Abdelhamid Abeer, El-Ghamry Amir, Abdelhay Ehab H, Abo-Zahhad Mohammed M, Moustafa Hossam El-Din
Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, 35516, Egypt.
Computer Science Department, Faculty of Computers and Information, Mansoura University, Mansoura, 35516, Egypt.
Sci Rep. 2025 Aug 26;15(1):31443. doi: 10.1038/s41598-025-16238-4.
Pulmonary embolism (PE) represents a severe, life-threatening cardiovascular condition and is notably the third leading cause of cardiovascular mortality, after myocardial infarction and stroke. This pathology occurs when blood clots obstruct the pulmonary arteries, impeding blood flow and oxygen exchange in the lungs. Prompt and accurate detection of PE is critical for appropriate clinical decision-making and patient survival. The complexity involved in interpreting medical images can often results misdiagnosis. However, recent advances in Deep Learning (DL) have substantially improved the capabilities of Computer-Aided Diagnosis (CAD) systems. Despite these advancements, existing single-model DL methods are limited when handling complex, diverse, and imbalanced medical imaging datasets. Addressing this gap, our research proposes an ensemble framework for classifying PE, capitalizing on the unique capabilities of ResNet50, DenseNet121, and Swin Transformer models. This ensemble method harnesses the complementary strengths of convolutional neural networks (CNNs) and vision transformers (ViTs), leading to improved prediction accuracy and model robustness. The proposed methodology includes a sophisticated preprocessing pipeline leveraging autoencoder (AE)-based dimensionality reduction, data augmentation to avoid overfitting, discrete wavelet transform (DWT) for multiscale feature extraction, and Sobel filtering for effective edge detection and noise reduction. The proposed model was rigorously evaluated using the public Radiological Society of North America (RSNA-STR) PE dataset, demonstrating remarkable performance metrics of 97.80% accuracy and a 0.99 for Area Under Receiver Operating Curve (AUROC). Comparative analysis demonstrated superior performance over state-of-the-art pre-trained models and recent ViT-based approaches, highlighting our method's effectiveness in improving early PE detection and providing robust support for clinical decision-making.
肺栓塞（PE）是一种严重的、危及生命的心血管疾病，是心血管疾病死亡的第三大主要原因，仅次于心肌梗死和中风。当血凝块阻塞肺动脉，阻碍肺部的血液流动和氧气交换时，就会发生这种病症。及时准确地检测PE对于适当的临床决策和患者生存至关重要。解读医学图像所涉及的复杂性常常导致误诊。然而，深度学习（DL）的最新进展极大地提高了计算机辅助诊断（CAD）系统的能力。尽管有这些进展，但现有的单模型DL方法在处理复杂、多样和不平衡的医学成像数据集时存在局限性。为了弥补这一差距，我们的研究提出了一个用于对PE进行分类的集成框架，利用ResNet50、DenseNet121和Swin Transformer模型的独特能力。这种集成方法利用了卷积神经网络（CNN）和视觉Transformer（ViT）的互补优势，从而提高了预测准确性和模型鲁棒性。所提出的方法包括一个复杂的预处理管道，利用基于自动编码器（AE）的降维、数据增强以避免过拟合、离散小波变换（DWT）进行多尺度特征提取，以及Sobel滤波进行有效的边缘检测和降噪。所提出的模型使用北美放射学会（RSNA-STR）PE公共数据集进行了严格评估，展示了97.80%的准确率和0.99的受试者工作特征曲线下面积（AUROC）等卓越的性能指标。对比分析表明，该模型的性能优于现有最先进的预训练模型和最近基于ViT的方法，突出了我们的方法在改善早期PE检测方面的有效性，并为临床决策提供了有力支持。
