Real‐time, high‐precision detection of aortic dissection key components for emergency triage using an enhanced deep learning model
Authors:
- 10 May 2026
- journal article
- Published by Wiley in Medical Physics
- Vol. 53 (5) , e70461
Abstract
Background: Aortic dissection (AD) is a life‐threatening cardiovascular emergency. For Type B AD (TBAD), rapid and accurate identification of the true lumen (TL), false lumen (FL), and false lumen thrombus (FLT) from CTA is critical for risk stratification and treatment planning. However, existing deep learning solutions often lack real‐time capability and fail to address the detection of FLT. Purpose: To develop a real‐time, high‐precision deep learning framework for the simultaneous detection of all three key AD components to support emergency triage. Methods: We propose AD‐YOLO11, an enhanced YOLOv11 model integrating three key innovations: (1) a Recursive Information Distillation Network (RIDNet) for CTA noise suppression, (2) a Triplet Attention Mechanism for spatial and channel feature enhancement, and (3) the MPDIoU loss function for optimized bounding box regression. The model was trained and internally validated on a dataset of 25 176 slices from 106 TBAD patients and externally validated on 18 238 slices from 71 independent patients. Results: On internal validation, AD‐YOLO11 achieved a precision of 0.991 ± 0.004, recall of 0.936 ± 0.006, mAP@0.5 of 0.951 ± 0.007, and mAP@0.5:0.95 of 0.883 ± 0.008. It maintained high performance on the external test set, demonstrating strong generalizability. The inference speed was 3.18 ± 0.23 ms per slice on GPU, and it remained clinically feasible on CPU (53.15 ± 2.76 ms per slice). Conclusions: AD‐YOLO11 achieves millisecond‐level, high‐accuracy detection of all three critical Type B aortic dissection components from CTA images. Its efficient inference on both GPU and CPU makes it a promising frontline tool for rapid triage in emergency and resource‐limited settings, effectively complementing time‐consuming 3D segmentation for aortic dissection assessment.Keywords
This publication has 20 references indexed in Scilit:
- Utilizing domain knowledge to improve the classification of intravenous contrast phase of CT scansComputerized Medical Imaging and Graphics, 2024
- Exploratory analysis of Type B Aortic Dissection (TBAD) segmentation in 2D CTA images using various kernelsComputerized Medical Imaging and Graphics, 2024
- Image detection of aortic dissection complications based on multi-scale feature fusionHeliyon, 2024
- Recent developments in denoising medical images using deep learning: An overview of models, techniques, and challengesMicron, 2024
- Improved detection of aortic dissection in non-contrast-enhanced chest CT using an attention-based deep learning modelHeliyon, 2024
- Risk of Type B Dissection in Marfan SyndromeJACC, 2023
- Automatic segmentation of thrombosed aortic dissection in post‐operative CT‐angiography imagesMedical Physics, 2023
- MOLS-Net: Multi-organ and lesion segmentation network based on sequence feature pyramid and attention mechanism for aortic dissection diagnosisKnowledge-Based Systems, 2022
- Double paths network with residual information distillation for improving lung CT image super resolutionBiomedical Signal Processing and Control, 2021
- Partial Thrombosis of the False Lumen in Patients with Acute Type B Aortic DissectionNew England Journal of Medicine, 2007