Diffusion models in medical imaging: A comprehensive survey

Kazerouni, Amirhossein; Aghdam, Ehsan Khodapanah; Heidari, Moein; Azad, Reza; Fayyaz, Mohsen; Hacihaliloglu, Ilker; Merhof, Dorit

doi:10.1016/j.media.2023.102846

Cited by 196 publications

(35 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the recent success of diffusion models, their relevance to ultrasound has seen very limited exploration [30], [31]. Nonetheless, diffusion models for image reconstruction have been successfully applied to other modalities in the medical field, such as CT and MRI [10], [12], [32].…”

Section: Related Workmentioning

confidence: 99%

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Stevens

Chennakeshava

Bruijn

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Echocardiography has been a prominent tool for the diagnosis of cardiac disease. However, these diagnoses can be heavily impeded by poor image quality. Acoustic clutter emerges due to multipath reflections imposed by layers of skin, subcutaneous fat, and intercostal muscle between the transducer and heart. As a result, haze and other noise artifacts pose a real challenge to cardiac ultrasound imaging. In many cases, especially with difficult-to-image patients such as patients with obesity, a diagnosis from B-Mode ultrasound imaging is effectively rendered unusable, forcing sonographers to resort to contrast-enhanced ultrasound examinations or refer patients to other imaging modalities. Tissue harmonic imaging has been a popular approach to combat haze, but in severe cases is still heavily impacted by haze. Alternatively, denoising algorithms are typically unable to remove highly structured and correlated noise, such as haze. It remains a challenge to accurately describe the statistical properties of structured haze, and develop an inference method to subsequently remove it. Diffusion models have emerged as powerful generative models and have shown their effectiveness in a variety of inverse problems. In this work, we present a joint posterior sampling framework that combines two separate diffusion models to model the distribution of both clean ultrasound and haze in an unsupervised manner. Furthermore, we demonstrate techniques for effectively training diffusion models on radiofrequency ultrasound data and highlight the advantages over image data. Experiments on both in-vitro and in-vivo cardiac datasets show that the proposed dehazing method effectively removes haze while preserving signals from weakly reflected tissue.

show abstract

Section: Related Workmentioning

confidence: 99%

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Stevens

Chennakeshava

Bruijn

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…[1][2][3] Recently, diffusion models have been shown to be particularly powerful deep learning tools for CT reconstruction and restoration. [4][5][6][7][8] Such methods have generally been based on denoising diffusion probabilistic models (DDPM) 9 and score-based generative diffusion models through stochastic differential equations (SDEs). 10 Most diffusion models for CT reconstruction are trained in a supervised manner, where the conditional data input is known in both training and generation.…”

Section: Introductionmentioning

confidence: 99%

Diffusion posterior sampling for nonlinear CT reconstruction

Li,

Tivnan,

Stayman

2024

Medical Imaging 2024: Physics of Medical Imaging

View full text Add to dashboard Cite

Diffusion models have been demonstrated as powerful deep learning tools for image generation in CT reconstruction and restoration. Recently, diffusion posterior sampling, where a score-based diffusion prior is combined with a likelihood model, has been used to produce high quality CT images given low-quality measurements. This technique is attractive since it permits a one-time, unsupervised training of a CT prior; which can then be incorporated with an arbitrary data model. However, current methods only rely on a linear model of x-ray CT physics to reconstruct or restore images. While it is common to linearize the transmission tomography reconstruction problem, this is an approximation to the true and inherently nonlinear forward model. We propose a new method that solves the inverse problem of nonlinear CT image reconstruction via diffusion posterior sampling. We implement a traditional unconditional diffusion model by training a prior score function estimator, and apply Bayes rule to combine this prior with a measurement likelihood score function derived from the nonlinear physical model to arrive at a posterior score function that can be used to sample the reverse-time diffusion process. This plug-and-play method allows incorporation of a diffusion-based prior with generalized nonlinear CT image reconstruction into multiple CT system designs with different forward models, without the need for any additional training. We demonstrate the technique in both fully sampled low dose data and sparse-view geometries using a single unsupervised training of the prior.

show abstract

“…Recently, latent diffusion models have gained popularity due to their ability to produce high‐quality medical images that can be fine‐tuned by changing the denoising process, such as with text prompting. Kazerouni et al 11 have reviewed the taxonomy and uses of diffusion models in medical imaging (including denoising medical images, detecting lesions, modality translation, and increasing the size of medical image databases).…”

Section: Introductionmentioning

confidence: 99%

Accelerating the integration of ChatGPT and other large‐scale AI models into biomedical research and healthcare

Wang

Feng

et al. 2023

MedComm – Future Medicine

View full text Add to dashboard Cite

Large-scale artificial intelligence (AI) models such as ChatGPT have the potential to improve performance on many benchmarks and real-world tasks. However, it is difficult to develop and maintain these models because of their complexity and resource requirements. As a result, they are still inaccessible to healthcare industries and clinicians. This situation might soon be changed because of advancements in graphics processing unit (GPU) programming and parallel computing. More importantly, leveraging existing large-scale AIs such as GPT-4 and Med-PaLM and integrating them into multiagent models (e.g., Visual-ChatGPT) will facilitate real-world implementations. This review aims to raise awareness of the potential applications of these models in healthcare. We provide a general overview of several advanced large-scale AI models, including language models, vision-language models, graph learning models, language-conditioned multiagent models, and multimodal embodied models. We discuss their potential medical applications in addition to the challenges and future directions. Importantly, we stress the need to align these models with human values and goals, such as using reinforcement learning from human feedback, to ensure that they provide accurate and personalized insights that support human decisionmaking and improve healthcare outcomes.

show abstract

Diffusion models in medical imaging: A comprehensive survey

Cited by 196 publications

References 52 publications

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Diffusion posterior sampling for nonlinear CT reconstruction

Accelerating the integration of ChatGPT and other large‐scale AI models into biomedical research and healthcare

Contact Info

Product

Resources

About