Deep Collocative Learning for Immunofixation Electrophoresis Image Analysis
Deep Collocative Learning for Immunofixation Electrophoresis Image Analysis
复制标题
用于免疫固定电泳图像分析的深度协同学习
DOI：
10.1109/tmi.2021.3068404
复制
发表时间：
2021
影响因子：
10.6
通讯作者：
Du Liang
中科院分区：
文献类型：
--
作者：
Wei Xiao-Yong;Yang Zhen-Qun;Zhang Xu-Lu;Liao Ga;Sheng Ai-Lin;Zhou S. Kevin;Wu Yongkang;Du Liang
免疫固定电泳（IFE）分析对于多发性骨髓瘤的诊断非常重要，多发性骨髓瘤是美国排名前九的癌症杀手之一，但很少在深度学习的背景下进行研究。两个可能的原因是：1）IFE模式的识别依赖于波段的共置，形成二元关系，与深度学习擅长建模的一元关系（视觉特征到标签）不同； 2）深度分类模型对于IFE识别可能具有较高的准确度，但无法为其预测提供确凿的证据（共置模式所在），从而给技术人员验证结果带来困难。我们建议通过搭配学习来解决这些问题，其中构建了搭配张量以将二元关系转换为与传统深度网络兼容的一元关系，并提出了一种利用 Grad-CAM 显着性图进行证据回溯的无位置标签方法以实现精确定位。此外，我们提出了Coached Attention Gates，它可以调节学习的推理，使其更符合人类逻辑，从而支持证据回溯。实验结果表明，该方法在 IoU 方面比其基础模型 ResNet18 获得了 741.30% 的性能增益，并且优于流行的 DenseNet、CBAM 和 Inception-v3 等深度网络。
Immunofixation Electrophoresis (IFE) analysis is of great importance to the diagnosis of Multiple Myeloma, which is among the top-9 cancer killers in the United States, but has rarely been studied in the context of deep learning. Two possible reasons are: 1) the recognition of IFE patterns is dependent on the co-location of bands that forms a binary relation, different from the unary relation (visual features to label) that deep learning is good at modeling; 2) deep classification models may perform with high accuracy for IFE recognition but is not able to provide firm evidence (where the co-location patterns are) for its predictions, rendering difficulty for technicians to validate the results. We propose to address these issues with collocative learning, in which a collocative tensor has been constructed to transform the binary relations into unary relations that are compatible with conventional deep networks, and a location-label-free method that utilizes the Grad-CAM saliency map for evidence backtracking has been proposed for accurate localization. In addition, we have proposed Coached Attention Gates that can regulate the inference of the learning to be more consistent with human logic and thus support the evidence backtracking. The experimental results show that the proposed method has obtained a performance gain over its base model ResNet18 by 741.30% in IoU and also outperformed popular deep networks of DenseNet, CBAM, and Inception-v3.