Voxel-level radiomics and deep learning for predicting pathologic complete response in esophageal squamous cell carcinoma after neoadjuvant immunotherapy and chemotherapy.

IF 10.3 1区 医学 Q1 IMMUNOLOGY
Zhen Zhang, Tianchen Luo, Meng Yan, Haixia Shen, Kaiyi Tao, Jian Zeng, Jingping Yuan, Min Fang, Jian Zheng, Inigo Bermejo, Andre Dekker, Dirk De Ruysscher, Leonard Wee, Wencheng Zhang, Youhua Jiang, Yongling Ji
{"title":"Voxel-level radiomics and deep learning for predicting pathologic complete response in esophageal squamous cell carcinoma after neoadjuvant immunotherapy and chemotherapy.","authors":"Zhen Zhang, Tianchen Luo, Meng Yan, Haixia Shen, Kaiyi Tao, Jian Zeng, Jingping Yuan, Min Fang, Jian Zheng, Inigo Bermejo, Andre Dekker, Dirk De Ruysscher, Leonard Wee, Wencheng Zhang, Youhua Jiang, Yongling Ji","doi":"10.1136/jitc-2024-011149","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Accurate prediction of pathologic complete response (pCR) following neoadjuvant immunotherapy combined with chemotherapy (nICT) is crucial for tailoring patient care in esophageal squamous cell carcinoma (ESCC). This study aimed to develop and validate a deep learning model using a novel voxel-level radiomics approach to predict pCR based on preoperative CT images.</p><p><strong>Methods: </strong>In this multicenter, retrospective study, 741 patients with ESCC who underwent nICT followed by radical esophagectomy were enrolled from three institutions. Patients from one center were divided into a training set (469 patients) and an internal validation set (118 patients) while the data from the other two centers was used as external validation sets (120 and 34 patients, respectively). The deep learning model, Vision-Mamba, integrated voxel-level radiomics feature maps and CT images for pCR prediction. Additionally, other commonly used deep learning models, including 3D-ResNet and Vision Transformer, as well as traditional radiomics methods, were developed for comparison. Model performance was evaluated using accuracy, area under the curve (AUC), sensitivity, specificity, and prognostic stratification capabilities. The SHapley Additive exPlanations analysis was employed to interpret the model's predictions.</p><p><strong>Results: </strong>The Vision-Mamba model demonstrated robust predictive performance in the training set (accuracy: 0.89, AUC: 0.91, sensitivity: 0.82, specificity: 0.92) and validation sets (accuracy: 0.83-0.91, AUC: 0.83-0.92, sensitivity: 0.73-0.94, specificity: 0.84-1.0). The model outperformed other deep learning models and traditional radiomics methods. The model's ability to stratify patients into high and low-risk groups was validated, showing superior prognostic stratification compared with traditional methods. SHAP provided quantitative and visual model interpretation.</p><p><strong>Conclusions: </strong>We present a voxel-level radiomics-based deep learning model to predict pCR to neoadjuvant immunotherapy combined with chemotherapy based on pretreatment diagnostic CT images with high accuracy and robustness. This model could provide a promising tool for individualized management of patients with ESCC.</p>","PeriodicalId":14820,"journal":{"name":"Journal for Immunotherapy of Cancer","volume":"13 3","pages":""},"PeriodicalIF":10.3000,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11911808/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal for Immunotherapy of Cancer","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/jitc-2024-011149","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"IMMUNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Accurate prediction of pathologic complete response (pCR) following neoadjuvant immunotherapy combined with chemotherapy (nICT) is crucial for tailoring patient care in esophageal squamous cell carcinoma (ESCC). This study aimed to develop and validate a deep learning model using a novel voxel-level radiomics approach to predict pCR based on preoperative CT images.

Methods: In this multicenter, retrospective study, 741 patients with ESCC who underwent nICT followed by radical esophagectomy were enrolled from three institutions. Patients from one center were divided into a training set (469 patients) and an internal validation set (118 patients) while the data from the other two centers was used as external validation sets (120 and 34 patients, respectively). The deep learning model, Vision-Mamba, integrated voxel-level radiomics feature maps and CT images for pCR prediction. Additionally, other commonly used deep learning models, including 3D-ResNet and Vision Transformer, as well as traditional radiomics methods, were developed for comparison. Model performance was evaluated using accuracy, area under the curve (AUC), sensitivity, specificity, and prognostic stratification capabilities. The SHapley Additive exPlanations analysis was employed to interpret the model's predictions.

Results: The Vision-Mamba model demonstrated robust predictive performance in the training set (accuracy: 0.89, AUC: 0.91, sensitivity: 0.82, specificity: 0.92) and validation sets (accuracy: 0.83-0.91, AUC: 0.83-0.92, sensitivity: 0.73-0.94, specificity: 0.84-1.0). The model outperformed other deep learning models and traditional radiomics methods. The model's ability to stratify patients into high and low-risk groups was validated, showing superior prognostic stratification compared with traditional methods. SHAP provided quantitative and visual model interpretation.

Conclusions: We present a voxel-level radiomics-based deep learning model to predict pCR to neoadjuvant immunotherapy combined with chemotherapy based on pretreatment diagnostic CT images with high accuracy and robustness. This model could provide a promising tool for individualized management of patients with ESCC.

体素水平放射组学和深度学习预测食管鳞状细胞癌新辅助免疫治疗和化疗后病理完全缓解。
背景:准确预测新辅助免疫治疗联合化疗(nICT)后的病理完全缓解(pCR)对食管鳞状细胞癌(ESCC)患者的定制护理至关重要。本研究旨在开发和验证一种深度学习模型,使用一种新的体素水平放射组学方法来预测基于术前CT图像的pCR。方法:在这项多中心、回顾性研究中,来自三个机构的741例ESCC患者行nICT后根治性食管切除术。其中一个中心的患者被分为训练集(469例)和内部验证集(118例),另外两个中心的数据被用作外部验证集(分别为120例和34例)。深度学习模型Vision-Mamba集成了体素级放射组学特征图和CT图像,用于pCR预测。此外,还开发了其他常用的深度学习模型,包括3D-ResNet和Vision Transformer,以及传统的放射组学方法进行比较。通过准确性、曲线下面积(AUC)、敏感性、特异性和预后分层能力来评估模型的性能。SHapley加性解释分析被用来解释模型的预测。结果:Vision-Mamba模型在训练集(准确率:0.89,AUC: 0.91,灵敏度:0.82,特异性:0.92)和验证集(准确率:0.83-0.91,AUC: 0.83-0.92,灵敏度:0.73-0.94,特异性:0.84-1.0)上表现出稳健的预测性能。该模型优于其他深度学习模型和传统放射组学方法。该模型将患者分为高风险和低风险组的能力得到了验证,与传统方法相比,显示出更好的预后分层。SHAP提供了定量和可视化的模型解释。结论:我们提出了一种基于体素水平放射组学的深度学习模型,可以基于预处理诊断CT图像预测pCR对新辅助免疫治疗联合化疗的影响,具有较高的准确性和鲁棒性。该模型为ESCC患者的个体化治疗提供了一个有前景的工具。
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
Journal for Immunotherapy of Cancer
Journal for Immunotherapy of Cancer Biochemistry, Genetics and Molecular Biology-Molecular Medicine
CiteScore
17.70
自引率
4.60%
发文量
522
审稿时长
18 weeks
期刊介绍: The Journal for ImmunoTherapy of Cancer (JITC) is a peer-reviewed publication that promotes scientific exchange and deepens knowledge in the constantly evolving fields of tumor immunology and cancer immunotherapy. With an open access format, JITC encourages widespread access to its findings. The journal covers a wide range of topics, spanning from basic science to translational and clinical research. Key areas of interest include tumor-host interactions, the intricate tumor microenvironment, animal models, the identification of predictive and prognostic immune biomarkers, groundbreaking pharmaceutical and cellular therapies, innovative vaccines, combination immune-based treatments, and the study of immune-related toxicity.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信