Region of interest detection for efficient aortic segmentation

TL;DR

This paper introduces a novel, efficient ROI detection method for aortic segmentation that outperforms existing models in accuracy and computational efficiency, facilitating clinical adoption of deep learning tools.

Contribution

The study proposes a simple, multi-task detection and segmentation model that improves accuracy and reduces computational cost compared to classical detection models.

Findings

Achieved a mean Dice coefficient of 0.944 on aortic segmentation.

Reduced computational power requirement to one-third of traditional models.

Outperformed nnU-Net in accuracy and efficiency.

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.