Texture analysis of apparent diffusion coefficient maps: can it identify nonresponse to neoadjuvant chemotherapy for additional radiation therapy in rectal cancer patients?

IF 3.8 3区医学 Q2 GASTROENTEROLOGY & HEPATOLOGY

Gastroenterology Report Pub Date : 2024-04-22 DOI:10.1093/gastro/goae035

Qianyu Wu, Yongju Yi, Bingjia Lai, Jiao Li, Yanbang Lian, Junhong Chen, Yue Wu, Xinhua Wang, Wuteng Cao

{"title":"Texture analysis of apparent diffusion coefficient maps: can it identify nonresponse to neoadjuvant chemotherapy for additional radiation therapy in rectal cancer patients?","authors":"Qianyu Wu, Yongju Yi, Bingjia Lai, Jiao Li, Yanbang Lian, Junhong Chen, Yue Wu, Xinhua Wang, Wuteng Cao","doi":"10.1093/gastro/goae035","DOIUrl":null,"url":null,"abstract":"Background Neoadjuvant chemotherapy (NCT) alone can achieve comparable treatment outcomes to chemoradiotherapy in locally advanced rectal cancer (LARC) patients. This study aimed to investigate the value of texture analysis (TA) in apparent diffusion coefficient (ADC) maps for identifying non-responders to NCT. Methods This retrospective study included patients with LARC after NCT, and they were categorized into nonresponse group (pTRG 3) and response group (pTRG 0–2) based on pathological tumor regression grade (pTRG). Predictive texture features were extracted from pre- and post-treatment ADC maps to construct a TA model using RandomForest. The ADC model was developed by manually measuring pre- and post-treatment ADC values and calculating their changes. Simultaneously, subjective evaluations based on magnetic resonance imaging assessment of TRG were performed by two experienced radiologists. Model performance was compared using the area under the curve (AUC) and DeLong test. Results A total of 299 patients from two centers were divided into three cohorts: the primary cohort (center A; n = 194, with 36 non-responders and 158 responders), the internal validation cohort (center A; n = 49, with 9 non-responders) and external validation cohort (center B; n = 56, with 33 non-responders). The TA model was constructed by post_mean, mean_change, post_skewness, post_entropy, and entropy_change, which outperformed both the ADC model and subjective evaluations with an impressive AUC of 0.997 (95% confidence interval [CI], 0.975–1.000) in the primary cohort. Robust performances were observed in internal and external validation cohorts, with AUCs of 0.919 (95% CI, 0.805–0.978) and 0.938 (95% CI, 0.840–0.985), respectively. Conclusions The TA model has the potential to serve as an imaging biomarker for identifying nonresponse to NCT in LARC patients, providing a valuable reference for these patients considering additional radiation therapy.","PeriodicalId":54275,"journal":{"name":"Gastroenterology Report","volume":"34 1","pages":""},"PeriodicalIF":3.8000,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gastroenterology Report","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/gastro/goae035","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background Neoadjuvant chemotherapy (NCT) alone can achieve comparable treatment outcomes to chemoradiotherapy in locally advanced rectal cancer (LARC) patients. This study aimed to investigate the value of texture analysis (TA) in apparent diffusion coefficient (ADC) maps for identifying non-responders to NCT. Methods This retrospective study included patients with LARC after NCT, and they were categorized into nonresponse group (pTRG 3) and response group (pTRG 0–2) based on pathological tumor regression grade (pTRG). Predictive texture features were extracted from pre- and post-treatment ADC maps to construct a TA model using RandomForest. The ADC model was developed by manually measuring pre- and post-treatment ADC values and calculating their changes. Simultaneously, subjective evaluations based on magnetic resonance imaging assessment of TRG were performed by two experienced radiologists. Model performance was compared using the area under the curve (AUC) and DeLong test. Results A total of 299 patients from two centers were divided into three cohorts: the primary cohort (center A; n = 194, with 36 non-responders and 158 responders), the internal validation cohort (center A; n = 49, with 9 non-responders) and external validation cohort (center B; n = 56, with 33 non-responders). The TA model was constructed by post_mean, mean_change, post_skewness, post_entropy, and entropy_change, which outperformed both the ADC model and subjective evaluations with an impressive AUC of 0.997 (95% confidence interval [CI], 0.975–1.000) in the primary cohort. Robust performances were observed in internal and external validation cohorts, with AUCs of 0.919 (95% CI, 0.805–0.978) and 0.938 (95% CI, 0.840–0.985), respectively. Conclusions The TA model has the potential to serve as an imaging biomarker for identifying nonresponse to NCT in LARC patients, providing a valuable reference for these patients considering additional radiation therapy.

查看原文本刊更多论文

表观扩散系数图的纹理分析：它能识别直肠癌患者对新辅助化疗的非响应性，从而进行额外放疗吗？

背景在局部晚期直肠癌（LARC）患者中，单用新辅助化疗（NCT）可获得与化疗放疗相当的治疗效果。本研究旨在探讨表观扩散系数（ADC）图中的纹理分析（TA）在识别 NCT 无应答者方面的价值。方法该回顾性研究纳入了经 NCT 治疗的 LARC 患者，根据病理肿瘤回归分级（pTRG）将其分为无反应组（pTRG 3）和反应组（pTRG 0-2）。从治疗前和治疗后的 ADC 图中提取预测纹理特征，使用 RandomForest 构建 TA 模型。ADC 模型是通过手动测量治疗前和治疗后的 ADC 值并计算其变化而建立的。同时，由两名经验丰富的放射科医生根据磁共振成像对 TRG 进行主观评估。使用曲线下面积（AUC）和 DeLong 检验比较模型性能。结果两个中心共 299 名患者被分为三个队列：主要队列（中心 A；n = 194，其中有 36 名无应答者和 158 名应答者）、内部验证队列（中心 A；n = 49，其中有 9 名无应答者）和外部验证队列（中心 B；n = 56，其中有 33 名无应答者）。TA模型由post_mean、mean_change、post_skewness、post_entropy和entropy_change构建而成，在主要队列中的AUC为0.997（95%置信区间[CI]，0.975-1.000），优于ADC模型和主观评价。在内部和外部验证队列中也观察到了稳健的表现，AUC 分别为 0.919（95% CI，0.805-0.978）和 0.938（95% CI，0.840-0.985）。结论 TA 模型有可能成为识别 LARC 患者对 NCT 无应答的影像生物标志物，为这些患者考虑额外放疗提供有价值的参考。

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

Gastroenterology Report Medicine-Gastroenterology

CiteScore

4.60

自引率

2.80%

发文量

审稿时长

8 weeks

期刊介绍： Gastroenterology Report is an international fully open access (OA) online only journal, covering all areas related to gastrointestinal sciences, including studies of the alimentary tract, liver, biliary, pancreas, enteral nutrition and related fields. The journal aims to publish high quality research articles on both basic and clinical gastroenterology, authoritative reviews that bring together new advances in the field, as well as commentaries and highlight pieces that provide expert analysis of topical issues.