Hassanzadeh Tahereh, Sachdev Sonal, Wen Wei, Sachdev Perminder S, Sowmya Arcot
School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia.
St Vincent's Hospital, Medical Imaging Department, Sydney, Australia.
Neuroimage Clin. 2025 Aug 27;48:103873. doi: 10.1016/j.nicl.2025.103873.
Cerebral microbleeds (CMB) are small hypointense lesions visible on gradient echo (GRE) or susceptibility-weighted (SWI) MRI, serving as critical biomarkers for various cerebrovascular and neurological conditions. Accurate quantification of CMB is essential, as their number correlates with the severity of conditions such as small vessel disease, stroke risk and cognitive decline. Current detection methods depend on manual inspection, which is time-consuming and prone to variability. Automated detection using deep learning presents a transformative solution but faces challenges due to the heterogeneous appearance of CMB, high false-positive rates, and similarity to other artefacts. This study investigates the application of deep learning techniques to public (ADNI and AIBL) and private datasets (OATS and MAS), leveraging GRE and SWI MRI modalities to enhance CMB detection accuracy, reduce false positives, and ensure robustness in both clinical and normal cases (i.e., scans without cerebral microbleeds). A 3D convolutional neural network (CNN) was developed for automated detection, complemented by a You Only Look Once (YOLO)-based approach to address false positive cases in more complex scenarios. The pipeline incorporates extensive preprocessing and validation, demonstrating robust performance across a diverse range of datasets. The proposed method achieves remarkable performance across four datasets, ADNI: Balanced accuracy: 0.953, AUC: 0.955, Precision: 0.954, Sensitivity: 0.920, F1-score: 0.930, AIBL: Balanced accuracy: 0.968, AUC: 0.956, Precision: 0.956, Sensitivity: 0.938, F1-score: 0.946, MAS: Balanced accuracy: 0.889, AUC: 0.889, Precision: 0.948, Sensitivity: 0.779, F1-score: 0.851, and OATS dataset: Balanced accuracy: 0.93, AUC: 0.930, Precision: 0.949, Sensitivity: 0.862, F1-score: 0.900. These results highlight the potential of deep learning models to improve early diagnosis and support treatment planning for conditions associated with CMB.
脑微出血（CMB）是在梯度回波（GRE）或磁敏感加权成像（SWI）磁共振成像（MRI）上可见的小低信号病变，是各种脑血管和神经疾病的关键生物标志物。准确量化CMB至关重要，因为其数量与诸如小血管疾病、中风风险和认知衰退等疾病的严重程度相关。当前的检测方法依赖于人工检查，既耗时又容易出现差异。使用深度学习的自动检测提供了一种变革性的解决方案，但由于CMB外观的异质性、高假阳性率以及与其他伪影的相似性而面临挑战。本研究调查了深度学习技术在公共数据集（阿尔茨海默病神经影像学计划（ADNI）和澳大利亚成像生物标志物与生活方式旗舰研究（AIBL））和私有数据集（老年认知和衰老轨迹研究（OATS）和多模态衰老研究（MAS））中的应用，利用GRE和SWI MRI模态提高CMB检测的准确性，减少假阳性，并确保在临床和正常病例（即没有脑微出血的扫描）中都具有稳健性。开发了一种三维卷积神经网络（CNN）用于自动检测，并辅以基于你只看一次（YOLO）的方法来处理更复杂场景中的假阳性病例。该流程包含广泛的预处理和验证，在各种不同的数据集上都表现出稳健的性能。所提出的方法在四个数据集上取得了显著的性能：ADNI：平衡准确率：0.953，曲线下面积（AUC）：0.955，精确率：0.954，灵敏度：0.920，F1分数：0.930；AIBL：平衡准确率：0.968，AUC：0.956，精确率：0.956，灵敏度：0.938，F1分数：0.946；MAS：平衡准确率：0.889，AUC：0.889，精确率：0.948，灵敏度：0.779，F分数：0.851；以及OATS数据集：平衡准确率：0.93，AUC：0.930，精确率：0.949，灵敏度：0.862，F1分数：0.900。这些结果凸显了深度学习模型在改善与CMB相关疾病的早期诊断和支持治疗规划方面的潜力。
