Department of Radiology, Stanford University School of Medicine, Stanford, CA, United States of America.
Department of Radiology, Stanford University School of Medicine, Stanford, CA, United States of America.
Comput Med Imaging Graph. 2018 Apr;65:167-175. doi: 10.1016/j.compmedimag.2017.05.002. Epub 2017 May 5.
This paper presents a deep-learning-based CADx for the differential diagnosis of embryonal (ERMS) and alveolar (ARMS) subtypes of rhabdomysarcoma (RMS) solely by analyzing multiparametric MR images. We formulated an automated pipeline that creates a comprehensive representation of tumor by performing a fusion of diffusion-weighted MR scans (DWI) and gadolinium chelate-enhanced T1-weighted MR scans (MRI). Finally, we adapted transfer learning approach where a pre-trained deep convolutional neural network has been fine-tuned based on the fused images for performing classification of the two RMS subtypes. We achieved 85% cross validation prediction accuracy from the fine-tuned deep CNN model. Our system can be exploited to provide a fast, efficient and reproducible diagnosis of RMS subtypes with less human interaction. The framework offers an efficient integration between advanced image processing methods and cutting-edge deep learning techniques which can be extended to deal with other clinical domains that involve multimodal imaging for disease diagnosis.
本文提出了一种基于深度学习的 CADx，仅通过分析多参数磁共振图像即可对胚胎性（ERMS）和肺泡性（ARMS）横纹肌肉瘤（RMS）亚型进行鉴别诊断。我们制定了一个自动化流水线，通过融合弥散加权磁共振扫描（DWI）和钆螯合物增强 T1 加权磁共振扫描（MRI）来创建肿瘤的综合表现。最后，我们采用了迁移学习方法，其中对预先训练的深度卷积神经网络进行了微调，以便根据融合图像对两种 RMS 亚型进行分类。我们从经过微调的深度 CNN 模型中实现了 85%的交叉验证预测准确性。我们的系统可用于提供快速、高效且可重复的 RMS 亚型诊断，减少人为交互。该框架提供了先进图像处理方法和前沿深度学习技术之间的有效集成，可扩展到涉及多模态成像用于疾病诊断的其他临床领域。
