Multimodal recurrence scoring system for prediction of clear cell renal cell carcinoma outcome: a discovery and validation study

作者：Chengpeng Gui, Yuhang Chen, Hongwei Zhao, Jiazheng Cao, Tianjie Liu, Shengwei Xiong, Yanfei Yu, Bing Liao, Yun Cao, Jiaying Li, Kangbo Huang, Hui Han, Zhiling Zhang, Wenfang Chen, Ze-Ying Jiang, Ye Gao, Guan-Peng Han, Qi Tang, Kui Ouyang, Guimei Qu, Jitao Wu, Jianping Guo, Caixia Li, Pei-Xing Li, Zhiping Liu, Jer‐Tsong Hsieh, Muyan Cai, Xuesong Li, Jinhuan Wei, Junhang Luo · 发表于：The Lancet Digital Health · 年份：2023 · DOI：10.1016/s2589-7500(23)00095-x · 被引用次数：47 · 研究领域：Renal cell carcinoma treatment、Ferroptosis and cancer prognosis、AI in cancer detection

BACKGROUND: Improved markers for predicting recurrence are needed to stratify patients with localised (stage I-III) renal cell carcinoma after surgery for selection of adjuvant therapy. We developed a novel assay integrating three modalities-clinical, genomic, and histopathological-to improve the predictive accuracy for localised renal cell carcinoma recurrence. METHODS: In this retrospective analysis and validation study, we developed a histopathological whole-slide image (WSI)-based score using deep learning allied to digital scanning of conventional haematoxylin and eosin-stained tumour tissue sections, to predict tumour recurrence in a development dataset of 651 patients with distinctly good or poor disease outcome. The six single nucleotide polymorphism-based score, which was detected in paraffin-embedded tumour tissue samples, and the Leibovich score, which was established using clinicopathological risk factors, were combined with the WSI-based score to construct a multimodal recurrence score in the training dataset of 1125 patients. The multimodal recurrence score was validated in 1625 patients from the independent validation dataset and 418 patients from The Cancer Genome Atlas set. The primary outcome measured was the recurrence-free interval (RFI). FINDINGS: The multimodal recurrence score had significantly higher predictive accuracy than the three single-modal scores and clinicopathological risk factors, and it precisely predicted the RFI of patients in the trainin...