Wang Chenru, Chen Zirui, Li Muyao, Yin Haoran, Zhou Saijie, Zhang Jingliang, Zeng Xueying, Zhang Qing
School of Mathematical Sciences, Ocean University of China, Qingdao, 266000, Shandong, China.
School of Mathematical Sciences, Ocean University of China, Qingdao, 266000, Shandong, China.
Med Eng Phys. 2025 May;139:104337. doi: 10.1016/j.medengphy.2025.104337. Epub 2025 Apr 7.
Deep learning methods are increasingly popular in assisting physicians with diagnosing coronary artery disease and reducing errors caused by subjective judgment. However, accessing and labeling medical imaging data, especially coronary angiography data, is challenging. Consequently, models trained on such datasets often exhibit low accuracy, high false-positive rates, and limited generalization capabilities. We propose a Deformable Dilatable U-structure Module that can specialize a common network for coronary stenosis detection and enhance its generalization ability. Experiments demonstrate that our proposed module significantly improves the performance of various models. When applying DDUM to a model with ResNet50 as the backbone and faster R-CNN as the detector, the mean average precision increases from 33.76 to 42.39, a 25.56% improvement. Additionally, we show that DDUM enhances the network's generalization ability through transfer learning experiments. This module can improve the network's accuracy for stenosis detection and enhance the generalization ability of the original model. Fine-tuning reduces training costs and ensures that the model can be easily adapted and deployed across different devices.
深度学习方法在协助医生诊断冠状动脉疾病以及减少主观判断导致的错误方面越来越受欢迎。然而，获取和标注医学影像数据，尤其是冠状动脉造影数据，具有挑战性。因此，在此类数据集上训练的模型通常准确率较低、假阳性率较高且泛化能力有限。我们提出了一种可变形可扩张U结构模块，它可以专门用于冠状动脉狭窄检测的通用网络，并增强其泛化能力。实验表明，我们提出的模块显著提高了各种模型的性能。当将DDUM应用于以ResNet50为骨干网络、以更快的R-CNN为检测器的模型时，平均精度均值从33.76提高到42.39，提高了25.56%。此外，我们通过迁移学习实验表明DDUM增强了网络的泛化能力。该模块可以提高网络对狭窄检测的准确性，并增强原始模型的泛化能力。微调降低了训练成本，并确保模型能够轻松地在不同设备上进行适配和部署。
