Sundaresan Vaanathi, Arthofer Christoph, Zamboni Giovanna, Murchison Andrew G, Dineen Robert A, Rothwell Peter M, Auer Dorothee P, Wang Chaoyue, Miller Karla L, Tendler Benjamin C, Alfaro-Almagro Fidel, Sotiropoulos Stamatios N, Sprigg Nikola, Griffanti Ludovica, Jenkinson Mark
Department of Computational and Data Sciences, Indian Institute of Science, Bengaluru, Karnataka, India.
Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom.
Front Neuroinform. 2023 Jul 10;17:1204186. doi: 10.3389/fninf.2023.1204186. eCollection 2023.
Cerebral microbleeds (CMBs) are associated with white matter damage, and various neurodegenerative and cerebrovascular diseases. CMBs occur as small, circular hypointense lesions on T2*-weighted gradient recalled echo (GRE) and susceptibility-weighted imaging (SWI) images, and hyperintense on quantitative susceptibility mapping (QSM) images due to their paramagnetic nature. Accurate automated detection of CMBs would help to determine quantitative imaging biomarkers (e.g., CMB count) on large datasets. In this work, we propose a fully automated, deep learning-based, 3-step algorithm, using structural and anatomical properties of CMBs from any single input image modality (e.g., GRE/SWI/QSM) for their accurate detections.
In our method, the first step consists of an initial candidate detection step that detects CMBs with high sensitivity. In the second step, candidate discrimination step is performed using a knowledge distillation framework, with a multi-tasking teacher network that guides the student network to classify CMB and non-CMB instances in an offline manner. Finally, a morphological clean-up step further reduces false positives using anatomical constraints. We used four datasets consisting of different modalities specified above, acquired using various protocols and with a variety of pathological and demographic characteristics.
On cross-validation within datasets, our method achieved a cluster-wise true positive rate (TPR) of over 90% with an average of <2 false positives per subject. The knowledge distillation framework improves the cluster-wise TPR of the student model by 15%. Our method is flexible in terms of the input modality and provides comparable cluster-wise TPR and better cluster-wise precision compared to existing state-of-the-art methods. When evaluating across different datasets, our method showed good generalizability with a cluster-wise TPR >80 % with different modalities. The python implementation of the proposed method is openly available.
脑微出血（CMB）与白质损伤以及各种神经退行性和脑血管疾病相关。在T2 *加权梯度回波（GRE）和磁敏感加权成像（SWI）图像上，CMB表现为小的圆形低信号病变，由于其顺磁性性质，在定量磁敏感图谱（QSM）图像上为高信号。准确自动检测CMB有助于在大型数据集中确定定量成像生物标志物（例如，CMB计数）。在这项工作中，我们提出了一种基于深度学习的全自动三步算法，利用来自任何单一输入图像模态（例如，GRE/SWI/QSM）的CMB的结构和解剖特性进行准确检测。
在我们的方法中，第一步包括一个初始候选检测步骤，该步骤以高灵敏度检测CMB。第二步是候选判别步骤，使用知识蒸馏框架，通过一个多任务教师网络以离线方式指导学生网络对CMB和非CMB实例进行分类。最后，一个形态学清理步骤利用解剖学约束进一步减少假阳性。我们使用了四个数据集，这些数据集由上述不同模态组成，采用各种协议采集，具有各种病理和人口统计学特征。
在数据集内的交叉验证中，我们的方法实现了超过90%的聚类真阳性率（TPR），平均每个受试者<2个假阳性。知识蒸馏框架将学生模型的聚类TPR提高了15%。我们的方法在输入模态方面具有灵活性，与现有的最先进方法相比，提供了相当的聚类TPR和更好的聚类精度。在跨不同数据集评估时，我们的方法表现出良好的通用性，不同模态下的聚类TPR>80%。所提出方法的Python实现是公开可用的。
