Deep learning-based diffusion tensor image generation model: a proof-of-concept study
Abstract This study created an image-to-image translation model that synthesizes diffusion tensor images (DTI) from conventional diffusion weighted images, and validated the similarities between the original and synthetic DTI. Thirty-two healthy volunteers were prospectively recruited. DTI and DWI w...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-02-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-53278-8 |
_version_ | 1797274803752665088 |
---|---|
author | Hiroyuki Tatekawa Daiju Ueda Hirotaka Takita Toshimasa Matsumoto Shannon L. Walston Yasuhito Mitsuyama Daisuke Horiuchi Shu Matsushita Tatsushi Oura Yuichiro Tomita Taro Tsukamoto Taro Shimono Yukio Miki |
author_facet | Hiroyuki Tatekawa Daiju Ueda Hirotaka Takita Toshimasa Matsumoto Shannon L. Walston Yasuhito Mitsuyama Daisuke Horiuchi Shu Matsushita Tatsushi Oura Yuichiro Tomita Taro Tsukamoto Taro Shimono Yukio Miki |
author_sort | Hiroyuki Tatekawa |
collection | DOAJ |
description | Abstract This study created an image-to-image translation model that synthesizes diffusion tensor images (DTI) from conventional diffusion weighted images, and validated the similarities between the original and synthetic DTI. Thirty-two healthy volunteers were prospectively recruited. DTI and DWI were obtained with six and three directions of the motion probing gradient (MPG), respectively. The identical imaging plane was paired for the image-to-image translation model that synthesized one direction of the MPG from DWI. This process was repeated six times in the respective MPG directions. Regions of interest (ROIs) in the lentiform nucleus, thalamus, posterior limb of the internal capsule, posterior thalamic radiation, and splenium of the corpus callosum were created and applied to maps derived from the original and synthetic DTI. The mean values and signal-to-noise ratio (SNR) of the original and synthetic maps for each ROI were compared. The Bland–Altman plot between the original and synthetic data was evaluated. Although the test dataset showed a larger standard deviation of all values and lower SNR in the synthetic data than in the original data, the Bland–Altman plots showed each plot localizing in a similar distribution. Synthetic DTI could be generated from conventional DWI with an image-to-image translation model. |
first_indexed | 2024-03-07T15:03:15Z |
format | Article |
id | doaj.art-4da435912f7f4c0db47e7a5274940872 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-07T15:03:15Z |
publishDate | 2024-02-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-4da435912f7f4c0db47e7a52749408722024-03-05T19:00:36ZengNature PortfolioScientific Reports2045-23222024-02-011411710.1038/s41598-024-53278-8Deep learning-based diffusion tensor image generation model: a proof-of-concept studyHiroyuki Tatekawa0Daiju Ueda1Hirotaka Takita2Toshimasa Matsumoto3Shannon L. Walston4Yasuhito Mitsuyama5Daisuke Horiuchi6Shu Matsushita7Tatsushi Oura8Yuichiro Tomita9Taro Tsukamoto10Taro Shimono11Yukio Miki12Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan UniversityAbstract This study created an image-to-image translation model that synthesizes diffusion tensor images (DTI) from conventional diffusion weighted images, and validated the similarities between the original and synthetic DTI. Thirty-two healthy volunteers were prospectively recruited. DTI and DWI were obtained with six and three directions of the motion probing gradient (MPG), respectively. The identical imaging plane was paired for the image-to-image translation model that synthesized one direction of the MPG from DWI. This process was repeated six times in the respective MPG directions. Regions of interest (ROIs) in the lentiform nucleus, thalamus, posterior limb of the internal capsule, posterior thalamic radiation, and splenium of the corpus callosum were created and applied to maps derived from the original and synthetic DTI. The mean values and signal-to-noise ratio (SNR) of the original and synthetic maps for each ROI were compared. The Bland–Altman plot between the original and synthetic data was evaluated. Although the test dataset showed a larger standard deviation of all values and lower SNR in the synthetic data than in the original data, the Bland–Altman plots showed each plot localizing in a similar distribution. Synthetic DTI could be generated from conventional DWI with an image-to-image translation model.https://doi.org/10.1038/s41598-024-53278-8 |
spellingShingle | Hiroyuki Tatekawa Daiju Ueda Hirotaka Takita Toshimasa Matsumoto Shannon L. Walston Yasuhito Mitsuyama Daisuke Horiuchi Shu Matsushita Tatsushi Oura Yuichiro Tomita Taro Tsukamoto Taro Shimono Yukio Miki Deep learning-based diffusion tensor image generation model: a proof-of-concept study Scientific Reports |
title | Deep learning-based diffusion tensor image generation model: a proof-of-concept study |
title_full | Deep learning-based diffusion tensor image generation model: a proof-of-concept study |
title_fullStr | Deep learning-based diffusion tensor image generation model: a proof-of-concept study |
title_full_unstemmed | Deep learning-based diffusion tensor image generation model: a proof-of-concept study |
title_short | Deep learning-based diffusion tensor image generation model: a proof-of-concept study |
title_sort | deep learning based diffusion tensor image generation model a proof of concept study |
url | https://doi.org/10.1038/s41598-024-53278-8 |
work_keys_str_mv | AT hiroyukitatekawa deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT daijuueda deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT hirotakatakita deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT toshimasamatsumoto deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT shannonlwalston deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT yasuhitomitsuyama deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT daisukehoriuchi deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT shumatsushita deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT tatsushioura deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT yuichirotomita deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT tarotsukamoto deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT taroshimono deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy AT yukiomiki deeplearningbaseddiffusiontensorimagegenerationmodelaproofofconceptstudy |