Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification.
Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification.
复制标题
知识引导的多视图深度课程学习用于肘部骨折分类。
DOI：
10.1007/978-3-030-87589-3_57
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Wu,Shandong
中科院分区：
文献类型：
--
作者：
Luo,Jun;Kitamura,Gene;Arefan,Dooman;Doganay,Emine;Panigrahy,Ashok;Wu,Shandong
肘关节骨折的诊断通常需要患者同时拍摄肘关节X线片的正面和侧面视图。在本文中，我们提出了一种用于肘部骨折亚型分类任务的多视图深度学习方法。我们的策略利用迁移学习，首先训练两个单视图模型，一个用于正面视图，另一个用于侧面视图，然后将权重转移到所提出的多视图网络架构中的相应层。同时，通过课程学习框架将定量医学知识整合到训练过程中，这使得模型能够首先从“较容易”的样本学习，然后过渡到“较难”的样本，以达到更好的性能。此外，我们的多视图网络既可以在双视图设置中工作，也可以使用单个视图作为输入。我们通过对肘部骨折的分类任务进行广泛的实验来评估我们的方法，数据集为1，964张图像。结果表明，我们的方法优于两个相关的方法在多个设置的骨折研究，我们的技术是能够提高性能的比较方法。该代码可在 https://github.com/ljaiverson/multiview-curriculum .
Elbow fracture diagnosis often requires patients to take both frontal and lateral views of elbow X-ray radiographs. In this paper, we propose a multiview deep learning method for an elbow fracture subtype classification task. Our strategy leverages transfer learning by first training two single-view models, one for frontal view and the other for lateral view, and then transferring the weights to the corresponding layers in the proposed multiview network architecture. Meanwhile, quantitative medical knowledge was integrated into the training process through a curriculum learning framework, which enables the model to first learn from “easier” samples and then transition to “harder” samples to reach better performance. In addition, our multiview network can work both in a dual-view setting and with a single view as input. We evaluate our method through extensive experiments on a classification task of elbow fracture with a dataset of 1,964 images. Results show that our method outperforms two related methods on bone fracture study in multiple settings, and our technique is able to boost the performance of the compared methods. The code is available at https://github.com/ljaiverson/multiview-curriculum .