BADRESC: Brain Anomaly Detection based on Registration Errors and Supervoxel Classification

Samuel B. Martins, Samuel B. Martins, Samuel B. Martins, Alexandre X. Falcão, Alexandru C. Telea

2020

Abstract

Automatic detection of brain anomalies in MR images is very challenging and complex due to intensity similarity between lesions and normal tissues as well as the large variability in shape, size, and location among different anomalies. Inspired by groupwise shape analysis, we adapt a recent fully unsupervised supervoxel-based approach (SAAD) — designed for abnormal asymmetry detection of the hemispheres — to detect brain anomalies from registration errors. Our method, called BADRESC, extracts supervoxels inside the right and left hemispheres, cerebellum, and brainstem, models registration errors for each supervoxel, and treats outliers as anomalies. Experimental results on MR-T1 brain images of stroke patients show that BADRESC attains similar detection rate for hemispheric lesions in comparison to SAAD with substantially less false positives. It also presents promising detection scores for lesions in the cerebellum and brainstem.

Download


Paper Citation


in Harvard Style

Martins S., Falcão A. and Telea A. (2020). BADRESC: Brain Anomaly Detection based on Registration Errors and Supervoxel Classification. In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 2: BIOIMAGING; ISBN 978-989-758-398-8, SciTePress, pages 74-81. DOI: 10.5220/0008987800740081


in Bibtex Style

@conference{bioimaging20,
author={Samuel B. Martins and Alexandre X. Falcão and Alexandru C. Telea},
title={BADRESC: Brain Anomaly Detection based on Registration Errors and Supervoxel Classification},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 2: BIOIMAGING},
year={2020},
pages={74-81},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008987800740081},
isbn={978-989-758-398-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 2: BIOIMAGING
TI - BADRESC: Brain Anomaly Detection based on Registration Errors and Supervoxel Classification
SN - 978-989-758-398-8
AU - Martins S.
AU - Falcão A.
AU - Telea A.
PY - 2020
SP - 74
EP - 81
DO - 10.5220/0008987800740081
PB - SciTePress