与胸外科医生相比，一种结合循环肿瘤细胞和放射学特征的深度学习模型用于纵隔病变多分类的大规模回顾性研究。

A deep learning model combining circulating tumor cells and radiological features in the multi-classification of mediastinal lesions in comparison with thoracic surgeons: a large-scale retrospective study.

作者信息

Wang Feng, Bao Minwei, Tao Bo, Yang Fugui, Wang Guangxue, Zhu Lei

机构信息

Department of Radiotherapy, School of Medicine, Shanghai Fourth People's Hospital, Tongji University, No. 1279, Sanmen Road, Shanghai, 200081, China.

Department of Thoracic Surgery, School of Medicine, Shanghai Pulmonary Hospital, Tongji University, 507 Zhengmin Road, Shanghai, 200433, China.

出版信息

BMC Med. 2025 May 7;23(1):267. doi: 10.1186/s12916-025-04104-z.

DOI:10.1186/s12916-025-04104-z

PMID:40335930

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12060378/

Abstract

BACKGROUND

CT images and circulating tumor cells (CTCs) are indispensable for diagnosing the mediastinal lesions by providing radiological and intra-tumoral information. This study aimed to develop and validate a deep multimodal fusion network (DMFN) combining CTCs and CT images for the multi-classification of mediastinal lesions.

METHODS

In this retrospective diagnostic study, we enrolled 1074 patients with 1500 enhanced CT images and 1074 CTCs results between Jan 1, 2020, and Dec 31, 2023. Patients were divided into the training cohort (n = 434), validation cohort (n = 288), and test cohort (n = 352). The DMFN and monomodal convolutional neural network (CNN) models were developed and validated using the CT images and CTCs results. The diagnostic performances of DMFN and monomodal CNN models were based on the Paraffin-embedded pathologies from surgical tissues. The predictive abilities were compared with thoracic resident physicians, attending physicians, and chief physicians by the area under the receiver operating characteristic (ROC) curve, and diagnostic results were visualized in the heatmap.

RESULTS

For binary classification, the predictive performances of DMFN (AUC = 0.941, 95% CI 0.901-0.982) were better than the monomodal CNN model (AUC = 0.710, 95% CI 0.664-0.756). In addition, the DMFN model achieved better predictive performances than the thoracic chief physicians, attending physicians, and resident physicians (P = 0.054, 0.020, 0.016) respectively. For the multiclassification, the DMFN achieved encouraging predictive abilities (AUC = 0.884, 95%CI 0.837-0.931), significantly outperforming the monomodal CNN (AUC = 0.722, 95%CI 0.705-0.739), also better than the chief physicians (AUC = 0.787, 95%CI 0.714-0.862), attending physicians (AUC = 0.632, 95%CI 0.612-0.654), and resident physicians (AUC = 0.541, 95%CI 0.508-0.574).

CONCLUSIONS

This study showed the feasibility and effectiveness of CNN model combing CT images and CTCs levels in predicting the diagnosis of mediastinal lesions. It could serve as a useful method to assist thoracic surgeons in improving diagnostic accuracy and has the potential to make management decisions.

摘要

背景

CT图像和循环肿瘤细胞（CTC）通过提供放射学和肿瘤内信息，对于纵隔病变的诊断不可或缺。本研究旨在开发并验证一种结合CTC和CT图像的深度多模态融合网络（DMFN），用于纵隔病变的多分类。

方法

在这项回顾性诊断研究中，我们纳入了2020年1月1日至2023年12月31日期间的1074例患者，他们有1500张增强CT图像和1074份CTC检测结果。患者被分为训练队列（n = 434）、验证队列（n = 288）和测试队列（n = 352）。使用CT图像和CTC检测结果开发并验证了DMFN和单模态卷积神经网络（CNN）模型。DMFN和单模态CNN模型的诊断性能基于手术组织的石蜡包埋病理结果。通过受试者操作特征（ROC）曲线下面积，将预测能力与胸科住院医师、主治医师和主任医师进行比较，并在热图中可视化诊断结果。

结果

对于二分类，DMFN的预测性能（AUC = 0.941，95%CI 0.901 - 0.982）优于单模态CNN模型（AUC = 0.710，95%CI 0.664 - 0.756）。此外，DMFN模型分别比胸科主任医师、主治医师和住院医师具有更好的预测性能（P = 0.054、0.020、0.016）。对于多分类，DMFN取得了令人鼓舞的预测能力（AUC = 0.884，95%CI 0.837 - 0.931），显著优于单模态CNN（AUC = 0.722，95%CI 0.705 - 0.739），也优于主任医师（AUC = 0.787，95%CI 0.714 - 0.862）、主治医师（AUC = 0.632，95%CI 0.6"12 - 0.654）和住院医师（AUC = 0.541，95%CI 0.508 - 0.574）。