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

TL;DR

This paper presents a robust 3D deep learning framework for automatic detection of cerebral microbleeds in COVID-19 patients, addressing challenges of data variability and class imbalance, with promising clinical applicability.

Contribution

The study introduces an efficient multi-domain trained 3D deep learning model that improves microbleed detection accuracy across diverse datasets, including COVID-19 cases.

Findings

Achieved 78% recall and 80% precision on test data.

Model is robust to low-resolution images.

Average false positives of 1.6 per scan.

Abstract

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.