Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency.
Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency.
复制标题
通过探索模型的可解释性、可解释性和数据模型依赖性，在放射肿瘤学中实现安全有效的机器学习临床应用。
DOI：
10.1088/1361-6560/ac678a
复制
发表时间：
2022-05-27
影响因子：
3.5
通讯作者：
Lee JA
中科院分区：
文献类型：
--
作者：
Barragán-Montero A;Bibal A;Dastarac MH;Draguet C;Valdés G;Nguyen D;Willems S;Vandewinckele L;Holmström M;Löfman F;Souris K;Sterpin E;Lee JA
近年来，人们对机器学习（ML）的兴趣大幅增长，部分原因是深度学习新技术、图像卷积神经网络、计算能力的提高以及大型数据集的更广泛可用性带来的性能飞跃。大多数医学领域都遵循这一流行趋势，特别是放射肿瘤学是最前沿的领域之一，在使用数字图像和完全计算机化的工作流程方面已经有了悠久的传统。ML模型由数据驱动，与许多统计或物理模型相比，它们可能非常庞大和复杂，具有无数的通用参数。这不可避免地提出了两个问题，即模型与提供它们的数据集之间的紧密依赖性，以及模型的可解释性，这与其复杂性成正比。用于训练模型的数据中的任何问题都将在稍后反映在其性能中。这一点，再加上ML模型的低可解释性，使得它们在临床工作流程中的实现特别困难。构建ML模型的风险评估和质量保证工具必须涉及两个要点：可解释性和数据模型依赖性。在联合介绍了放射肿瘤学和ML之后，本文回顾了将后者应用于前者工作流程时的主要风险和当前解决方案。详细介绍了与数据和模型相关的风险以及它们之间的相互作用。接下来，正式定义了可解释性、可解释性和数据模型依赖性的核心概念，并通过示例进行了说明。之后，广泛讨论了ML在放射肿瘤学工作流程中的关键应用以及供应商对ML临床实施的看法。
The interest for machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors’ perspectives for the clinical implementation of ML.
登录
查看更多内容
DOI：
10.1016/j.ejmp.2021.04.016
发表时间：
2021-03
期刊：
Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)
影响因子：
--
作者：
Barragán-Montero A;Javaid U;Valdés G;Nguyen D;Desbordes P;Macq B;Willems S;Vandewinckele L;Holmström M;Löfman F;Michiels S;Souris K;Sterpin E;Lee JA
通讯作者：
Lee JA
影响因子：
3.8
作者：
Barragan-Montero, Ana Maria;Dan Nguyen;Jiang, Steve
通讯作者：
Jiang, Steve
DOI：
10.1016/j.ejmp.2021.02.026
发表时间：
2021-03-10
影响因子：
3.4
作者：
Barragan-Montero, Ana M.;Thomas, Melissa;Sterpin, Edmond
通讯作者：
Sterpin, Edmond
影响因子：
5.5
作者：
Barrett, JF;Keat, N
通讯作者：
Keat, N
影响因子：
158.5
作者：
Bach, PB;Cramer, LD;Begg, CB
通讯作者：
Begg, CB