Synchronous Image-Label Diffusion Probability Model with Application to Stroke Lesion Segmentation on Non-contrast CT
This addresses the challenge of automatically measuring stroke lesion volume for Acute Ischemic Stroke patients, but it is incremental as it builds on existing diffusion probabilistic models for segmentation.
The authors tackled stroke lesion segmentation on non-contrast CT scans by proposing a Synchronous image-label Diffusion Probability Model (SDPM), which achieved state-of-the-art performance compared to U-net and transformer-based methods on three datasets.
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.