Deep Learning and Radiomic Signatures Associated with Tumor Immune Heterogeneity Predict Microvascular Invasion in Colon Cancer.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 Yong'an Road, Xicheng District, Beijing 100050, China (J.J., J.W., Y.N.).
- Department of Radiology, Beijing Tongren Hospital, Capital Medical University, No.1 DongJiaoMinXiang Street, DongCheng District, Beijing 100730, China (Y.Z.).
- Department of Medical Imaging Center, The Affiliated Huaian NO.1 People's Hospital of Nanjing Medical University, Huaian 223300, Jiangsu, PR China (G.B.).
- Department of Medical Imaging, Huaian Hospital Affiliated to Xuzhou Medical University, Huaian 223001, Jiangsu, China (L.H.).
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 Yong'an Road, Xicheng District, Beijing 100050, China (J.J., J.W., Y.N.). Electronic address: [email protected].
Abstract
This study aims to develop and validate a deep learning radiomics signature (DLRS) that integrates radiomics and deep learning features for the non-invasive prediction of microvascular invasion (MVI) in patients with colon cancer (CC). Furthermore, the study explores the potential association between DLRS and tumor immune heterogeneity. This study is a multi-center retrospective study that included a total of 1007 patients with colon cancer (CC) from three medical centers and The Cancer Genome Atlas (TCGA-COAD) database. Patients from Medical Centers 1 and 2 were divided into a training cohort (n = 592) and an internal validation cohort (n = 255) in a 7:3 ratio. Medical Center 3 (n = 135) and the TCGA-COAD database (n = 25) were used as external validation cohorts. Radiomics and deep learning features were extracted from contrast-enhanced venous-phase CT images. Feature selection was performed using machine learning algorithms, and three predictive models were developed: a radiomics model, a deep learning (DL) model, and a combined deep learning radiomics (DLR) model. The predictive performance of each model was evaluated using multiple metrics, including the area under the curve (AUC), sensitivity, and specificity. Additionally, differential gene expression analysis was conducted on RNA-seq data from the TCGA-COAD dataset to explore the association between the DLRS and tumor immune heterogeneity within the tumor microenvironment. Compared to the standalone radiomics and deep learning models, DLR fusion model demonstrated superior predictive performance. The AUC for the internal validation cohort was 0.883 (95% CI: 0.828-0.937), while the AUC for the external validation cohort reached 0.855 (95% CI: 0.775-0.935). Furthermore, stratifying patients from the TCGA-COAD dataset into high-risk and low-risk groups based on the DLRS revealed significant differences in immune cell infiltration and immune checkpoint expression between the two groups (P < 0.05). The contrast-enhanced CT-based DLR fusion model developed in this study effectively predicts the MVI status in patients with CC. This model serves as a non-invasive preoperative assessment tool and reveals a potential association between the DLRS and immune heterogeneity within the tumor microenvironment, providing insights to optimize individualized treatment strategies.