Region of interest detection for efficient aortic segmentation

2025-03-17

Medical Imaging

AI Summary

This study addresses the challenge of precise imaging analysis for thoracic aortic dissection and aneurysms, which is hindered by the high computational cost and operational complexity of -dimensional aortic segmentation. To overcome this, the authors propose a lightweight cascaded multi-task framework featuring a shared encoder that simultaneously performs region-of-interest (ROI) detection and segmentation of the aorta. The ROI detection module, implemented via a fully connected network attached to a bottleneck layer, substantially reduces the spatial domain requiring processing. Experimental results demonstrate that the method achieves Dice scores consistently above 0.9—averaging 0.944—while utilizing only approximately one-third of the computational resources required by baseline approaches such as nnU-Net. The proposed framework thus offers a highly efficient, robust, and clinically viable solution for automated aortic analysis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Thoracic aortic dissection and aneurysms are the most lethal diseases of the aorta. The major hindrance to treatment lies in the accurate analysis of the medical images. More particularly, aortic segmentation of the 3D image is often tedious and difficult. Deep-learning-based segmentation models are an ideal solution, but their inability to deliver usable outputs in difficult cases and their computational cost cause their clinical adoption to stay limited. This study presents an innovative approach for efficient aortic segmentation using targeted region of interest (ROI) detection. In contrast to classical detection models, we propose a simple and efficient detection model that can be widely applied to detect a single ROI. Our detection model is trained as a multi-task model, using an encoder-decoder architecture for segmentation and a fully connected network attached to the bottleneck for detection. We compare the performance of a one-step segmentation model applied to a complete image, nnU-Net and our cascade model composed of a detection and a segmentation step. We achieve a mean Dice similarity coefficient of 0.944 with over 0.9 for all cases using a third of the computing power. This simple solution achieves state-of-the-art performance while being compact and robust, making it an ideal solution for clinical applications.

Problem

• aortic segmentation
• region of interest detection
• thoracic aortic dissection
• medical image analysis
• 3D image segmentation

Innovation

• region of interest detection
• aortic segmentation
• multi-task learning
• efficient deep learning
• cascade model