Related Experiment Video
Updated: Aug 22, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
CMB-HUNT: Automatic detection of cerebral microbleeds using a deep neural network
Aleksandra Suwalska1, Yingzhe Wang2, Ziyu Yuan3
1Department of Data Science and Engineering, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland.
Abstract:
Cerebral microbleeds (CMBs) are gaining increasing interest due to their importance in diagnosing cerebral small vessel diseases. However, manual inspection of CMBs is time-consuming and prone to human error. Existing automated or semi-automated solutions still have insufficient detection sensitivity and specificity. Furthermore, they frequently use more than one magnetic resonance imaging modality, but these are not always available. The majority of AI-based solutions use either numeric or image data, which may not provide sufficient information about the true nature of CMBs. This paper proposes a deep neural network with multi-type input data for automated CMB detection (CMB-HUNT) using only susceptibility-weighted imaging data (SWI). Combination of SWIs and radiomic-type numerical features allowed us to identify CMBs with high accuracy without the need for additional imaging modalities or complex predictive models. Two independent datasets were used: one with 304 patients (39 with CMBs) for training and internal system validation and one with 61 patients (21 with CMBs) for external validation. For the hold-out testing dataset, CMB-HUNT reached a sensitivity of 90.0%. As results of testing showed, CMB-HUNT outperforms existing methods in terms of the number of FPs per case, which is the lowest reported thus far (0.54 FPs/patient). The proposed system was successfully applied to the independent validation set, reaching a sensitivity of 91.5% with 1.9 false positives per patient and proving its generalization potential. The results were comparable to previous studies. Our research confirms the usefulness of deep learning solutions for CMB detection based only on one MRI modality.
Insights
This study introduces CMB-HUNT, an AI tool for detecting cerebral microbleeds (CMBs) using only SWI MRI scans. CMB-HUNT achieves high accuracy and fewer false positives than existing methods, aiding in diagnosing small vessel diseases.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Medical Diagnostics
Background:
- Cerebral microbleeds (CMBs) are crucial biomarkers for cerebral small vessel diseases.
- Manual CMB detection is labor-intensive and error-prone.
- Current automated methods lack sufficient sensitivity, specificity, or require multiple MRI sequences.
Purpose of the Study:
- To develop an automated deep learning system (CMB-HUNT) for accurate CMB detection.
- To utilize only susceptibility-weighted imaging (SWI) data for CMB detection.
- To improve upon existing automated CMB detection techniques.
Main Methods:
- A deep neural network integrating SWI images and radiomic features was developed.
- The model, CMB-HUNT, was trained and validated on two independent patient datasets.
- Performance was evaluated using sensitivity and false positive rates.
Main Results:
- CMB-HUNT achieved 90.0% sensitivity on the hold-out test set with only 0.54 false positives per patient.
- External validation demonstrated 91.5% sensitivity and 1.9 false positives per patient, confirming generalization.
- The system's performance was comparable to existing studies, outperforming them in false positive reduction.
Conclusions:
- Deep learning models can effectively detect CMBs using solely SWI MRI data.
- CMB-HUNT offers a promising, accurate, and efficient solution for CMB detection.
- The system's ability to use a single MRI modality enhances its clinical applicability.
