Diffusion models in medical imaging: A comprehensive survey

计算机科学 人工智能 扩散图 概率逻辑 噪音(视频) 降噪 机器学习 扩散 医学影像学 数据科学 图像(数学) 非线性降维 降维 热力学 物理
作者
Amirhossein Kazerouni,Ehsan Khodapanah Aghdam,Moein Heidari,Reza Azad,Mohsen Fayyaz,Ilker Hacihaliloglu,Dorit Merhof
出处
期刊:Medical Image Analysis [Elsevier BV]
卷期号:88: 102846-102846 被引量:1022
标识
DOI:10.1016/j.media.2023.102846
摘要

Denoising diffusion models, a class of generative models, have garnered immense interest lately in various deep-learning problems. A diffusion probabilistic model defines a forward diffusion stage where the input data is gradually perturbed over several steps by adding Gaussian noise and then learns to reverse the diffusion process to retrieve the desired noise-free data from noisy data samples. Diffusion models are widely appreciated for their strong mode coverage and quality of the generated samples in spite of their known computational burdens. Capitalizing on the advances in computer vision, the field of medical imaging has also observed a growing interest in diffusion models. With the aim of helping the researcher navigate this profusion, this survey intends to provide a comprehensive overview of diffusion models in the discipline of medical imaging. Specifically, we start with an introduction to the solid theoretical foundation and fundamental concepts behind diffusion models and the three generic diffusion modeling frameworks, namely, diffusion probabilistic models, noise-conditioned score networks, and stochastic differential equations. Then, we provide a systematic taxonomy of diffusion models in the medical domain and propose a multi-perspective categorization based on their application, imaging modality, organ of interest, and algorithms. To this end, we cover extensive applications of diffusion models in the medical domain, including image-to-image translation, reconstruction, registration, classification, segmentation, denoising, 2/3D generation, anomaly detection, and other medically-related challenges. Furthermore, we emphasize the practical use case of some selected approaches, and then we discuss the limitations of the diffusion models in the medical domain and propose several directions to fulfill the demands of this field. Finally, we gather the overviewed studies with their available open-source implementations at our GitHub.1 We aim to update the relevant latest papers within it regularly.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
1秒前
1秒前
所所的应助被卢西奥采纳,获得10
1秒前
猪猪猪发布了新的文献求助10
1秒前
Akim的应助被sunidea采纳,获得10
1秒前
1秒前
科研饭桶完成签到,获得积分10
1秒前
集力申完成签到,获得积分0
1秒前
Xsmall完成签到,获得积分10
1秒前
栖迟发布了新的文献求助10
1秒前
2秒前
白小白完成签到,获得积分10
2秒前
开心的谷菱完成签到,获得积分10
2秒前
GS草台班子的应助被邱文采纳,获得50
2秒前
脑洞疼的应助被慕许采纳,获得10
2秒前
科研不懂12完成签到,获得积分20
3秒前
合适的天完成签到,获得积分10
3秒前
科研通AI6.2的应助被大力思萱采纳,获得10
3秒前
王尹发布了新的文献求助10
3秒前
wck发布了新的文献求助10
3秒前
3秒前
3秒前
LLL完成签到,获得积分10
4秒前
寒冷的冷荷完成签到,获得积分10
4秒前
李健的小迷弟的应助被chy-wz采纳,获得10
4秒前
4秒前
小二郎的应助被acher采纳,获得10
5秒前
嗷呜发布了新的文献求助10
5秒前
5秒前
Souvenir完成签到,获得积分10
5秒前
5秒前
5秒前
szxa发布了新的文献求助10
6秒前
6秒前
6秒前
6秒前
7秒前
charlesliu116完成签到,获得积分20
7秒前
yangm9发布了新的文献求助10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8159663
求助须知:如何正确求助?哪些是违规求助? 9555211
关于积分的说明 21725494
捐赠科研通 7749713
什么是DOI,文献DOI怎么找? 3427292
关于科研通互助平台的介绍 2552372
邀请新用户注册赠送积分活动 2471628