Department of Information Convergence Engineering, Pusan National University, Yangsan, Republic of Korea.
Department of Radiology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan, Republic of Korea.
Comput Med Imaging Graph. 2024 Jul;115:102387. doi: 10.1016/j.compmedimag.2024.102387. Epub 2024 Apr 24.
Dual-energy computed tomography (CT) is an excellent substitute for identifying bone marrow edema in magnetic resonance imaging. However, it is rarely used in practice owing to its low contrast. To overcome this problem, we constructed a framework based on deep learning techniques to screen for diseases using axial bone images and to identify the local positions of bone lesions. To address the limited availability of labeled samples, we developed a new generative adversarial network (GAN) that extends expressions beyond conventional augmentation (CA) methods based on geometric transformations. We theoretically and experimentally determined that combining the concepts of data augmentation optimized for GAN training (DAG) and Wasserstein GAN yields a considerably stable generation of synthetic images and effectively aligns their distribution with that of real images, thereby achieving a high degree of similarity. The classification model was trained using real and synthetic samples. Consequently, the GAN technique used in the diagnostic test had an improved F1 score of approximately 7.8% compared with CA. The final F1 score was 80.24%, and the recall and precision were 84.3% and 88.7%, respectively. The results obtained using the augmented samples outperformed those obtained using pure real samples without augmentation. In addition, we adopted explainable AI techniques that leverage a class activation map (CAM) and principal component analysis to facilitate visual analysis of the network's results. The framework was designed to suggest an attention map and scattering plot to visually explain the disease predictions of the network.
双能 CT 是一种优秀的磁共振成像骨髓水肿替代物。但由于其对比度低，在实践中很少使用。为了克服这个问题，我们构建了一个基于深度学习技术的框架，该框架使用轴向骨图像进行疾病筛查，并识别骨病变的局部位置。为了解决标记样本有限的问题，我们开发了一种新的生成对抗网络（GAN），该网络扩展了基于几何变换的传统增强（CA）方法的表达。我们从理论和实验上确定，将用于 GAN 训练的（DAG）数据增强概念与 Wasserstein GAN 相结合，可以生成相当稳定的合成图像，并有效地将其分布与真实图像对齐，从而实现高度相似性。分类模型使用真实和合成样本进行训练。因此，与 CA 相比，诊断测试中使用的 GAN 技术的 F1 评分提高了约 7.8%。最终的 F1 评分为 80.24%，召回率和精度分别为 84.3%和 88.7%。与不进行增强的纯真实样本相比，使用增强样本获得的结果更好。此外，我们采用了可解释 AI 技术，利用类激活图（CAM）和主成分分析来促进对网络结果的可视化分析。该框架旨在建议一个注意力图和散点图，以便对网络的疾病预测进行直观解释。
