发表机构
Johns Hopkins University; Harvard Medical School; Massachusetts General Hospital; University of California, San Francisco; University of Zurich; Istanbul Medipol University; Johns Hopkins Medicine（约翰霍普金斯大学; 哈佛医学院; 马萨诸塞总医院; 加利福尼亚大学旧金山分校; 苏黎世大学; 伊斯坦布尔梅迪波尔大学; 约翰霍普金斯医学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RT-Super利用纵向影像、多期影像和放射学报告替代肿瘤掩膜，通过教师-学生网络和一致性损失训练，实现对食管、子宫和脾脏肿瘤的高质量分割，超越公共模型。
AI 中文摘要
多肿瘤分割对于早期癌症检测至关重要，并能使放射科医生可视化、验证和理解人工智能的预测。然而，肿瘤分割掩膜昂贵且耗时，且在公共数据中许多肿瘤类型缺乏此类掩膜。相反，医院拥有大量易于获取的数据可用于指导分割：放射学报告、纵向影像和多期影像。我们利用这些易于获取的数据来替代肿瘤掩膜，用于训练人工智能进行肿瘤分割。为此，我们提出了一种新架构RT-Super。它包含一个教师网络，该网络分析患者的纵向影像和报告以生成高质量的肿瘤掩膜。这些掩膜用于训练一个学生网络，该网络仅查看单张影像且无报告。在推理时，当纵向影像和报告不可用时，我们使用学生网络。RT-Super采用了一种新的CNN-Transformer架构和利用纵向影像间肿瘤位置一致性的新颖一致性损失。我们训练RT-Super分割食管、子宫和脾脏肿瘤，这些肿瘤几乎没有或没有公共掩膜。即使没有训练掩膜，RT-Super也能分割这些肿瘤并超越公共人工智能模型。总体而言，我们证明了从纵向影像、多期影像和报告中学习可以克服掩膜稀缺问题，并推进多癌症检测与分割。代码：此https URL
英文摘要
Multi-tumor segmentation is important for early cancer detection and allows radiologists to visualize, verify, and understand AI predictions. However, tumor segmentation masks are expensive, time-consuming, and unavailable for many tumor types in public data. Instead, hospitals have vast, readily available data that can guide segmentation: radiology reports, longitudinal images, and multi-phase images. We use this readily available data to substitute for tumor masks in training AI for tumor segmentation. To this end, we propose a new architecture, RT-Super. It has a teacher network, which analyzes the patient's longitudinal images and reports to create high-quality tumor masks. These masks train a student network, which sees a single image and no report. At inference, when longitudinal images and reports are unavailable, we use the student. RT-Super uses a new CNN-Transformer architecture and novel Consistency Losses that exploit tumor location consistency across longitudinal images. We train RT-Super to segment esophagus, uterus and spleen tumors, which have few or no public masks. Even without training masks, RT-Super can segment these tumors and surpass public AI models. Overall, we demonstrate that learning from longitudinal images, multi-phase images, and reports can overcome mask scarcity and advance multi-cancer detection and segmentation. Code: https://github.com/MrGiovanni/RT-Super
CommentsMICCAI 2026
