基于概念的肺结节CT图像恶性程度可解释评分
Concept-based Explainable Malignancy Scoring on Pulmonary Nodules in CT Images
- Peter the Great St.Petersburg Polytechnic University（彼得大帝圣彼得堡理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种基于广义加性模型和概念学习的可解释模型，用于肺结节CT图像恶性程度评分，通过检测临床属性并解释其贡献，在LIDC-IDRI数据集上验证了与临床一致的诊断结果和竞争性能。
AI中文摘要：
为了提高现代计算机辅助诊断（CAD）系统在评估肺结节恶性程度方面的透明度，提出了一种基于广义加性模型和概念学习的可解释模型。该模型在输出最终恶性程度回归评分的同时，检测一组临床显著属性，并学习肺结节属性与最终诊断决策之间的关联以及它们对决策的贡献。所提出的基于概念的学习框架提供了以不同概念（数值型和类别型）、其值及其对最终预测的贡献为形式的人类可读解释。使用LIDC-IDRI数据集的数值实验表明，所提出的模型通过显式探索内部关系获得的诊断结果与临床实践中观察到的类似模式一致。此外，所提出的模型在分类和结节属性评分性能上表现出竞争力，突显了其在肺结节诊断中有效决策的潜力。
英文摘要：
To increase the transparency of modern computer-aided diagnosis (CAD) systems for assessing the malignancy of lung nodules, an interpretable model based on applying the generalized additive models and the concept-based learning is proposed. The model detects a set of clinically significant attributes in addition to the final malignancy regression score and learns the association between the lung nodule attributes and a final diagnosis decision as well as their contributions into the decision. The proposed concept-based learning framework provides human-readable explanations in terms of different concepts (numerical and categorical), their values, and their contribution to the final prediction. Numerical experiments with the LIDC-IDRI dataset demonstrate that the diagnosis results obtained using the proposed model, which explicitly explores internal relationships, are in line with similar patterns observed in clinical practice. Additionally, the proposed model shows the competitive classification and the nodule attribute scoring performance, highlighting its potential for effective decision-making in the lung nodule diagnosis.
