构建首个喉癌分期标准数据集，验证深度学习模型性能。
Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset
- 用弱监督方法统一提取6个数据源的喉部CT影像，形成标准化数据集。
- 3D CNN在早期与晚期分期任务中准确率达85.4%，但T4检测敏感性不足41.2%。
- 提供可解释性工具，助力临床医生理解AI决策逻辑，适合医学AI研究者使用。
喉癌影像研究缺乏标准化公开数据集，制约深度学习模型的可复现开发。本文构建了LaryngealCT，整合来自癌症影像档案馆（TCIA）六个来源的1,029例计算机断层扫描（CT）数据，通过弱监督参数搜索框架提取统一的1 mm等距兴趣体积，经临床专家验证。评估六种3D深度学习架构（自定义3D CNN、ResNet18/50/101、DenseNet121和预训练MedicalNet-ResNet50）在（i）早期（Tis,T1,T2） vs. 晚期（T3,T4）以及（ii）T4 vs. 非T4分类任务中的表现。独立测试集上，3D CNN在整体及各类别指标上表现最优（准确率0.854，F1-macro 0.841）。T4分类任务中，多数模型的AU-ROC超过0.82，但T4检测敏感性均不超过0.412；其中ResNet101展现出最优校准后的召回率（0.706）。基于GradCAMpp结合甲状腺软骨叠加的可解释性分析显示，模型在软骨周围激活区域具有解剖学合理性，但空间重叠度较低。通过开源数据、预训练模型与集成可解释性工具，LaryngealCT为人工智能驱动的喉癌研究提供了可复现基础，支持未来临床决策。
原文摘要 · Abstract (English)
Laryngeal cancer imaging research lacks standardised public datasets to enable reproducible deep learning (DL) model development. We present LaryngealCT, a curated benchmark of 1,029 computed tomography (CT) scans aggregated from six collections from The Cancer Imaging Archive (TCIA). Uniform 1 mm isotropic volumes of interest encompassing the larynx were extracted using a weakly supervised parameter search framework validated by clinical experts. Six 3D DL architectures (custom 3D CNN, ResNet18,50,101, DenseNet121 and MedicalNet-pretrained ResNet50) were benchmarked on (i) early (Tis,T1,T2) vs. advanced (T3,T4) and (ii) T4 vs. non-T4 classification tasks. On the independent test set, the 3D CNN achieved the strongest overall performance across global and per-class metrics (Accuracy 0.854, F1-macro 0.841) in early vs. advanced classification. In the T4 task, AU-ROC values exceeded 0.82 for most models, but sensitivity for T4 disease remained limited (less than or equal to 0.412), with ResNet101 showing the most promising calibrated T4 recall (0.706. Model explainability assessed using GradCAMpp with thyroid cartilage overlays for T4 classification task revealed anatomically plausible peri-cartilage activations, although spatial overlap was modest. Through open-source data, pretrained models, and integrated explainability tools, LaryngealCT offers a reproducible foundation for AI-driven research to support future clinical decision-making in laryngeal oncology.
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。