Surf-CDM: Score-Based Surface Cold-Diffusion Model For Medical Image
Segmentation
- URL: http://arxiv.org/abs/2312.12649v1
- Date: Tue, 19 Dec 2023 22:50:02 GMT
- Title: Surf-CDM: Score-Based Surface Cold-Diffusion Model For Medical Image
Segmentation
- Authors: Fahim Ahmed Zaman, Mathews Jacob, Amanda Chang, Kan Liu, Milan Sonka
and Xiaodong Wu
- Abstract summary: We propose a conditional score-based generative modeling framework for medical image segmentation.
We evaluate our method on the segmentation of the left ventricle from 65 transthoracic echocardiogram videos.
Our proposed model not only outperformed the compared methods in terms of segmentation accuracy, but also showed potential in estimating segmentation uncertainties.
- Score: 15.275335829889086
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Diffusion models have shown impressive performance for image generation,
often times outperforming other generative models. Since their introduction,
researchers have extended the powerful noise-to-image denoising pipeline to
discriminative tasks, including image segmentation. In this work we propose a
conditional score-based generative modeling framework for medical image
segmentation which relies on a parametric surface representation for the
segmentation masks. The surface re-parameterization allows the direct
application of standard diffusion theory, as opposed to when the mask is
represented as a binary mask. Moreover, we adapted an extended variant of the
diffusion technique known as the "cold-diffusion" where the diffusion model can
be constructed with deterministic perturbations instead of Gaussian noise,
which facilitates significantly faster convergence in the reverse diffusion. We
evaluated our method on the segmentation of the left ventricle from 65
transthoracic echocardiogram videos (2230 echo image frames) and compared its
performance to the most popular and widely used image segmentation models. Our
proposed model not only outperformed the compared methods in terms of
segmentation accuracy, but also showed potential in estimating segmentation
uncertainties for further downstream analyses due to its inherent generative
nature.
Related papers
- Latent Diffusion for Medical Image Segmentation: End to end learning for fast sampling and accuracy [14.545920180010201]
Conditional diffusion in latent space ensures accurate image segmentation for multiple interacting objects.
Our proposed model was significantly more robust to noise compared to traditional deterministic segmentation models.
arXiv Detail & Related papers (2024-07-17T18:44:38Z) - Masked Diffusion as Self-supervised Representation Learner [5.449210269462304]
Masked diffusion model (MDM) is a scalable self-supervised representation learner for semantic segmentation.
This paper decomposes the interrelation between the generative capability and representation learning ability inherent in diffusion models.
arXiv Detail & Related papers (2023-08-10T16:57:14Z) - SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired
Image-to-Image Translation [96.11061713135385]
This work presents a new score-decomposed diffusion model to explicitly optimize the tangled distributions during image generation.
We equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold.
SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.
arXiv Detail & Related papers (2023-08-04T06:21:57Z) - Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image Attenuation [53.04220377034574]
We propose incorporating an analytical image attenuation process into the forward diffusion process for high-quality (un)conditioned image generation.
Our method represents the forward image-to-noise mapping as simultaneous textitimage-to-zero mapping and textitzero-to-noise mapping.
We have conducted experiments on unconditioned image generation, textite.g., CIFAR-10 and CelebA-HQ-256, and image-conditioned downstream tasks such as super-resolution, saliency detection, edge detection, and image inpainting.
arXiv Detail & Related papers (2023-06-23T18:08:00Z) - Towards Better Certified Segmentation via Diffusion Models [62.21617614504225]
segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-decision systems like healthcare or autonomous driving.
Recently, randomized smoothing has been proposed to certify segmentation predictions by adding Gaussian noise to the input to obtain theoretical guarantees.
In this paper, we address the problem of certifying segmentation prediction using a combination of randomized smoothing and diffusion models.
arXiv Detail & Related papers (2023-06-16T16:30:39Z) - Conditional Diffusion Models for Weakly Supervised Medical Image
Segmentation [18.956306942099097]
Conditional diffusion models (CDM) is capable of generating images subject to specific distributions.
We utilize category-aware semantic information underlied in CDM to get the prediction mask of the target object.
Our method outperforms state-of-the-art CAM and diffusion model methods on two public medical image segmentation datasets.
arXiv Detail & Related papers (2023-06-06T17:29:26Z) - Denoising Diffusion Semantic Segmentation with Mask Prior Modeling [61.73352242029671]
We propose to ameliorate the semantic segmentation quality of existing discriminative approaches with a mask prior modeled by a denoising diffusion generative model.
We evaluate the proposed prior modeling with several off-the-shelf segmentors, and our experimental results on ADE20K and Cityscapes demonstrate that our approach could achieve competitively quantitative performance.
arXiv Detail & Related papers (2023-06-02T17:47:01Z) - Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance.
We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring.
Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
arXiv Detail & Related papers (2023-05-22T12:18:20Z) - BerDiff: Conditional Bernoulli Diffusion Model for Medical Image
Segmentation [19.036821997968552]
We propose a conditional Bernoulli Diffusion model for medical image segmentation (BerDiff)
Our results show that our BerDiff outperforms other recently published state-of-the-art methods.
arXiv Detail & Related papers (2023-04-10T07:21:38Z) - Unifying Diffusion Models' Latent Space, with Applications to
CycleDiffusion and Guidance [95.12230117950232]
We show that a common latent space emerges from two diffusion models trained independently on related domains.
Applying CycleDiffusion to text-to-image diffusion models, we show that large-scale text-to-image diffusion models can be used as zero-shot image-to-image editors.
arXiv Detail & Related papers (2022-10-11T15:53:52Z) - Diffusion Models for Implicit Image Segmentation Ensembles [1.444701913511243]
We present a novel semantic segmentation method based on diffusion models.
By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images.
Compared to state-of-the-art segmentation models, our approach yields good segmentation results and, additionally, meaningful uncertainty maps.
arXiv Detail & Related papers (2021-12-06T16:28:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.