TY - JOUR
T1 - Investigating the impact of supervoxel segmentation for unsupervised abnormal brain asymmetry detection
AU - Martins, Samuel B.
AU - Telea, Alexandru C.
AU - Falcão, Alexandre X.
N1 - Funding Information:
The authors thank CNPq ( 303808/2018-7 ) and FAPESP ( 2014/12236-1 ) for the financial support, and NVIDIA for providing a graphics card.
Publisher Copyright:
© 2020 Elsevier Ltd
PY - 2020/10
Y1 - 2020/10
N2 - 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.
AB - 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.
KW - Abnormal brain asymmetry
KW - Anomaly detection
KW - MR images of the brain
KW - One-class classification
KW - Supervoxel segmentation
UR - http://www.scopus.com/inward/record.url?scp=85089742497&partnerID=8YFLogxK
U2 - 10.1016/j.compmedimag.2020.101770
DO - 10.1016/j.compmedimag.2020.101770
M3 - Article
C2 - 32854021
AN - SCOPUS:85089742497
SN - 0895-6111
VL - 85
JO - Computerized medical imaging and graphics
JF - Computerized medical imaging and graphics
M1 - 101770
ER -