Next Article in Journal
Data-Driven Identification of Crane Dynamics Using Regularized Genetic Programming
Next Article in Special Issue
Synthetic Medical Imaging Generation with Generative Adversarial Networks for Plain Radiographs
Previous Article in Journal
Design of Series-Fed Circularly Polarized Beam-Tilted Antenna for Microwave Power Transmission in UAV Application
Previous Article in Special Issue
Enhancing Acute Bilirubin Encephalopathy Diagnosis with Multi-Modal MRI: A Deep Learning Approach
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 14
Issue 8
10.3390/app14083489
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Practical Medical Image Generation with Provable Privacy Protection Based on Denoising Diffusion Probabilistic Models for High-Resolution Volumetric Images

by
Hisaichi Shibata
1,*,
Shouhei Hanaoka
1,
Takahiro Nakao
2,
Tomohiro Kikuchi
2,3,
Yuta Nakamura
2,
Yukihiro Nomura
2,4,
Takeharu Yoshikawa
2 and
Osamu Abe
1
1
Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo, Tokyo 113-8655, Japan
2
Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo, Tokyo 113-8655, Japan
3
Department of Radiology, School of Medicine, Jichi Medical University, 3311-1 Yakushiji, Shimotsuke, Tochigi 329-0498, Japan
4
Center for Frontier Medical Engineering, Chiba University, 1-33 Yayoi-cho, Inage, Chiba 263-8522, Japan
*
Author to whom correspondence should be addressed.
Appl. Sci. 2024, 14(8), 3489; https://doi.org/10.3390/app14083489
Submission received: 19 March 2024 / Revised: 19 April 2024 / Accepted: 19 April 2024 / Published: 20 April 2024
(This article belongs to the Special Issue Artificial Intelligence in Biomedical Image Processing)
Browse Figures
Versions Notes

Abstract

Local differential privacy algorithms combined with deep generative models can enhance secure medical image sharing among researchers in the public domain without central administrators; however, these images were limited to the generation of low-resolution images, which are very insufficient for diagnosis by medical doctors. To enhance the performance of deep generative models so that they can generate high-resolution medical images, we propose a large-scale diffusion model that can, for the first time, unconditionally generate high-resolution (256×256×256) volumetric medical images (head magnetic resonance images). This diffusion model has 19 billion parameters, but to make it easy to train it, we temporally divided the model into 200 submodels, each of which has 95 million parameters. Moreover, on the basis of this new diffusion model, we propose another formulation of image anonymization with which the processed images can satisfy provable Gaussian local differential privacy and with which we can generate images semantically different from the original image but belonging to the same class. We believe that the formulation of this new diffusion model and the implementation of local differential privacy algorithms combined with the diffusion models can contribute to the secure sharing of practical images upstream of data processing.
Keywords: deep generative models; denoising; differential privacy; diffusion models; head magnetic resonance images deep generative models; denoising; differential privacy; diffusion models; head magnetic resonance images

Share and Cite

MDPI and ACS Style

Shibata, H.; Hanaoka, S.; Nakao, T.; Kikuchi, T.; Nakamura, Y.; Nomura, Y.; Yoshikawa, T.; Abe, O. Practical Medical Image Generation with Provable Privacy Protection Based on Denoising Diffusion Probabilistic Models for High-Resolution Volumetric Images. Appl. Sci. 2024, 14, 3489. https://doi.org/10.3390/app14083489

AMA Style

Shibata H, Hanaoka S, Nakao T, Kikuchi T, Nakamura Y, Nomura Y, Yoshikawa T, Abe O. Practical Medical Image Generation with Provable Privacy Protection Based on Denoising Diffusion Probabilistic Models for High-Resolution Volumetric Images. Applied Sciences. 2024; 14(8):3489. https://doi.org/10.3390/app14083489

Chicago/Turabian Style

Shibata, Hisaichi, Shouhei Hanaoka, Takahiro Nakao, Tomohiro Kikuchi, Yuta Nakamura, Yukihiro Nomura, Takeharu Yoshikawa, and Osamu Abe. 2024. "Practical Medical Image Generation with Provable Privacy Protection Based on Denoising Diffusion Probabilistic Models for High-Resolution Volumetric Images" Applied Sciences 14, no. 8: 3489. https://doi.org/10.3390/app14083489

APA Style

Shibata, H., Hanaoka, S., Nakao, T., Kikuchi, T., Nakamura, Y., Nomura, Y., Yoshikawa, T., & Abe, O. (2024). Practical Medical Image Generation with Provable Privacy Protection Based on Denoising Diffusion Probabilistic Models for High-Resolution Volumetric Images. Applied Sciences, 14(8), 3489. https://doi.org/10.3390/app14083489

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop