Modality-Agnostic Style Transfer for Holistic Feature Imputation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917946252591104 |
|---|---|
| author | Baek, Seunghun Sim, Jaeyoon Dere, Mustafa Kim, Minjeong Wu, Guorong Kim, Won Hwa |
| author_facet | Baek, Seunghun Sim, Jaeyoon Dere, Mustafa Kim, Minjeong Wu, Guorong Kim, Won Hwa |
| contents | Characterizing a preclinical stage of Alzheimer's Disease (AD) via single imaging is difficult as its early symptoms are quite subtle. Therefore, many neuroimaging studies are curated with various imaging modalities, e.g., MRI and PET, however, it is often challenging to acquire all of them from all subjects and missing data become inevitable. In this regards, in this paper, we propose a framework that generates unobserved imaging measures for specific subjects using their existing measures, thereby reducing the need for additional examinations. Our framework transfers modality-specific style while preserving AD-specific content. This is done by domain adversarial training that preserves modality-agnostic but AD-specific information, while a generative adversarial network adds an indistinguishable modality-specific style. Our proposed framework is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) study and compared with other imputation methods in terms of generated data quality. Small average Cohen's $d$ $< 0.19$ between our generated measures and real ones suggests that the synthetic data are practically usable regardless of their modality type. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02898 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modality-Agnostic Style Transfer for Holistic Feature Imputation Baek, Seunghun Sim, Jaeyoon Dere, Mustafa Kim, Minjeong Wu, Guorong Kim, Won Hwa Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Characterizing a preclinical stage of Alzheimer's Disease (AD) via single imaging is difficult as its early symptoms are quite subtle. Therefore, many neuroimaging studies are curated with various imaging modalities, e.g., MRI and PET, however, it is often challenging to acquire all of them from all subjects and missing data become inevitable. In this regards, in this paper, we propose a framework that generates unobserved imaging measures for specific subjects using their existing measures, thereby reducing the need for additional examinations. Our framework transfers modality-specific style while preserving AD-specific content. This is done by domain adversarial training that preserves modality-agnostic but AD-specific information, while a generative adversarial network adds an indistinguishable modality-specific style. Our proposed framework is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) study and compared with other imputation methods in terms of generated data quality. Small average Cohen's $d$ $< 0.19$ between our generated measures and real ones suggests that the synthetic data are practically usable regardless of their modality type. |
| title | Modality-Agnostic Style Transfer for Holistic Feature Imputation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.02898 |