Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China.
School of Nursing, Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China.
Phys Med Biol. 2024 Sep 13;69(18). doi: 10.1088/1361-6560/ad7455.
The diagnosis of chronic thromboembolic pulmonary hypertension (CTEPH) is challenging due to nonspecific early symptoms, complex diagnostic processes, and small lesion sizes. This study aims to develop an automatic diagnosis method for CTEPH using non-contrasted computed tomography (NCCT) scans, enabling automated diagnosis without precise lesion annotation.A novel cascade network (CN) with multiple instance learning (CNMIL) framework was developed to improve the diagnosis of CTEPH. This method uses a CN architecture combining two Resnet-18 CNN networks to progressively distinguish between normal and CTEPH cases. Multiple instance learning (MIL) is employed to treat each 3D CT case as a 'bag' of image slices, using attention scoring to identify the most important slices. An attention module helps the model focus on diagnostically relevant regions within each slice. The dataset comprised NCCT scans from 300 subjects, including 117 males and 183 females, with an average age of 52.5 ± 20.9 years, consisting of 132 normal cases and 168 cases of lung diseases, including 88 cases of CTEPH. The CNMIL framework was evaluated using sensitivity, specificity, and the area under the curve (AUC) metrics, and compared with common 3D supervised classification networks and existing CTEPH automatic diagnosis networks.. The CNMIL framework demonstrated high diagnostic performance, achieving an AUC of 0.807, accuracy of 0.833, sensitivity of 0.795, and specificity of 0.849 in distinguishing CTEPH cases. Ablation studies revealed that integrating MIL and the CN significantly enhanced performance, with the model achieving an AUC of 0.978 and perfect sensitivity (1.000) in normal classification. Comparisons with other 3D network architectures confirmed that the integrated model outperformed others, achieving the highest AUC of 0.8419.. The CNMIL network requires no additional scans or annotations, relying solely on NCCT. This approach can improve timely and accurate CTEPH detection, resulting in better patient outcomes.
慢性血栓栓塞性肺动脉高压（CTEPH）的诊断具有挑战性，因为其早期症状不具有特异性、诊断过程复杂以及病变较小。本研究旨在开发一种使用非对比计算机断层扫描（NCCT）的 CTEPH 自动诊断方法，实现无需精确病变标注的自动诊断。本研究提出了一种新颖的级联网络（CN）与多实例学习（MIL）框架（CNMIL），以提高 CTEPH 的诊断能力。该方法使用一个结合了两个 Resnet-18CNN 网络的 CN 架构，逐步区分正常和 CTEPH 病例。多实例学习（MIL）将每个 3DCT 病例视为一个“包”的图像切片，使用注意力评分来识别最重要的切片。注意力模块帮助模型专注于每个切片中与诊断相关的区域。该数据集包含来自 300 名受试者的 NCCT 扫描，其中包括 117 名男性和 183 名女性，平均年龄为 52.5±20.9 岁，包括 132 名正常病例和 168 名肺部疾病病例，其中 88 名 CTEPH 病例。使用灵敏度、特异性和曲线下面积（AUC）指标评估了 CNMIL 框架，并与常见的 3D 监督分类网络和现有的 CTEPH 自动诊断网络进行了比较。结果显示，CNMIL 框架具有较高的诊断性能，在区分 CTEPH 病例时，AUC 为 0.807，准确率为 0.833，灵敏度为 0.795，特异性为 0.849。消融研究表明，集成 MIL 和 CN 显著提高了性能，模型在正常分类中达到了 AUC 为 0.978 和完美灵敏度（1.000）。与其他 3D 网络架构的比较证实，集成模型的表现优于其他模型，达到了最高的 AUC 0.8419。CNMIL 网络无需额外的扫描或标注，仅依靠 NCCT。这种方法可以提高 CTEPH 的及时和准确检测，从而改善患者的预后。
