation and data annotation , 2019, Medical Imaging.

[30]  Higino Correia,et al.  Brain Tumour Segmentation based on Extremely Randomized Forest with high-level features , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[31]  Juha Koikkalainen,et al.  Fast and robust multi-atlas segmentation of brain magnetic resonance images , 2010, NeuroImage.

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

[33]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[34]  Yuankai Huo,et al.  Brain structure segmentation in the presence of multiple sclerosis lesions , 2019, NeuroImage: Clinical.

[35]  Samuel Botter Martins,et al.  An Adaptive Probabilistic Atlas for Anomalous Brain Segmentation in MR Images. , 2019, Medical physics.

[36]  Guang Yang,et al.  Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI , 2016, International Journal of Computer Assisted Radiology and Surgery.

[37]  Alexandre X. Falcão,et al.  An Iterative Spanning Forest Framework for Superpixel Segmentation , 2018, IEEE Transactions on Image Processing.

[38]  André J. Szameitat,et al.  Detection of Infarct Lesions From Single MRI Modality Using Inconsistency Between Voxel Intensity and Spatial Location—A 3-D Automatic Approach , 2008, IEEE Transactions on Information Technology in Biomedicine.

[39]  Hao Chen,et al.  VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images , 2017, NeuroImage.

[40]  Nassir Navab,et al.  Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images , 2018, BrainLes@MICCAI.

[41]  Paulo E. Rauber,et al.  Projections as visual aids for classification system design , 2017, Inf. Vis..

[42]  Daniel L. Rubin,et al.  Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions , 2017, Journal of Digital Imaging.

[43]  Lei Ai,et al.  A large, open source dataset of stroke anatomical brain images and manual lesion segmentations , 2017, Scientific Data.

[44]  Daniel Rueckert,et al.  Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy , 2009, NeuroImage.