paper-with-me

홈 › Papers

LSegDiff: A Latent Diffusion Model for Medical Image Segmentation

2023-12-07 · SOICT 2023: The 12th International Symposium on Information and Communication Technology 2023 12 · Vu Quoc Hung, Tran Le Phuong Thao, Trinh Xuan Minh, Dinh Viet Sang

Initially designed for image generation, diffusion models can also be effectively applied to various tasks, including semantic segmentation. However, most existing diffusion-based approaches for semantic segmentation operate in high-dimensional pixel space, demanding a lot of computing and memory resources during training and inference. This paper makes the first attempt to utilize latent diffusion models for semantic segmentation. Specifically, we propose a fast yet effective latent diffusion model and valuate it on medical image segmentation tasks. Firstly, we train a Variational Autoencoder (VAE) network to convert binary image masks into compact latent vectors. The diffusion process can then be executed in this low-dimensional latent space and thus drastically accelerated. Subsequently, we employ the VAE decoder to reconstruct a precise prediction map from the latent output vector produced by the diffusion process. Eventually, we refine the final segmentation results through a straightforward post-processing step using morphological operations. We report our results on two public datasets, including colon polyp images and skin cancer images. Experiments show that our approach achieves competitive accuracy compared to traditional diffusion models while having much better training and inference speed, as well as much more efficient memory consumption.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImage GenerationImage SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Similar Papers 제목 키워드 기반

Latent Diffusion for Medical Image Segmentation: End to end learning for fast sampling and accuracy

2024-07-17 · Fahim Ahmed Zaman, Mathews Jacob, Amanda Chang, Kan Liu 외

Diffusion Probabilistic Models (DPMs) suffer from inefficient inference due to their slow sampling and high memory consumption, which limits their applicability to various medical imaging applications. In this work, we p…

DenoisingImage DenoisingImage GenerationImage Segmentation+4

Conditional diffusion model with spatial attention and latent embedding for medical image segmentation

2025-02-10 · Behzad Hejrati, Soumyanil Banerjee, Carri Glide-Hurst, Ming Dong

Diffusion models have been used extensively for high quality image and video generation tasks. In this paper, we propose a novel conditional diffusion model with spatial attention and latent embedding (cDAL) for medical …

HippocampusImage SegmentationMedical Image SegmentationSegmentation+2

Diffusion-Based Data Augmentation for Medical Image Segmentation

2025-08-25 · Maham Nazir, Muhammad Aqeel, Francesco Setti arxiv

Medical image segmentation models struggle with rare abnormalities due to scarce annotated pathological data. We propose DiffAug a novel framework that combines textguided diffusion-based generation with automatic segmen…

Medical Image SegmentationData Augmentation

LEAF: Latent Diffusion with Efficient Encoder Distillation for Aligned Features in Medical Image Segmentation

2025-07-24 · Qilin Huang, Tianyu Lin, Zhiguang Chen, Fudan Zheng arxiv

Leveraging the powerful capabilities of diffusion models has yielded quite effective results in medical image segmentation tasks. However, existing methods typically transfer the original training process directly withou…

Medical Image Segmentation

Robust Noisy Pseudo-label Learning for Semi-supervised Medical Image Segmentation Using Diffusion Model

2025-07-22 · Lin Xi, Yingliang Ma, Cheng Wang, Sandra Howell 외 arxiv

Obtaining pixel-level annotations in the medical domain is both expensive and time-consuming, often requiring close collaboration between clinical experts and developers. Semi-supervised medical image segmentation aims t…

Semi-supervised Medical Image SegmentationObject Segmentation