TY - GEN

T1 - Deep Learning-Based Assessment of Cerebral Microbleeds in COVID-19

AU - Ferrer, Neus Rodeja

AU - Vendela Sagar, Malini

AU - Klein, Kiril Vadimovic

AU - Kruuse, Christina

AU - Nielsen, Mads

AU - Ghazi, Mostafa Mehdipour

N1 - Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - Cerebral Microbleeds (CMBs), typically captured as hypointensities from susceptibility-weighted imaging (SWI), are particularly important for the study of dementia, cerebrovascular disease, and normal aging. Recent studies on COVID-19 have shown an increase in CMBs of coronavirus cases. Automatic detection of CMBs is challenging due to the small size and amount of CMBs making the classes highly imbalanced, lack of publicly available annotated data, and similarity with CMB mimics such as calcifications, irons, and veins. Hence, the existing deep learning methods are mostly trained on very limited research data and fail to generalize to unseen data with high variability and cannot be used in clinical setups. To this end, we propose an efficient 3D deep learning framework that is actively trained on multi-domain data. Two public datasets assigned for normal aging, stroke, and Alzheimer's disease analysis as well as an in-house dataset for COVID-19 assessment are used to train and evaluate the models. The obtained results show that the proposed method is robust to low-resolution images and achieves 78% recall and 80% precision on the entire test set with an average false positive of 1.6 per scan.

AB - Cerebral Microbleeds (CMBs), typically captured as hypointensities from susceptibility-weighted imaging (SWI), are particularly important for the study of dementia, cerebrovascular disease, and normal aging. Recent studies on COVID-19 have shown an increase in CMBs of coronavirus cases. Automatic detection of CMBs is challenging due to the small size and amount of CMBs making the classes highly imbalanced, lack of publicly available annotated data, and similarity with CMB mimics such as calcifications, irons, and veins. Hence, the existing deep learning methods are mostly trained on very limited research data and fail to generalize to unseen data with high variability and cannot be used in clinical setups. To this end, we propose an efficient 3D deep learning framework that is actively trained on multi-domain data. Two public datasets assigned for normal aging, stroke, and Alzheimer's disease analysis as well as an in-house dataset for COVID-19 assessment are used to train and evaluate the models. The obtained results show that the proposed method is robust to low-resolution images and achieves 78% recall and 80% precision on the entire test set with an average false positive of 1.6 per scan.

KW - cerebral microbleeds

KW - COVID-19

KW - Deep learning

KW - precision-recall

KW - susceptibility-weighted imaging

UR - http://www.scopus.com/inward/record.url?scp=85172124932&partnerID=8YFLogxK

U2 - 10.1109/ISBI53787.2023.10230832

DO - 10.1109/ISBI53787.2023.10230832

M3 - Article in proceedings

AN - SCOPUS:85172124932

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1

EP - 4

BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023

PB - IEEE Computer Society Press

T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023

Y2 - 18 April 2023 through 21 April 2023

ER -