DAFNet：基于全肺 CT 的多模态深度学习模型用于肺腺癌气腔播散的自动预测
DAFNet: A multi-modal deep learning model based on whole-lung CT for the automated prediction of the air space spread of lung adenocarcinoma.
作者
作者单位
- Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China.
- Department of Radiology, Harbin Medical University, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, Heilongjiang 150081, China.
- Department of Radiology, Beijing Jishuitan Hospital, Capital Medical University, Beijing 100035, China.
- Department of Radiology, Harbin Medical University, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, Heilongjiang 150081, China. Electronic address: articlemengwei@163.com.
- Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China. Electronic address: huyang@hit.edu.cn.
摘要
中文
气腔播散（STAS）是肺腺癌（LUAD）的一种特征性侵袭模式，与高复发率和不良预后相关。本研究引入了自动深度学习多模态检测网络（DAFNet），用于基于术前全肺 CT 扫描预测 STAS。与传统需要手动勾勒肿瘤的方法不同，DAFNet 通过整合多模态数据融合和多尺度特征提取方法，对肺部影像数据进行全面的端到端分析。对来自两个中心的 1164 例 LUAD 患者（511 例 STAS 阳性，653 例阴性）进行了回顾性分析，训练与测试集的划分比例为 70:30（训练集 814 例，测试集 350 例）。在测试集中，DAFNet 的受试者工作特征曲线下面积（AUROC）为 0.90（95% 置信区间 0.86-0.94），显著优于仅使用临床检查数值数据的预测模型（AUROC 0.72）和单独使用影像组学特征的模型（AUROC 0.65）。自适应门控融合机制与基于 DINOv3 的预训练架构的实施显著提高了 STAS 状态判定的预测准确性。这些发现使 DAFNet 成为一种有前景的完全自动化、非侵入性诊断工具，用于肺腺癌术前 STAS 预测，从而推进个性化手术规划，并通过增强临床转化潜力推动 AI 驱动的肿瘤学应用。
English
Spread through air spaces (STAS) is a characteristic invasive pattern of lung adenocarcinoma (LUAD), which is associated with a high recurrence rate and poor prognosis. This research introduced the automatic deep learning multimodal detection network (DAFNet) for predicting STAS based on preoperative whole-lung CT scans. In contrast to conventional approaches necessitating manual tumor delineation, DAFNet performs comprehensive end-to-end analysis of pulmonary imaging data through integrated multimodal data fusion and multiscale feature extraction methodologies. A retrospective analysis was performed on 1164 patients with LUAD (511 STAS-positive and 653 negative) from two centers, with a training-to-test split ratio of 70:30 (814 in training set and 350 in test set). In the test set, DAFNet demonstrated an area under the receiver operating characteristic curve (AUROC) of 0.90 (95% confidence interval 0.86-0.94), significantly outperforming predictive models utilizing clinical examination numerical data alone (AUROC 0.72) and radiomics features independently (AUROC 0.65). The implementation of an adaptive gate fusion mechanism combined with a DINOv3-based pre-trained architecture substantially improved predictive accuracy for STAS status determination. These findings establish DAFNet as a promising fully automated, non-invasive diagnostic tool for preoperative STAS prediction in lung adenocarcinoma, thereby advancing personalized surgical planning and promoting AI-driven oncological applications through enhanced clinical translation potential.
分类与指标
- 研究类型
- AI/ML
- 病种
- 肺癌
- JCR 分区
- Q1
- 影响因子
- 5.3
- 新锐分区
- 2区