Department of Radiology, Hangzhou Xiaoshan Hospital of Traditional Chinese Medicine, Hangzhou, 311201, China.
Department of Radiology, Hangzhou Ninth People's Hospital (Hangzhou Red Cross Hospital Qiantang Campus), No.98 Yilong Road, Yipong Street, Qiantang New Area, Hangzhou, 310012, China.
Jpn J Radiol. 2024 Dec;42(12):1448-1457. doi: 10.1007/s11604-024-01630-3. Epub 2024 Jul 29.
This study aims to evaluate the application value of multi-parametric magnetic resonance imaging (MRI) radiomics in predicting the response of patients with locally advanced rectal cancer (LARC) to neoadjuvant chemoradiotherapy(nCRT), aiming to provide non-invasive biomarkers for clinical decision-making in personalized treatment.
A retrospective analysis was conducted on the clinical data and imaging records of patients with LARC who received nCRT and total mesorectal excision (TME) in two medical centers from 2017 to 2023. The patients were divided into a training group and a test group in a 7:3 ratio. Through radiomics analysis, radiomics features of tumor volume and mesorectal fat at baseline, before and after neoadjuvant therapy were extracted. Radiomics models based on single sequences (T2WI, DWI) and multi-sequence fusion were constructed, and the logistic regression classifier model was used to evaluate the prediction performance.
A total of 82 patients were included, with 30 in the good response group and 52 in the poor response group. Through the selection of radiomics features, radiomics models based on baseline MRI of tumor volume, mesorectal fat, and differences before and after treatment (Delta) were constructed. The area under the receiver operating characteristic curve (AUC) of the multi-parametric radiomics fusion model in the training and test groups was 0.852 and 0.848, respectively, showing high prediction performance and good calibration.
This study demonstrates that the multi-parametric MRI radiomics model can effectively predict the response of patients with locally advanced rectal cancer to neoadjuvant chemoradiotherapy. Especially, the fusion model provides high accuracy and good calibration. This result is conducive to the formulation of personalized treatment plans and optimization of treatment strategies.
本研究旨在评估多参数磁共振成像（MRI）放射组学在预测局部晚期直肠癌（LARC）患者对新辅助放化疗（nCRT）反应中的应用价值，旨在为个性化治疗中的临床决策提供非侵入性生物标志物。
回顾性分析了 2017 年至 2023 年在两家医疗中心接受 nCRT 和全直肠系膜切除术（TME）的 LARC 患者的临床资料和影像学记录。患者按 7:3 的比例分为训练组和测试组。通过放射组学分析，提取基线、新辅助治疗前后肿瘤体积和直肠系膜脂肪的放射组学特征。构建基于单序列（T2WI、DWI）和多序列融合的放射组学模型，并使用逻辑回归分类器模型评估预测性能。
共纳入 82 例患者，其中 30 例为缓解良好组，52 例为缓解不良组。通过放射组学特征选择，构建了基于肿瘤体积、直肠系膜脂肪基线 MRI 及治疗前后差异（Delta）的放射组学模型。训练组和测试组多参数放射组学融合模型的受试者工作特征曲线下面积（AUC）分别为 0.852 和 0.848，具有较高的预测性能和良好的校准度。
本研究表明，多参数 MRI 放射组学模型可有效预测局部晚期直肠癌患者对新辅助放化疗的反应，尤其是融合模型具有较高的准确性和良好的校准度。这一结果有助于制定个体化治疗计划和优化治疗策略。
