arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.05424cs.CVcs.AI
收藏

Doctor Imitator：通过模仿评分方法进行基于手部X光片的骨龄评估

Doctor Imitator: Hand-Radiography-based Bone Age Assessment by Imitating Scoring Methods

Zhejiang University（浙江大学）；University of Notre Dame（圣母大学）

Jintai Chen, Bohan Yu, Biwen Lei, Ruiwei Feng, Danny Z. Chen, Jian Wu

备注：
Original Title: "Doctor Imitator: A Graph-based Bone Age Assessment Framework Using Hand Radiographs" @inproceedings{chen2020doctor, title={Doctor imitator: A graph-based bone age assessment framework using hand radiographs}, author={Chen, Jintai and Yu, Bohan and Lei, Biwen and Feng, Ruiwei and Chen, Danny Z and Wu, Jian}, booktitle={MICCAI}, year={2020} }
发表信息：
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI-2020)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Doctor Imitator图深度学习框架，通过模仿Tanner-Whitehouse等评分方法的诊断流程，在仅用骨龄标签监督下实现高性能、轻量化且可解释的手部X光骨龄评估。

摘要：

由于骨龄评估流程复杂，其在临床实践中具有挑战性。当前的自动骨龄评估方法在设计时很少考虑诊断逻辑，因此可能产生某些不可解释的隐藏状态和输出。因此，医生发现很难与此类模型顺畅协作，因为难以核查模型预测的正确性。在本研究中，我们提出了一种新的基于图的深度学习框架，用于利用手部X光片进行骨龄评估，称为Doctor Imitator（DI）。DI的架构旨在学习医生使用评分方法（例如Tanner-Whitehouse方法）进行骨龄评估的诊断逻辑。具体而言，DI的卷积捕获手部X光片上解剖感兴趣区域（ROI）的局部特征，并通过我们提出的基于解剖的分组卷积预测ROI评分，将其相加以进行骨龄预测。此外，我们开发了一种新颖的双图注意力模块，用于计算针对ROI特征的患者特定注意力以及针对ROI评分的上下文注意力。据我们所知，DI是首个在没有完全监督手部X光片的情况下遵循评分方法的自动骨龄评估框架。在仅有骨龄监督的手部X光片上进行的实验验证了DI能够以稀疏参数实现优异性能，并提供更强的可解释性。

英文摘要：

Bone age assessment is challenging in clinical practice due to the complicated bone age assessment process. Current automatic bone age assessment methods were designed with rare consideration of the diagnostic logistics and thus may yield certain uninterpretable hidden states and outputs. Consequently, doctors can find it hard to cooperate with such models harmoniously because it is difficult to check the correctness of the model predictions. In this work, we propose a new graph-based deep learning framework for bone age assessment with hand radiographs, called Doctor Imitator (DI). The architecture of DI is designed to learn the diagnostic logistics of doctors using the scoring methods (e.g., the Tanner-Whitehouse method) for bone age assessment. Specifically, the convolutions of DI capture the local features of the anatomical regions of interest (ROIs) on hand radiographs and predict the ROI scores by our proposed Anatomy-based Group Convolution, summing up for bone age prediction. Besides, we develop a novel Dual Graph-based Attention module to compute patient-specific attention for ROI features and context attention for ROI scores. As far as we know, DI is the first automatic bone age assessment framework following the scoring methods without fully supervised hand radiographs. Experiments on hand radiographs with only bone age supervision verify that DI can achieve excellent performance with sparse parameters and provide more interpretability.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑