| 32 | 0 | 90 |
| 下载次数 | 被引频次 | 阅读次数 |
目的 建立并验证影像组学与病理学联合模型，预测局部晚期直肠癌患者新辅助放化疗后能否达到病理完全缓解。方法 收集303例接受新辅助放化疗后根治性手术的符合条件的局部晚期直肠癌患者，盆腔磁共振成像（MRI）预处理，收集苏木精-伊红染色活检切片的全切片图像用于注释和特征提取。构建一种以MRI为主、全切片图像（WSI）为辅的影像-病理融合预测模型（RPIP）。采用曲线下面积(AUC)、敏感性(Sen)、特异性(Sep)、阳性预测值(PPV)和阴性预测值(NPV)评价模型的性能。结果 训练队列AUC达到1（95%CI：1.000，1.000)、验证队列AUC达到0.926（95%CI：0.868， 0.983）。结论 基于影像组学与病理学的联合模型在预测病理完全缓解上具有良好的准确性。
Abstract：Objective To develop and validate a combined radiomics and pathomics model for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy in patients with locally advanced rectal cancer (LARC).Methods A total of 303 eligible LARC patients who underwent neoadjuvant chemoradiotherapy followed by radical surgery were included. Pre-treatment pelvic MRI and hematoxylin–eosin stained whole slide images (WSIs) of biopsy specimens were collected for annotation and feature extraction. We developed a fusion prediction model (Radiomics–Pathomics Integrated Prediction， RPIP) primarily based on MRI with supplementary WSI data. Model performance was evaluated using the area under the curve (AUC)， sensitivity， specificity， positive predictive value (PPV)， and negative predictive value (NPV).Results The model achieved an AUC of 1.000 [95% confidence interval (CI): 1.000， 1.000] in the training cohort and an AUC of 0.926 (95% CI: 0.868， 0.983) in the validation cohort. Conclusion The integrated model combining radiomics and pathomics demonstrates high accuracy in predicting pathological complete response.
[1] Rahma O E， Yothers G， Hong T S， et al. Use of total neoadjuvant therapy for locally advanced rectal cancer: initial results from the pembrolizumab arm of a phase 2 randomized clinical trial[J]. JAMA Oncol， 2021， 7(8): 1225-30. doi:10.1001/jamaoncol.2021.1683.
[2] George T J， Yothers G， Rahma O E， et al. Long-term results from NRG-GI002: a phase II clinical trial platform using total neoadjuvant therapy (TNT) in locally advanced rectal cancer (LARC)[J]. J Clin Oncol， 2023， 41(4＿suppl): 7. doi:10.1200/jco.2023.41.4＿suppl.7.
[3] Lu X， Qi R， Xu Y， et al. Tumor regression grade in locally advanced rectal cancer after neoadjuvant chemoradiotherapy: influencing factors and prognostic significance[J]. Int J Clin Exp Pathol， 2023， 16(6): 124-32.
[4] Curcean S， Curcean A， Martin D， et al. The role of predictive and prognostic MRI-based biomarkers in the era of total neoadjuvant treatment in rectal cancer[J]. Cancers， 2024， 16(17): 3111. doi:10.3390/cancers16173111.
[5] Feng L， Liu Z， Li C， et al. Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicentre observational study[J]. Lancet Digit Health， 2022， 4(1): e8-e17. doi:10.1016/S2589-7500(21)00215-6.
[6] Shao L， Liu Z， Feng L， et al. Multiparametric MRI and whole slide image-based pretreatment prediction of pathological response to neoadjuvant chemoradiotherapy in rectal cancer: a multicenter radiopathomic study[J]. Ann Surg Oncol， 2020， 27(11): 4296-306. doi:10.1245/s10434-020-08659-4.
[7] 朱宏庆， 张 涛， 顾康琛， 等. 基于临床和CT影像组学构建列线图在术前预测肾透明细胞癌分级中的价值[J]. 安徽医科大学学报， 2025， 60(6): 1127-33.doi:10.19405/j.cnki.issn1000-1492.2025.06.022.
[8] 谢 亮， 秦甲霖， 吴瑞雪， 等. 基于18F-FDG PET/CT影像组学联合临床特征鉴别淋巴瘤及淋巴炎性增生[J]. 安徽医科大学学报， 2025， 60(5): 954-63. doi:10.19405/j.cnki.issn1000-1492.2025.05.024.
[9] Boehm K M， Aherne E A， Ellenson L， et al. Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer[J]. Nat Cancer， 2022， 3(6): 723-33. doi:10.1038/s43018-022-00388-9.
[10] Boehm K M， El Nahhas O S M， Marra A， et al. Multimodal histopathologic models stratify hormone receptor-positive early breast cancer[J]. Nat Commun， 2025， 16(1): 2106. doi:10.1038/s41467-025-57283-x.
[11] Hollmann N， Müller S， Purucker L， et al. Accurate predictions on small data with a tabular foundation model[J]. Nature， 2025， 637(8045): 319-26. doi:10.1038/s41586-024-08328-6.
[12] Vaswani A， Shazeer N， Parmar N， et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. December 4 - 9， 2017， Long Beach， California， USA. ACM， 2017: 6000-10. doi:10.5555/3295222.3295349.
[13] van Griethuysen J J M， Fedorov A， Parmar C， et al. Computational radiomics system to decode the radiographic phenotype[J]. Cancer Res， 2017， 77(21): e104-7. doi:10.1158/0008-5472.CAN-17-0339.
[14] Chen R J， Ding T， Lu M Y， et al. Towards a general-purpose foundation model for computational pathology[J]. Nat Med， 2024， 30(3): 850-62. doi:10.1038/s41591-024-02857-3.
[15] Lundberg S M， Lee S I. A unified approach to interpreting model predictions[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. December 4 - 9， 2017， Long Beach， California， USA. ACM， 2017: 4768-77. doi:10.5555/3295222.3295230.
[16] Ranjbaran G， Recupero D R， Roy C K， et al. C-SHAP: a hybrid method for fast and efficient interpretability[J]. Appl Sci， 2025， 15(2): 672. doi:10.3390/app15020672.
[17] Chandra M A， Bedi S S. Survey on SVM and their application in imageclassification[J]. Int J Inf Technol， 2021， 13(5): 1-11. doi:10.1007/s41870-017-0080-1.
基本信息:
中图分类号:R735.37
引用信息:
[1]袁源,姜小明,王伟,等.基于影像与病理融合的局部晚期直肠癌新辅助同步放化疗疗效预测[J].安徽医科大学学报().
基金信息:
国家自然科学基金项目（编号：62571001、82302316）
2026-09-02
2026-09-02
2026-09-02