M-DFNet: Multi-phase Discriminative Feature Network for Retrieval of Focal Liver Lesions
M-DFNet: Multi-phase Discriminative Feature Network for Retrieval of Focal Liver Lesions
复制标题
DOI：
10.1145/3460426.3463672
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Yingying Xu;Jing Liu;Lanfen Lin;Hongjie Hu;Ruofeng Tong;Jingsong Li;Yenwei Chen
中科院分区：
文献类型：
--
作者：
Yingying Xu;Jing Liu;Lanfen Lin;Hongjie Hu;Ruofeng Tong;Jingsong Li;Yenwei Chen
基于内容的医学图像检索（CBMIR）在计算机辅助诊断中发挥着重要作用，可以帮助放射科医生检测和描述肝脏局灶性病变（FLL）。深度学习在CBMIR上取得了令人兴奋的表现。而使用softmax loss训练的深度学习模型生成的特征总是可分离的，但不够区分，这不足以执行检索任务。在本文中，我们提出了一个多阶段判别特征网络（M-DFNet），它具有DeepExtracter和特征细化模块（FRModule），可以在中心损失和softmax损失的联合监督下学习判别和可分离特征。混合损失使得能够最小化类内变化并尽可能地扩大类间差异。FRModule被提出来基于学习的类中心重新校准深度特征，以解决FLL的复杂成像表现，并进一步增强特征区分和泛化。多期计算机断层扫描（CT）图像包含FLL诊断的关键信息。因此，M-DFNet的设计，以科普多阶段的信息，我们探索了一个合适的和有效的方法，多阶段的特征集成有限的数据。实验结果清楚地表明，我们提出的方法具有很强的性能优势。
Content based medical image retrieval (CBMIR) plays a great role in computer aided diagnosis for assisting radiologists to detect and characterize focal liver lesions (FLLs). Deep learning has gained exciting performance on CBMIR. While the features generated by deep learning models trained using softmax loss are always separable but not discriminative enough, which is insufficient for retrieval task. In this paper, we propose a multi-phase discriminative feature network (M-DFNet) with a DeepExtracter and a feature refine module (FRModule) to learn discriminative and separable features under a joint supervision of center loss and softmax loss. The hybrid loss enables to minimize intra-class variations and enlarge inter-class differences as much as possible. The FRModule is proposed to recalibrate the deep features based on the learned class centers to tackle the complex imaging manifestations of FLLs and further enhance both the feature discrimination and generalization. Multi-phase computed tomography (CT) images contain pivotal information for diagnosis of FLLs. Thus the M-DFNet is designed to cope with multi-phase information and we explore an appropriate and effective method for multi-phase feature integration on limited data. Experimental results clearly demonstrate strong performance superiority by our proposed method.