Key result
Cross-modal deep-learning model detects severe coronary stenosis with ~0.83 AUC, outperforming manual CCTA reading.
Why the study?
Conventional manual reading of CCTA suffers from subjective bias and limited reproducibility, motivating a cross-modal deep-learning framework integrating image and clinical text information to improve detection of severe coronary stenosis.
Does a cross-modal image-text collaborative deep-learning model improve diagnostic performance for identifying severe coronary artery stenosis from CCTA compared to conventional manual CCTA reading in patients undergoing CCTA and invasive coronary angiography?
Observational (n=96)
Single-blind
No
Does a cross-modal image-text collaborative deep-learning model improve diagnostic performance for identifying severe coronary artery stenosis from CCTA compared to conventional manual CCTA reading in patients undergoing CCTA and invasive coronary angiography?
Answers are grounded in this paper and cite their sources.
A cross-modal image-text collaborative deep-learning model integrating CCTA images and clinical text significantly improved diagnostic accuracy and AUC (0.83 vs 0.676) for detecting severe coronary stenosis compared with conventional manual reading.
Background Coronary computed tomography angiography (CCTA) is a cornerstone non‑invasive modality for coronary artery evaluation. Nevertheless, conventional manual reading suffers from subjective bias and limited reproducibility. We proposed a cross‑modal deep‑learning framework integrating image and clinical text information to improve detection of severe coronary stenosis. Objective To develop and validate a cross‑modal radiomics deep‑learning model based on CCTA data and further evaluate its clinical performance for identifying severe coronary artery stenosis. Methods In this single‑center retrospective study, 96 patients receiving both CCTA and invasive coronary angiography (ICA) were enrolled, yielding 288 raw coronary vessel‑level samples; two vessels were excluded for vessel‑specific poor image quality, resulting in 286 evaluable coronary vessel‑level (unit of analysis) samples. A dual‑branch cross‑modal model combining ResNet‑18 image encoder and lightweight Transformer text encoder was constructed. Class‑differentiated augmentation and multi‑loss joint optimization were applied to mitigate class imbalance. Dataset was split into training/test set (8:2). Using ICA as reference gold‑standard, ROC‑based diagnostic metrics (AUC, sensitivity, specificity, accuracy, PPV, NPV) were calculated for model and manual interpretation. Results Our cross‑modal deep‑learning model achieved AUC = 0.83 (95%CI 0.71‑0.94), sensitivity 64.0%, specificity 93.0%, accuracy 79.0%, PPV 89.0%, NPV 74.0%. It outperformed manual CCTA reading (AUC = 0.676; sensitivity 46.38%, specificity 88.7%, accuracy 68.5%). Conclusion The proposed cross‑modal image‑text collaborative deep‑learning model improves diagnostic performance for severe coronary stenosis. It could serve as a promising intelligent auxiliary tool for CCTA‑based non‑invasive assessment of coronary artery disease.
No takes yet. Share an insight, caveat, or question.
Ma et al. (2026) conducted an observational in Severe coronary artery stenosis (n=96). Cross-modal image-text collaborative deep-learning model (ResNet-18 and lightweight Transformer) vs. Conventional manual CCTA reading was evaluated on Diagnostic accuracy and discriminative performance (AUC) for identifying severe coronary stenosis (≥70%) using invasive coronary angiography as the gold standard (AUC 0.83, 95% CI 0.71-0.94). The cross-modal image-text deep-learning model achieved an AUC of 0.83 and 79.0% accuracy for detecting severe coronary stenosis, outperforming manual CCTA reading.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: