皮肤镜概念瓶颈模型中的概念不一致：对Derm7pt数据集的粗糙集分析
Concept Inconsistency in Dermoscopic Concept Bottleneck Models: A Rough-Set Analysis of the Derm7pt Dataset
AI总结：
本文通过粗糙集理论分析Derm7pt数据集中的概念不一致问题，发现16.4%的概念配置存在冲突，导致理论准确率上限为92.1%，并通过过滤策略构建一致数据集并评估CBM模型性能。
摘要：
概念瓶颈模型（CBMs）通过临床基础的概念层进行预测，将可解释性绑定到概念-标签一致性。当数据集存在概念层面的不一致时，相同的概念配置映射到冲突的诊断标签会形成不可解决的瓶颈，限制可达到的准确率。本文将粗糙集理论应用于Derm7pt皮肤镜基准测试，并表征这种不一致的完整范围和临床结构。在由7个皮肤镜标准构成的7点黑色素瘤清单中，305个独特的概念配置中，50个（16.4%）存在不一致，涵盖306张图像（30.3%的数据集）。这导致理论准确率上限为92.1%，与CBM的底层架构或训练策略无关。此外，我们表征了冲突严重程度分布，识别了最负责边界模糊的临床特征，并评估了两种过滤策略对数据集组成和CBM可解释性的影响。对所有边界区域图像对称移除得到Derm7pt+，一个完全一致的基准子集，包含705张图像，具有完美的分类质量和无硬准确率上限。基于此过滤数据集，我们展示了在EfficientNet、DenseNet、ResNet和Wide ResNet家族中的19种底层架构上评估的硬CBM。在对称过滤下，EfficientNet-B5在测试集上实现了最佳的标签F1分数（0.85）和标签准确率（0.90），概念准确率为0.70。在不对称过滤下，EfficientNet-B7在所有四个指标上领先，达到标签F1分数0.82和概念准确率0.70。这些结果为在皮肤镜数据上评估概念一致的CBM奠定了可重复的基准。
英文摘要：
Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label consistency. When a dataset contains concept-level inconsistencies, identical concept profiles mapped to conflicting diagnosis labels create an unresolvable bottleneck that imposes a hard ceiling on achievable accuracy. In this paper, we apply rough set theory to the Derm7pt dermoscopy benchmark and characterize the full extent and clinical structure of this inconsistency. Among 305 unique concept profiles formed by the 7 dermoscopic criteria of the 7-point melanoma checklist, 50 (16.4%) are inconsistent, spanning 306 images (30.3% of the dataset). This yields a theoretical accuracy ceiling of 92.1%, independent of backbone architecture or training strategy for CBMs that exclusively operate with hard concepts. In addition, we characterize the conflict-severity distribution, identify the clinical features most responsible for boundary ambiguity, and evaluate two filtering strategies with quantified effects on dataset composition and CBM interpretability. Symmetric removal of all boundary-region images yields Derm7pt+, a fully consistent benchmark subset of 705 images with perfect quality of classification and no hard accuracy ceiling. Building on this filtered dataset, we present a hard CBM evaluated across 19 backbone architectures from the EfficientNet, DenseNet, ResNet, and Wide ResNet families. Under symmetric filtering, explored for completeness, EfficientNet-B5 achieves the best label F1 score (0.85) and label accuracy (0.90) on the held-out test set, with a concept accuracy of 0.70. Under asymmetric filtering, EfficientNet-B7 leads across all four metrics, reaching a label F1 score of 0.82 and concept accuracy of 0.70. These results establish reproducible baselines for concept-consistent CBM evaluation on dermoscopic data.
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。
