AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging

2025-10-01

AI Summary

This study addresses two key challenges in abdominal aortic aneurysm (AAA) assessment: safety risks associated with iodinated contrast-enhanced CT (CECT) and error accumulation from multi-stage processing pipelines. To overcome these, we propose an end-to-end jointly optimized framework based on conditional diffusion modeling and multi-task learning, which simultaneously synthesizes high-fidelity CECT-like images from non-contrast CT (NCCT) and performs precise segmentation of the aortic lumen and intraluminal thrombus. The model employs shared encoder-decoder parameters, operates mask-free, and supports semi-supervised training to mitigate annotation scarcity. Evaluated on 264 clinical cases, our method achieves a PSNR of 25.61 dB for synthetic CECT and Dice scores of 0.89 and 0.53 for lumen and thrombus segmentation, respectively—outperforming state-of-the-art approaches. Clinical measurement errors are substantially reduced, establishing a novel, contrast-free paradigm for accurate AAA evaluation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

While contrast-enhanced CT (CECT) is standard for assessing abdominal aortic aneurysms (AAA), the required iodinated contrast agents pose significant risks, including nephrotoxicity, patient allergies, and environmental harm. To reduce contrast agent use, recent deep learning methods have focused on generating synthetic CECT from non-contrast CT (NCCT) scans. However, most adopt a multi-stage pipeline that first generates images and then performs segmentation, which leads to error accumulation and fails to leverage shared semantic and anatomical structures. To address this, we propose a unified deep learning framework that generates synthetic CECT images from NCCT scans while simultaneously segmenting the aortic lumen and thrombus. Our approach integrates conditional diffusion models (CDM) with multi-task learning, enabling end-to-end joint optimization of image synthesis and anatomical segmentation. Unlike previous multitask diffusion models, our approach requires no initial predictions (e.g., a coarse segmentation mask), shares both encoder and decoder parameters across tasks, and employs a semi-supervised training strategy to learn from scans with missing segmentation labels, a common constraint in real-world clinical data. We evaluated our method on a cohort of 264 patients, where it consistently outperformed state-of-the-art single-task and multi-stage models. For image synthesis, our model achieved a PSNR of 25.61 dB, compared to 23.80 dB from a single-task CDM. For anatomical segmentation, it improved the lumen Dice score to 0.89 from 0.87 and the challenging thrombus Dice score to 0.53 from 0.48 (nnU-Net). These segmentation enhancements led to more accurate clinical measurements, reducing the lumen diameter MAE to 4.19 mm from 5.78 mm and the thrombus area error to 33.85% from 41.45% when compared to nnU-Net. Code is available at https://github.com/yuxuanou623/AortaDiff.git.

Problem

• Generating synthetic contrast CT from non-contrast scans for AAA assessment
• Simultaneously performing aortic lumen and thrombus segmentation tasks
• Overcoming error accumulation in multi-stage pipelines through unified modeling

Innovation

• Unified diffusion framework generates synthetic CECT from NCCT
• Jointly optimizes image synthesis and anatomical segmentation end-to-end
• Shares encoder-decoder parameters and uses semi-supervised training strategy