Na ïve bayes classifier assisted automated detection of cerebral microbleeds in SWI brain images

Biochem Cell Biol. 2023 Aug 28. doi: 10.1139/bcb-2023-0156. Online ahead of print.ABSTRACTCerebral Microbleeds (CMBs) in the brain are the essential indicators of critical brain disorders such as dementia and ischemic stroke. Generally, CMBs are detected manually by experts which is an exhaustive task with limited productivity. Since, CMBs have complex morphological nature, so manual detection is prone to errors. This paper presents a machine learning-based automated Cerebral Microbleeds detection technique in the brain SWI scans based on statistical feature extraction and classification. The proposed method consists of three steps: 1. Removal of the skull and extraction of the brain 2. Thresholding for the extraction of initial candidates 3. Extracting features and applying classification models such as random forest and naïve bayes classifiers for the detection of true positive cerebral microbleeds. The proposed technique is validated on a dataset consisting of 20 subjects. The dataset is divided into training data which consists of 14 subjects with 104 microbleeds and testing data which consists of 6 subjects with 63 microbleeds. We were able to 85.7% sensitivity using the random forest classifier with 4.2 false positives per CMB and the naive bayes classifier achieved 90.5% sensitivity with 5.5 false positives per CMB. The proposed technique outperformed many state-of-the-art methods proposed in previous studies.PMID:37639730 | DOI:10.1139/bcb-2023-0156

Source: Biochemistry and Cell Biology - August 28, 2023 Category: Biochemistry Authors: Tayyab Ateeq Zaid Bin Faheem Mohamed Ghoneimy Dr Jehad Ali PhD Computer Engineering Yang Li Abdullah Baz Source Type: research