LOTUS: Latent Outpainting Diffusion Model for Three-Dimensional Ultrasound Stitching

Xing Yao, Runxuan Yu, Nick DiSanto, Ehsan Khodapanah Aghdam, Kanyifeechukwu Jane Oguine, Daiwei Lu, Ange Lou, Jiacheng Wang, Dewei Hu, Gabriel A Arenas, Baris Oguz, Alison Marie Pouch, Nadav Schwartz, Brett Byram, Ipek Oguz

Keywords: Latent Diffusion Model, Ultrasound, Outpainting, Registration

TL;DR: We propose LOTUS, a novel Latent Dif- fusion Model (LDM) specifically designed for 3DUS FOV outpainting and improve the 3DUS stitching performance

Abstract:

3D ultrasound (3DUS) stitching can enlarge the field-of-view (FOV) by registering partially overlapping 3DUS images collected from different probe positions. However, standard registration algorithms frequently encounter difficulties with this task, primarily due to the sector-shaped FOV, which often leads to pronounced local minima, thereby obstructing optimization efforts.
To address these limitations, we propose LOTUS, a novel Latent Diffusion Model (LDM) specifically designed for 3DUS FOV outpainting. LOTUS innovatively encodes the 3DUS data into a compact latent space and performs outpainting at test time, effectively extending the sector-shaped FOV into a standard rectangular shape. This transformation facilitates a more robust registration by mitigating the issues of local minima associated with the original FOV shape. Experimental results show that LOTUS significantly improves the accuracy of the registration as well as the efficiency of the outpainting process compared to existing models. The code is available at https://github.com/MedICL-VU/LOTUS.

Primary Subject Area: Image Registration

Secondary Subject Area: Generative Models

Paper Type: Methodological Development

Registration Requirement: Yes

Reproducibility: https://github.com/MedICL-VU/LOTUS

Submission Number: 131