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

被引：0
作者：
Martins S.B. [1 ,2 ,3 ]
Telea A.C. [4 ]
Falcão A.X. [1 ]
机构：
[1] Laboratory of Image Data Science (LIDS), Institute of Computing, University of Campinas
[2] Bernoulli Institute, University of Groningen
[3] Federal Institute of São Paulo, Campinas
[4] Department of Information and Computing Sciences, Utrecht University
来源：
Computerized Medical Imaging and Graphics | 2020年 / 85卷
基金：
巴西圣保罗研究基金会;
关键词：
Abnormal brain asymmetry; Anomaly detection; MR images of the brain; One-class classification; Supervoxel segmentation;
D O I：
10.1016/j.compmedimag.2020.101770
中图分类号：
学科分类号：
摘要：
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. © 2020 Elsevier Ltd
引用
收藏
相关论文
共 45 条
[1]  
Akkus Z., Et al., Deep learning for brain MRI segmentation: state of the art and future directions, J. Digit. Imaging, 30, pp. 449-459, (2017)
[2]  
Aljabar P., Heckemann R.A., Hammers A., Hajnal J.V., Rueckert D., Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy, Neuroimage, 46, pp. 726-738, (2009)
[3]  
Aslani S., Dayan M., Murino V., Sona D., Deep 2D encoder-decoder convolutional neural network for multiple sclerosis lesion segmentation in brain MRI, Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 132-141, (2018)
[4]  
Atlason A., Love H.E., Sigurdsson S., Gudnason V., Ellingsen L.M., Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder, SPIE Med. Imag., vol. 10949, pp. 372-378, (2019)
[5]  
Baur C., Wiestler B., Albarqouni S., Navab N., Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images, (2018)
[6]  
Chen X., Konukoglu E., Unsupervised Detection of Lesions in Brain MRI Using Constrained Adversarial Auto-Encoders, (2018)
[7]  
Chen X., Pawlowski N., Rajchl M., Glocker B., Konukoglu E., Deep Generative Models in the Real-World: An Open Challenge From Medical Imaging, (2018)
[8]  
Chen H., Et al., VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images, Neuroimage, 170, pp. 446-455, (2018)
[9]  
Commowick O., Et al., Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure, Sci. Rep., 8, (2018)
[10]  
Fonov V.S., Et al., Unbiased nonlinear average age-appropriate brain templates from birth to adulthood, Neuroimage, 47, (2009)
12345