arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.00340cs.AI
收藏

为可解释的人工智能生成放射科医生质量的报告

Producing radiologist-quality reports for interpretable artificial intelligence

The University of Adelaide(阿德莱德大学);Queensland University of Technology(昆士兰科技大学)

William Gale, Luke Oakden-Rayner, Gustavo Carneiro, Andrew P Bradley, Lyle J Palmer

摘要:

目前解释深度学习系统在医疗任务中的决策的方法主要集中在可视化促成每个决策的元素。我们认为,这些方法不足以“打开医疗决策系统的黑匣子”,因为它们缺少一个几个世纪以来一直被用作医生之间标准沟通工具的关键组成部分:语言。我们提出了一种与模型无关的可解释性方法,该方法涉及训练一个简单的递归神经网络模型来生成描述性句子,以澄清深度学习分类器的决策。我们测试我们的方法上的任务,检测髋部骨折,从骨盆X射线。这个过程需要最少的额外标记,尽管产生的文本包含原始深度学习分类模型没有专门训练来检测的元素。实验结果表明:1)我们的方法产生的句子始终包含所需的信息,2)与当前创建显着图的工具相比,医生更喜欢生成的句子,3)可视化和生成的文本的组合优于单独使用。

英文摘要:

Current approaches to explaining the decisions of deep learning systems for medical tasks have focused on visualising the elements that have contributed to each decision. We argue that such approaches are not enough to "open the black box" of medical decision making systems because they are missing a key component that has been used as a standard communication tool between doctors for centuries: language. We propose a model-agnostic interpretability method that involves training a simple recurrent neural network model to produce descriptive sentences to clarify the decision of deep learning classifiers. We test our method on the task of detecting hip fractures from frontal pelvic x-rays. This process requires minimal additional labelling despite producing text containing elements that the original deep learning classification model was not specifically trained to detect. The experimental results show that: 1) the sentences produced by our method consistently contain the desired information, 2) the generated sentences are preferred by doctors compared to current tools that create saliency maps, and 3) the combination of visualisations and generated text is better than either alone.

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。

↑