提出多维度可解释医学分类框架，提升模型透明度与实用性
Towards Multi-dimensional Explanation Alignment for Medical Classification
- 融合神经符号推理、概念语义与显著图的多角度可解释方法
- 在四个基准数据集上实现高准确率与强可解释性，优于现有方法
- 端到端概念标注自动完成，减少人工标注成本，适合临床应用
医学图像分析中的可解释性不足带来重大伦理与法律风险。现有可解释方法存在对特定模型依赖、难以理解与可视化、效率低等问题。为此，我们提出新型框架Med-MICN（Medical Multi-dimensional Interpretable Concept Network），从神经符号推理、概念语义和显著图三个维度实现可解释性对齐，优于当前方法。该框架具备高预测准确率、多维可解释性，并通过端到端概念标注流程实现自动化，大幅降低新数据集上的人工训练成本。我们在四个基准数据集上验证其有效性，结果表明Med-MICN在性能与可解释性方面均表现卓越。
原文摘要 · Abstract (English)
The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understanding and visualization, as well as issues related to efficiency. To address these limitations, we propose a novel framework called Med-MICN (Medical Multi-dimensional Interpretable Concept Network). Med-MICN provides interpretability alignment for various angles, including neural symbolic reasoning, concept semantics, and saliency maps, which are superior to current interpretable methods. Its advantages include high prediction accuracy, interpretability across multiple dimensions, and automation through an end-to-end concept labeling process that reduces the need for extensive human training effort when working with new datasets. To demonstrate the effectiveness and interpretability of Med-MICN, we apply it to four benchmark datasets and compare it with baselines. The results clearly demonstrate the superior performance and interpretability of our Med-MICN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。