Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Sooyoung, Kwon, Joonwoo, Kwon, Junbeom, Min, Jungyoun Janice, Bae, Sangyoon, Lin, Yuewei, Yoo, Shinjae, Cha, Jiook
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.11277
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917040823992320
author Kim, Sooyoung
Kwon, Joonwoo
Kwon, Junbeom
Min, Jungyoun Janice
Bae, Sangyoon
Lin, Yuewei
Yoo, Shinjae
Cha, Jiook
author_facet Kim, Sooyoung
Kwon, Joonwoo
Kwon, Junbeom
Min, Jungyoun Janice
Bae, Sangyoon
Lin, Yuewei
Yoo, Shinjae
Cha, Jiook
contents The human brain is a complex system requiring both macroscopic and microscopic components for comprehensive understanding. However, mapping nonlinear relationships between these scales remains challenging due to technical limitations and the high cost of multimodal Magnetic Resonance Imaging (MRI) acquisition. To address this, we introduce Macro2Micro, a deep learning framework that predicts brain microstructure from macrostructure using a Generative Adversarial Network (GAN). Based on the hypothesis that microscale structural information can be inferred from macroscale structures, Macro2Micro explicitly encodes multiscale brain information into distinct processing branches. To enhance artifact elimination and output quality, we propose a simple yet effective auxiliary discriminator and learning objective. Extensive experiments demonstrated that Macro2Micro faithfully translates T1-weighted MRIs into corresponding Fractional Anisotropy (FA) images, achieving a 6.8\% improvement in the Structural Similarity Index Measure (SSIM) compared to previous methods, while retaining the individual biological characteristics of the brain. With an inference time of less than 0.01 seconds per MR modality translation, Macro2Micro introduces the potential for real-time multimodal rendering in medical and research applications. The code will be made available upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11277
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Macro2Micro: A Rapid and Precise Cross-modal Magnetic Resonance Imaging Synthesis using Multi-scale Structural Brain Similarity
Kim, Sooyoung
Kwon, Joonwoo
Kwon, Junbeom
Min, Jungyoun Janice
Bae, Sangyoon
Lin, Yuewei
Yoo, Shinjae
Cha, Jiook
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
The human brain is a complex system requiring both macroscopic and microscopic components for comprehensive understanding. However, mapping nonlinear relationships between these scales remains challenging due to technical limitations and the high cost of multimodal Magnetic Resonance Imaging (MRI) acquisition. To address this, we introduce Macro2Micro, a deep learning framework that predicts brain microstructure from macrostructure using a Generative Adversarial Network (GAN). Based on the hypothesis that microscale structural information can be inferred from macroscale structures, Macro2Micro explicitly encodes multiscale brain information into distinct processing branches. To enhance artifact elimination and output quality, we propose a simple yet effective auxiliary discriminator and learning objective. Extensive experiments demonstrated that Macro2Micro faithfully translates T1-weighted MRIs into corresponding Fractional Anisotropy (FA) images, achieving a 6.8\% improvement in the Structural Similarity Index Measure (SSIM) compared to previous methods, while retaining the individual biological characteristics of the brain. With an inference time of less than 0.01 seconds per MR modality translation, Macro2Micro introduces the potential for real-time multimodal rendering in medical and research applications. The code will be made available upon acceptance.
title Macro2Micro: A Rapid and Precise Cross-modal Magnetic Resonance Imaging Synthesis using Multi-scale Structural Brain Similarity
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11277