Abstract
Lung cancer remains the leading cause of cancer mortality, with CT imaging central to screening, prognosis, and treatment. Manual segmentation is variable and time-intensive, while deep learning (DL) offers automation but faces barriers to clinical adoption. Guided by the Knowledge-to-Action framework, this study develops a clinician-in-the-loop DL pipeline to enhance reproducibility, prognostic accuracy, and clinical trust. Multi-center CT data from 999 patients across 12 public datasets were analyzed using five DL models (3D Attention U-Net, ResUNet, VNet, ReconNet, SAM-Med3D), benchmarked against expert contours on whole and click-point cropped images. Segmentation reproducibility was assessed using 497 PySERA-extracted radiomic features via Spearman correlation, ICC, Wilcoxon tests, and MANOVA, while prognostic modeling compared supervised (SL) and semi-supervised learning (SSL) across 38 dimensionality reduction strategies and 24 classifiers. Six physicians qualitatively evaluated masks across seven domains, including clinical meaningfulness, boundary quality, prognostic value, trust, and workflow integration. VNet achieved the best performance (Dice = 0.83, IoU = 0.71), radiomic stability (mean correlation = 0.76, ICC = 0.65), and predictive accuracy under SSL (accuracy = 0.88, F1 = 0.83). SSL consistently outperformed SL across models. Radiologists favored VNet for peritumoral representation and smoother boundaries, preferring AI-generated initial masks for refinement rather than replacement. These results demonstrate that integrating VNet with SSL yields accurate, reproducible, and clinically trusted CT-based lung cancer prognosis, highlighting a feasible path toward physician-centered AI translation.
Abstract (translated)
肺癌仍然是癌症死亡的主要原因，CT成像在筛查、预后和治疗中处于核心地位。手动分割过程存在可变性和耗时的问题，而深度学习（DL）虽然提供了自动化解决方案，但面临着临床应用的障碍。本研究遵循知识到行动框架，开发了一种由医生参与的深度学习管道，以提高再现性、预测准确性以及临床信任度。 通过使用来自12个公共数据集中的999名患者的多中心CT数据，五种深度学习模型（3D注意力U-Net、ResUNet、VNet、ReconNet和SAM-Med3D）在完整图像与点击点裁剪的图像上进行对比测试，以专家轮廓为基准。通过Spearman相关性、ICC（组内一致性系数）、Wilcoxon检验及MANOVA对分割再现性的497个PySERA提取放射学特征进行了评估；同时通过38种降维策略和24种分类器比较了监督学习（SL）与半监督学习（SSL）的预后建模。六位医生从七个领域，包括临床意义、边界质量、预测价值、信任度及工作流程整合对掩码进行定性评估。 VNet在性能上表现出色（Dice系数=0.83，IoU=0.71），放射学稳定性表现优异（平均相关性=0.76，ICC=0.65）并在SSL下具有更高的预测准确度（准确性=0.88，F1值=0.83）。在各种模型上，SSL始终优于SL。放射科医生更倾向于使用VNet进行肿瘤周围组织的表示及平滑边界，并且他们偏好AI生成的初步掩码供后续细化而非替代现有操作。 这些结果表明，结合VNet与SSL可以为基于CT图像肺癌预后的准确、可重复性以及临床可信度提供一条可行路径。这强调了一种医生为中心的人工智能转化方法的有效应用。
URL
https://arxiv.org/abs/2510.17039
