Guo Zhongping, Liu Ying, Xu Jingxu, Huang Chencui, Zhang Fandong, Miao Chongchang, Zhang Yonggang, Li Mengshuang, Shan Hangsheng, Gu Yan
Department of Radiology, The First People's Hospital of Lianyungang, Lianyungang Clinical College of Nanjing Medical University, Lianyungang, China.
Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd., Beijing, China.
Front Neurol. 2025 Jan 13;15:1480792. doi: 10.3389/fneur.2024.1480792. eCollection 2024.
To develop a deep learning (DL) model for carotid plaque detection based on CTA images and evaluate the clinical application feasibility and value of the model.
We retrospectively collected data from patients with carotid atherosclerotic plaques who underwent continuous CTA examinations of the head and neck at a tertiary hospital from October 2020 to October 2022. The model combined ResUNet with the Pyramid Scene Parsing Network (PSPNet) to enhance plaque segmentation. Patient plaques were divided into training, validation, and testing sets in a ratio of 7:1.5:1.5. We analyzed recall (lesion-level sensitivity), sensitivity (patient-level), and precision to evaluate the model's diagnostic performance for carotid plaques. The two stepwise early-stage clinical validation study (Comparison study and Model-human study) was used to simulate real clinical plaque diagnostic scenarios.
In total, 647 patients were included in the dataset, including 475 for training, 86 for validation, and 86 for testing. The DL model based on CTA images showed good precision in plaque diagnosis (validation set: precision = 80.49%, sensitivity = 90.70%, recall = 84.62%; test set: precision = 78.37%, sensitivity = 91.86%, recall = 84.58%). In addition, subgroup analysis of the plaque was carried out in the test set. The model had high accuracy in identifying plaques at different locations (Recall: 83.72, 76.32, 89.25, and 83.02%) and with different morphologies (Recall: 86.03, 79.17%). This model also analyzed the results of different types of plaques and showed good to moderate plaque diagnostic accuracy for different plaque types (Recall: 70.00, 86.87, 84.29%). Especially, in the clinical application scenario analysis, the model's diagnostic results for plaques were found to be higher than those of 4 out of 6 radiologists ( < 0.001). Furthermore, in Model-human Real Clinical Scenarios study, we found that the model improved the radiologists' sensitivity in diagnosing plaques. Additionally, the model's diagnostic time for plaques (6 s) was found to be significantly shorter than that all of radiologists ( < 0.001).
This AI model demonstrated strong clinical potential for carotid plaque detection with improved clinician diagnostic performance, shortening time, and practical implementation in real-world clinical cases.
基于CTA图像开发一种用于颈动脉斑块检测的深度学习（DL）模型，并评估该模型的临床应用可行性和价值。
我们回顾性收集了2020年10月至2022年10月在一家三级医院接受头颈部连续CTA检查的颈动脉粥样硬化斑块患者的数据。该模型将ResUNet与金字塔场景解析网络（PSPNet）相结合以增强斑块分割。患者的斑块按7:1.5:1.5的比例分为训练集、验证集和测试集。我们分析召回率（病灶级敏感性）、敏感性（患者级）和精确率来评估该模型对颈动脉斑块的诊断性能。采用两步法早期临床验证研究（比较研究和模型-人研究）来模拟真实的临床斑块诊断场景。
数据集中共纳入647例患者，其中475例用于训练，86例用于验证，86例用于测试。基于CTA图像的DL模型在斑块诊断中显示出良好的精确率（验证集：精确率 = 80.49%，敏感性 = 90.70%，召回率 = 84.62%；测试集：精确率 = 78.37%，敏感性 = 91.86%，召回率 = 84.58%）。此外，在测试集中对斑块进行了亚组分析。该模型在识别不同位置的斑块（召回率：83.72%、76.32%、89.25%和83.02%）和不同形态的斑块（召回率：86.03%、79.17%）方面具有较高的准确性。该模型还分析了不同类型斑块的结果，对不同类型的斑块显示出良好至中等的斑块诊断准确性（召回率：70.00%、86.87%、84.29%）。特别是，在临床应用场景分析中，发现该模型对斑块的诊断结果高于6名放射科医生中的4名（<0.001）。此外，在模型-人真实临床场景研究中，我们发现该模型提高了放射科医生诊断斑块的敏感性。此外，发现该模型对斑块的诊断时间（6秒）明显短于所有放射科医生的诊断时间（<0.001）。
该人工智能模型在颈动脉斑块检测方面显示出强大的临床潜力，可提高临床医生的诊断性能、缩短时间并在实际临床病例中切实可行。
