Synchronous Image-Label Diffusion Probability Model with Application to Stroke Lesion Segmentation on Non-contrast CT

TL;DR

This paper introduces a novel Synchronous image-label Diffusion Probability Model (SDPM) for stroke lesion segmentation on Non-Contrast CT scans, leveraging probabilistic diffusion processes to improve accuracy.

Contribution

The paper presents a fully probabilistic SDPM based on a Latent Variable Model with an additional net-stream for efficient label inference, achieving state-of-the-art results.

Findings

Outperforms U-net and transformer-based methods

Achieves state-of-the-art segmentation accuracy

Validated on multiple stroke lesion datasets

Abstract

Stroke lesion volume is a key radiologic measurement for assessing the prognosis of Acute Ischemic Stroke (AIS) patients, which is challenging to be automatically measured on Non-Contrast CT (NCCT) scans. Recent diffusion probabilistic models have shown potentials of being used for image segmentation. In this paper, a novel Synchronous image-label Diffusion Probability Model (SDPM) is proposed for stroke lesion segmentation on NCCT using Markov diffusion process. The proposed SDPM is fully based on a Latent Variable Model (LVM), offering a complete probabilistic elaboration. An additional net-stream, parallel with a noise prediction stream, is introduced to obtain initial noisy label estimates for efficiently inferring the final labels. By optimizing the specified variational boundaries, the trained model can infer multiple label estimates for reference given the input images with noises. The proposed model was assessed on three stroke lesion datasets including one public and two private datasets. Compared to several U-net and transformer-based segmentation methods, our proposed SDPM model is able to achieve state-of-the-art performance. The code is publicly available.