Naïve Bayes classifier assisted automated detection of cerebral microbleeds in susceptibility-weighted imaging brain
Tayyab Ateeq1, Zaid Bin Faheem2, Mohamed Ghoneimy3
1Department of Computer Engineering, The University of Lahore, Lahore 54000, Pakistan.
Abstract:
Cerebral 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, manual detection is prone to errors. This paper presents a machine learning-based automated CMB detection technique in the brain susceptibility-weighted imaging (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; and (3) extracting features and applying classification models such as random forest and naïve Bayes classifiers for the detection of true positive CMBs. The proposed technique is validated on a dataset consisting of 20 subjects. The dataset is divided into training data that consist of 14 subjects with 104 microbleeds and testing data that consist of 6 subjects with 63 microbleeds. We were able to achieve 85.7% sensitivity using the random forest classifier with 4.2 false positives per CMB, and the naïve 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.
Insights
This study introduces an automated machine learning method for detecting cerebral microbleeds (CMBs) in brain scans. The technique improves accuracy and efficiency compared to manual detection, aiding in diagnosing brain disorders.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Medical Diagnostics
Background:
- Cerebral microbleeds (CMBs) are crucial indicators of neurological conditions like dementia and stroke.
- Manual detection of CMBs from susceptibility-weighted imaging (SWI) is labor-intensive and error-prone due to their complex morphology.
Purpose of the Study:
- To develop and validate a machine learning-based automated technique for detecting CMBs in brain SWI scans.
- To improve the efficiency and accuracy of CMB detection compared to traditional manual methods.
Main Methods:
- The proposed method involves brain extraction, thresholding for candidate identification, and statistical feature extraction.
- Classification models, including Random Forest and Naïve Bayes, were employed for accurate CMB detection.
- The technique was validated on a dataset of 20 subjects (104 CMBs for training, 63 for testing).
Main Results:
- The Random Forest classifier achieved 85.7% sensitivity with 4.2 false positives per CMB.
- The Naïve Bayes classifier demonstrated 90.5% sensitivity with 5.5 false positives per CMB.
- The automated technique outperformed several existing state-of-the-art methods.
Conclusions:
- The developed machine learning approach offers a promising automated solution for CMB detection in SWI.
- This method has the potential to enhance the diagnosis and monitoring of brain disorders associated with CMBs.
- The study highlights the effectiveness of statistical feature extraction and classification for improving CMB detection accuracy.
