LeFusion: Synthesizing Myocardial Pathology on Cardiac MRI via Lesion-Focus Diffusion Models
- URL: http://arxiv.org/abs/2403.14066v1
- Date: Thu, 21 Mar 2024 01:25:39 GMT
- Title: LeFusion: Synthesizing Myocardial Pathology on Cardiac MRI via Lesion-Focus Diffusion Models
- Authors: Hantao Zhang, Jiancheng Yang, Shouhong Wan, Pascal Fua,
- Abstract summary: This study aims to mitigate these challenges through data synthesis.
Inspired by diffusion-based image inpainting, we propose LeFusion, lesion-focused diffusion models.
Our methodology employs the popular nnUNet to demonstrate that the synthetic data make it possible to effectively enhance a state-of-the-art model.
- Score: 46.59911767338791
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Data generated in clinical practice often exhibits biases, such as long-tail imbalance and algorithmic unfairness. This study aims to mitigate these challenges through data synthesis. Previous efforts in medical imaging synthesis have struggled with separating lesion information from background context, leading to difficulties in generating high-quality backgrounds and limited control over the synthetic output. Inspired by diffusion-based image inpainting, we propose LeFusion, lesion-focused diffusion models. By redesigning the diffusion learning objectives to concentrate on lesion areas, it simplifies the model learning process and enhance the controllability of the synthetic output, while preserving background by integrating forward-diffused background contexts into the reverse diffusion process. Furthermore, we generalize it to jointly handle multi-class lesions, and further introduce a generative model for lesion masks to increase synthesis diversity. Validated on the DE-MRI cardiac lesion segmentation dataset (Emidec), our methodology employs the popular nnUNet to demonstrate that the synthetic data make it possible to effectively enhance a state-of-the-art model. Code and model are available at https://github.com/M3DV/LeFusion.
Related papers
- Similarity-aware Syncretic Latent Diffusion Model for Medical Image Translation with Representation Learning [15.234393268111845]
Non-contrast CT (NCCT) imaging may reduce image contrast and anatomical visibility, potentially increasing diagnostic uncertainty.
We propose a novel Syncretic generative model based on the latent diffusion model for medical image translation (S$2$LDM)
S$2$LDM enhances the similarity in distinct modal images via syncretic encoding and diffusing, promoting amalgamated information in the latent space and generating medical images with more details in contrast-enhanced regions.
arXiv Detail & Related papers (2024-06-20T03:54:41Z) - Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models [48.87160158792048]
We introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way.
Experiments on a public high-resolution OCT dataset show that our synthetic data have realistic high-resolution and global features, surpassing the capabilities of existing methods.
arXiv Detail & Related papers (2024-05-26T10:58:22Z) - Training Class-Imbalanced Diffusion Model Via Overlap Optimization [55.96820607533968]
Diffusion models trained on real-world datasets often yield inferior fidelity for tail classes.
Deep generative models, including diffusion models, are biased towards classes with abundant training images.
We propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
arXiv Detail & Related papers (2024-02-16T16:47:21Z) - EMIT-Diff: Enhancing Medical Image Segmentation via Text-Guided
Diffusion Model [4.057796755073023]
We develop controllable diffusion models for medical image synthesis, called EMIT-Diff.
We leverage recent diffusion probabilistic models to generate realistic and diverse synthetic medical image data.
In our approach, we ensure that the synthesized samples adhere to medically relevant constraints.
arXiv Detail & Related papers (2023-10-19T16:18:02Z) - ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic
Diffusion Models [69.9178140563928]
Colonoscopy analysis is essential for assisting clinical diagnosis and treatment.
The scarcity of annotated data limits the effectiveness and generalization of existing methods.
We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
arXiv Detail & Related papers (2023-09-03T07:55:46Z) - 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) - DiffMIC: Dual-Guidance Diffusion Network for Medical Image
Classification [32.67098520984195]
We propose the first diffusion-based model (named DiffMIC) to address general medical image classification.
Our experimental results demonstrate that DiffMIC outperforms state-of-the-art methods by a significant margin.
arXiv Detail & Related papers (2023-03-19T09:15:45Z) - Diffusion Models for Medical Image Analysis: A Comprehensive Survey [7.272308924113656]
Denoising diffusion models, a class of generative models, have garnered immense interest lately in various deep-learning problems.
Diffusion models are widely appreciated for their strong mode coverage and quality of the generated samples.
This survey intends to provide a comprehensive overview of diffusion models in the discipline of medical image analysis.
arXiv Detail & Related papers (2022-11-14T23:50:52Z) - Incremental Cross-view Mutual Distillation for Self-supervised Medical
CT Synthesis [88.39466012709205]
This paper builds a novel medical slice to increase the between-slice resolution.
Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy.
Our method outperforms state-of-the-art algorithms by clear margins.
arXiv Detail & Related papers (2021-12-20T03:38:37Z) - Decoupling Shape and Density for Liver Lesion Synthesis Using
Conditional Generative Adversarial Networks [0.0]
The quality and diversity of synthesized data are highly dependent on the annotated data used to train the models.
This paper presents a method for decoupling shape and density for liver lesion synthesis, creating a framework that allows straight-forwardly driving the synthesis.
arXiv Detail & Related papers (2021-06-01T16:45:19Z)
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.