L-former: a lightweight transformer for realistic medical image generation and its application to super-resolution

Tong Zheng; Hirohisa Oda; Yuichiro Hayashi; Shota Nakamura; Masaki Mori; Hirotsugu Takabatake; Hiroshi Natori; Masahiro Oda; Kensaku Mori

doi:10.1117/12.2653776

3 April 2023 L-former: a lightweight transformer for realistic medical image generation and its application to super-resolution

Tong Zheng, Hirohisa Oda, Yuichiro Hayashi, Shota Nakamura, Masaki Mori, Hirotsugu Takabatake, Hiroshi Natori, Masahiro Oda, Kensaku Mori

Author Affiliations +

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 1246415 (2023) https://doi.org/10.1117/12.2653776
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Abstract

Medical image analysis approaches such as data augmentation and domain adaption need huge amounts of realistic medical images. Generating realistic medical images by machine learning is a feasible approach. We propose L-former, a lightweight Transformer for realistic medical image generation. L-former can generate more reliable and realistic medical images than recent generative adversarial networks (GANs). Meanwhile, L-former does not consume as high computational cost as conventional Transformer-based generative models. L-former uses Transformers to generate low-resolution feature vectors at shallow layers, and uses convolutional neural networks to generate high-resolution realistic medical images at deep layers. Experimental results showed that L-former outperformed conventional GANs by FID scores 33.79 and 76.85 on two datasets, respectively. We further conducted a downstream study by using the images generated by L-former to perform a super-resolution task. A high PSNR score of 27.87 proved L-former’s ability to generate reliable images for super-resolution and showed its potential for applications in medical diagnosis.

Conference Presentation

Citation Download Citation

Tong Zheng, Hirohisa Oda, Yuichiro Hayashi, Shota Nakamura, Masaki Mori, Hirotsugu Takabatake, Hiroshi Natori, Masahiro Oda, and Kensaku Mori "L-former: a lightweight transformer for realistic medical image generation and its application to super-resolution", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 1246415 (3 April 2023); https://doi.org/10.1117/12.2653776

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available