Deep Learning on Hyperspectral Pathology for Recurrence Prediction in Clear Cell Renal Cell Carcinoma.

IF 2.3

Journal of biophotonics Pub Date : 2026-03-01 Epub Date: 2025-12-14 DOI:10.1002/jbio.202500546

Xulei Wang, Wenshi Tian, Yihan Zhao, Yihui He, Zhengyang Zhang, Xiaobo Shao, Yunchao Wang, Jianning Wang

{"title":"Deep Learning on Hyperspectral Pathology for Recurrence Prediction in Clear Cell Renal Cell Carcinoma.","authors":"Xulei Wang, Wenshi Tian, Yihan Zhao, Yihui He, Zhengyang Zhang, Xiaobo Shao, Yunchao Wang, Jianning Wang","doi":"10.1002/jbio.202500546","DOIUrl":null,"url":null,"abstract":"Background: Clear cell renal cell carcinoma (ccRCC), the most common aggressive renal cancer subtype, shows marked heterogeneity that hinders recurrence prediction.Objective: To evaluate hyperspectral pathology imaging (HSI) with deep learning for individualized recurrence risk prediction in ccRCC.Methods: Slides from 48 patients with ccRCC were imaged using a 400-1000 nm hyperspectral microscope. Spectral data were preprocessed, and a dual-branch network (HSI-FusionNet) extracted spatial and spectral features via 2D and 1D convolution, followed by gated fusion and multiple instance learning (MIL) for patient-level prediction.Results: HSI-FusionNet achieved strong test performance (area under the receiver operating characteristic curve [AUC] = 0.912; sensitivity = 0.881; specificity = 0.846), outperforming ResNet-50, 1D-Convolutional Neural Network (CNN), and a 1D-Transformer. Recurrence-related spectral bands (530-580 and 830-900 nm) reflected hemoglobin and lipid-collagen differences.Conclusion: HSI with deep learning accurately identifies recurrent ccRCC and reveals molecular-metabolic signatures, supporting precision postoperative risk stratification.","PeriodicalId":94068,"journal":{"name":"Journal of biophotonics","volume":" ","pages":"e202500546"},"PeriodicalIF":2.3000,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of biophotonics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1002/jbio.202500546","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/12/14 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Clear cell renal cell carcinoma (ccRCC), the most common aggressive renal cancer subtype, shows marked heterogeneity that hinders recurrence prediction.

Objective: To evaluate hyperspectral pathology imaging (HSI) with deep learning for individualized recurrence risk prediction in ccRCC.

Methods: Slides from 48 patients with ccRCC were imaged using a 400-1000 nm hyperspectral microscope. Spectral data were preprocessed, and a dual-branch network (HSI-FusionNet) extracted spatial and spectral features via 2D and 1D convolution, followed by gated fusion and multiple instance learning (MIL) for patient-level prediction.

Results: HSI-FusionNet achieved strong test performance (area under the receiver operating characteristic curve [AUC] = 0.912; sensitivity = 0.881; specificity = 0.846), outperforming ResNet-50, 1D-Convolutional Neural Network (CNN), and a 1D-Transformer. Recurrence-related spectral bands (530-580 and 830-900 nm) reflected hemoglobin and lipid-collagen differences.

Conclusion: HSI with deep learning accurately identifies recurrent ccRCC and reveals molecular-metabolic signatures, supporting precision postoperative risk stratification.

查看原文本刊更多论文

基于高光谱病理学的深度学习预测透明细胞肾细胞癌复发。

背景：透明细胞肾细胞癌（Clear cell renal cell carcinoma, ccRCC）是最常见的侵袭性肾癌亚型，具有明显的异质性，难以预测其复发。目的：探讨深度学习高光谱病理成像（HSI）在ccRCC个体化复发风险预测中的应用价值。方法：采用400-1000 nm高光谱显微镜对48例ccRCC患者的载玻片进行成像。光谱数据进行预处理，双分支网络（HSI-FusionNet）通过二维和一维卷积提取空间和光谱特征，然后进行门控融合和多实例学习（MIL）进行患者级预测。结果：hsii - fusionnet获得了较强的测试性能（受试者工作特征曲线下面积[AUC] = 0.912，灵敏度= 0.881，特异性= 0.846），优于ResNet-50、1d -卷积神经网络（CNN）和1D-Transformer。复发相关光谱波段（530-580 nm和830-900 nm）反映了血红蛋白和脂质-胶原蛋白的差异。结论：基于深度学习的HSI能够准确识别复发性ccRCC，揭示分子代谢特征，支持精准的术后风险分层。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of biophotonics

自引率

0.00%

发文量