消化道癌新辅助治疗疗效评估影像组学研究进展

Advances in radiomics research on efficacy evaluation of neoadjuvant therapy for gastrointestinal cancer

影像学检查是消化道癌新辅助治疗疗效预测和评估的重要手段,影像组学将人工智能与医学影像大数据结合,提取并整合肿瘤影像图像从基础形态到纹理特征、再到复杂高维特征中蕴含的海量信息,通过降维和建模构建辅助临床评估的决策模型,已在消化道癌新辅助治疗疗效预测和评价方面展现出较大潜力,大量研究应用不同方法构建模型,获得了较好的评效效果。受到模型间异质性和复杂性因素的影响,以及缺乏临床应用所需的高证据级别研究,目前尚未实现明确的临床转化。影像组学在消化道癌新辅助治疗疗效评估的应用亟需设计严谨的多中心、大样本临床研究及前瞻性验证,为这一创新方法在临床的常规应用提供有效证据。

Radiologic metrics are reliable biomarkers for evaluating the efficacy of neoadjuvant therapy in the context of digestive system cancer.Radiomics is an emerging field that combines artificial intelligence with medical images.Radiomics models could be built to support clinical decisionmaking by extracting and combining the vast amount of information embedded in the images,such as morphologic features,texture features,and high-dimensional features of the region of interest.It has great potential for evaluating responses precisely. Some encouraging radionics researchresults have been published. Affected by inter- modelheterogeneity and complexity factors, as well as the lack ofhigh-level evidence studies required for clinical application,clear clinical translation has not yet been achieved. Theapplication of radiomics in evaluating the efficacy ofneoadjuvant therapy for gastrointestinal cancer needsrigorously designed multi- center,large- sample clinicalstudies and prospective verification to provide effectiveevidence for the routine clinical application of this innovativemethod.