SurgicaL-CD: Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Models
This addresses the challenge of limited annotated surgical data for surgeons and developers, though it is incremental as it builds on existing unpaired image translation techniques.
The paper tackled the problem of generating realistic surgical images for training computer-assisted surgery systems without requiring paired data, achieving superior performance over GANs and diffusion-based methods in quality and utility across three datasets.
Computer-assisted surgery (CAS) systems are designed to assist surgeons during procedures, thereby reducing complications and enhancing patient care. Training machine learning models for these systems requires a large corpus of annotated datasets, which is challenging to obtain in the surgical domain due to patient privacy concerns and the significant labeling effort required from doctors. Previous methods have explored unpaired image translation using generative models to create realistic surgical images from simulations. However, these approaches have struggled to produce high-quality, diverse surgical images. In this work, we introduce \emph{SurgicaL-CD}, a consistency-distilled diffusion method to generate realistic surgical images with only a few sampling steps without paired data. We evaluate our approach on three datasets, assessing the generated images in terms of quality and utility as downstream training datasets. Our results demonstrate that our method outperforms GANs and diffusion-based approaches. Our code is available at https://gitlab.com/nct_tso_public/gan2diffusion.