深度学习与亚区域放射组学的整合改善了局部晚期直肠癌患者对新辅助放化疗病理完全缓解的预测。

Integration of Deep Learning and Sub-regional Radiomics Improves the Prediction of Pathological Complete Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Patients.

作者信息

Wu Xixi, Wang Jinyong, Chen Chao, Cai Weimin, Guo Yu, Guo Kun, Chen Yongxian, Shi Yubo, Chen Junkai, Lin Xinran, Jiang Xuepei

机构信息

Department of Gastroenterology and Hepatology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China (X.W., C.C., W.C., Y.G., X.L., X.J.); Department of Pathology, Wenzhou Hospital of Integrated Traditional Chinese and Western Medicine Hospital, Wenzhou 325000, China (X.W., J.W., C.C., W.C., Y.G., K.G., Y.C., Y.S., J.C., X.L., X.J.).

Department of Infectious, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China (J.W., K.G.); Department of Pathology, Wenzhou Hospital of Integrated Traditional Chinese and Western Medicine Hospital, Wenzhou 325000, China (X.W., J.W., C.C., W.C., Y.G., K.G., Y.C., Y.S., J.C., X.L., X.J.).

出版信息

Acad Radiol. 2025 Jun;32(6):3384-3396. doi: 10.1016/j.acra.2024.12.049. Epub 2025 Jan 13.

DOI:10.1016/j.acra.2024.12.049

PMID:39809603

Abstract

RATIONALE AND OBJECTIVES

The precise prediction of response to neoadjuvant chemoradiotherapy is crucial for tailoring perioperative treatment in patients diagnosed with locally advanced rectal cancer (LARC). This retrospective study aims to develop and validate a model that integrates deep learning and sub-regional radiomics from MRI imaging to predict pathological complete response (pCR) in patients with LARC.

MATERIALS AND METHODS

We retrospectively enrolled 768 eligible participants from three independent hospitals who had received neoadjuvant chemoradiotherapy followed by radical surgery. Pretreatment pelvic MRI scans (T2-weighted), were collected for annotation and feature extraction. The K-means approach was used to segment the tumor into sub-regions. Radiomics and deep learning features were extracted by the Pyradiomics and 3D ResNet50, respectively. The predictive models were developed using the radiomics, sub-regional radiomics, and deep learning features with the machine learning algorithm in training cohort, and then validated in the external tests. The models' performance was assessed using various metrics, including the area under the curve (AUC), decision curve analysis, Kaplan-Meier survival analysis.

RESULTS

We constructed a combined model, named SRADL, which includes deep learning with sub-regional radiomics signatures, enabling precise prediction of pCR in LARC patients. SRADL had satisfactory performance for the prediction of pCR in the training cohort (AUC 0.925 [95% CI 0.894 to 0.948]), and in test 1 (AUC 0.915 [95% CI 0.869 to 0.949]) and in test 2 (AUC 0.902 [95% CI 0.846 to 0.945]). By employing optimal threshold of 0.486, the predicted pCR group had longer survival compared to predicted non-pCR group across three cohorts. SRADL also outperformed other single-modality prediction models.

CONCLUSION

The novel SRADL, which integrates deep learning with sub-regional signatures, showed high accuracy and robustness in predicting pCR to neoadjuvant chemoradiotherapy using pretreatment MRI images, making it a promising tool for the personalized management of LARC.

摘要

原理与目的

准确预测新辅助放化疗的反应对于为诊断为局部晚期直肠癌（LARC）的患者量身定制围手术期治疗至关重要。这项回顾性研究旨在开发并验证一种整合深度学习和MRI成像的亚区域放射组学的模型，以预测LARC患者的病理完全缓解（pCR）。

材料与方法

我们回顾性纳入了来自三家独立医院的768名符合条件的参与者，他们接受了新辅助放化疗后进行了根治性手术。收集治疗前盆腔MRI扫描（T2加权）用于标注和特征提取。采用K均值方法将肿瘤分割为亚区域。分别通过Pyradiomics和3D ResNet50提取放射组学和深度学习特征。在训练队列中使用放射组学、亚区域放射组学和深度学习特征以及机器学习算法开发预测模型，然后在外部测试中进行验证。使用包括曲线下面积（AUC）、决策曲线分析、Kaplan-Meier生存分析等各种指标评估模型性能。

结果

我们构建了一个名为SRADL的联合模型，该模型包括具有亚区域放射组学特征的深度学习，能够精确预测LARC患者的pCR。SRADL在训练队列（AUC 0.925 [95% CI 0.894至0.948]）、测试1（AUC 0.915 [95% CI 0.869至0.949]）和测试2（AUC 0.902 [95% CI 0.846至0.945]）中对pCR的预测具有令人满意的性能。通过采用0.486的最佳阈值，在三个队列中，预测的pCR组比预测的非pCR组具有更长的生存期。SRADL也优于其他单模态预测模型。