Kiernan Maxwell J, Al Mukaddim Rashid, Mitchell Carol C, Maybock Jenna, Wilbrand Stephanie M, Dempsey Robert J, Varghese Tomy
Department of Medical Physics, University of Wisconsin School of Medicine and Public health (UW-SMPH), 1111 Highland Ave #1005, Madison, WI 53705, United States.
Department of Medicine, UW-SMPH, 5158 Medical Foundation Centennial Building, 1685 Highland Ave, Madison, WI 53792, United States.
ArXiv. 2025 Jul 30:arXiv:2507.22848v1.
Ultrasound imaging plays a pivotal role in diagnosing carotid atherosclerosis, a significant precursor to cardiovascular and cerebrovascular diseases and events. This noninvasive modality provides real-time, high-resolution images, allowing clinicians to assess atherosclerotic plaques in the carotid arteries without invasive procedures. Early detection using ultrasound aids in timely interventions, reducing the risk of adverse cardiovascular events. Purpose: In this study, we present the refinement of a Mask R-CNN model initially designed for carotid lumen detection to automatically generate bounding boxes (BB) enclosing atherosclerotic plaque for segmentation to assist in our ultrasound elastography workflow.
We utilize a PyTorch torchvision implementation of the Mask R-CNN for carotid plaque detection and BB placement. Our dataset consists of 118 severe stenotic carotid plaques from presenting patients, clinically indicated for a carotid endarterectomy. Due to the variability of plaque presentation in the dataset, a multitude of different R-CNN models were observed to have varying results based on the allowed number of prediction regions. An overview analysis looking at shared predictions from these models showed a slight improvement compared to the individual model results.
Evaluation metrics such as Dice similarity coefficient and intersection over Union are employed. The model trained with 5 maximum BB prediction regions and tested with 2 maximum BB prediction regions produced the highest individual accuracy with a Dice score of 0.74 and intersection over union of 0.61. A filtered combined analysis of all the models demonstrated a slight increase in performance with scores of 0.76 and 0.61 respectively.
Due to the significant variation in plaque presentation and types amongst presenting patients, the accuracy of the Plaque Mask R-CNN network would benefit from the incorporation of additional patient datasets to incorporate increased variation into the training dataset.
超声成像在诊断颈动脉粥样硬化中起着关键作用，颈动脉粥样硬化是心血管和脑血管疾病及事件的重要先兆。这种非侵入性检查方式可提供实时、高分辨率图像，使临床医生无需进行侵入性操作就能评估颈动脉中的动脉粥样硬化斑块。利用超声进行早期检测有助于及时干预，降低不良心血管事件的风险。目的：在本研究中，我们对最初设计用于颈动脉管腔检测的Mask R-CNN模型进行了改进，以自动生成围绕动脉粥样硬化斑块的边界框（BB）用于分割，辅助我们的超声弹性成像工作流程。
我们利用PyTorch的torchvision实现的Mask R-CNN进行颈动脉斑块检测和BB放置。我们的数据集由118例来自就诊患者的严重狭窄颈动脉斑块组成，这些患者临床上有颈动脉内膜切除术的指征。由于数据集中斑块表现的变异性，观察到许多不同的R-CNN模型根据允许的预测区域数量会有不同的结果。对这些模型的共享预测进行的概述分析显示，与单个模型结果相比有轻微改进。
采用了如骰子相似系数和交并比等评估指标。使用5个最大BB预测区域进行训练并使用2个最大BB预测区域进行测试的模型产生了最高的个体准确率，骰子评分为0.74，交并比为0.61。对所有模型进行的过滤后综合分析显示性能略有提高，分数分别为0.76和0.61。
由于就诊患者中斑块表现和类型存在显著差异，斑块Mask R-CNN网络的准确性将受益于纳入更多患者数据集，以便在训练数据集中纳入更多变异性。
