Home › Research › Brain scans and imaging
Multi-domain synthetic medical image generation and dataset balancing with DGAN-WP-TL
Marya Ryspayeva, Olga Salykova. Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization, 2025-09-12
Topic: Brain proteins, microglia and lab models
Imbalanced medical datasets significantly impair the performance of diagnostic models by biasing predictions towards majority classes. This study introduces DGAN-WP-TL, a multi-domain generative adversarial network that integrates Wasserstein loss with gradient penalty, VGG19-based perceptual regularisation, and transfer learning to generate high-quality synthetic medical images across three modalities: BUSI ultrasound, CBIS-DDSM mammography, and Alzheimer MRI. Quantitative evaluation shows that DGAN-WP-TL achieves substantial improvements over StyleGAN2 on BUSI and Alzheimer MRI datasets, reducing KID from 0.3797 to 0.1448 and FID from 330.94 to 179.42 on BUSI, and lowering KID from 0.7097 to 0.3567 and FID from 458.74 to 289.79 on Alzheimer MRI. LPIPS (real – fake) and (fake – fake) scores indicate both enhanced perceptual realism and diversity. On CBIS-DDSM, DGAN-WP-TL surpasses StyleGAN2 in LPIPS and MS-SSIM diversity metrics, while StyleGAN2 retains slightly better KID and FID. An ablation study confirms the contribution of each architectural component, with perceptual regularisation and transfer learning yielding the most pronounced gains in realism and diversity. Downstream classification experiments using the augmented datasets demonstrate measurable performance improvement. DGAN-WP-TL offers a robust, multi-domain solution for synthetic medical data generation in low-data regimes. Future research will focus on incorporating domain-specific priors, attention-based synthesis, and clinical validation.
Key findings
- Imbalanced medical datasets significantly impair the performance of diagnostic models by biasing predictions towards majority classes.
Why it matters
This study built a method for generating fake medical images, including Alzheimer MRI scans, to balance imbalanced datasets, and it produced more realistic images than an older method on the Alzheimer MRI data. Downstream classification improved measurably when the augmented datasets were used, but this is a technical image-generation tool, not a treatment, cure or prevention for Alzheimer's disease.
New to this subject? Start with our plain-English guide: Brain scans & tests →
Study details
- Evidence strengthLow
How this study scored 32/100
Published in a peer-reviewed journal. Scored zero for study design, sample size, effect reported, studied in people and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization) |
| Journal's citation record | 0 / 4 | Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization: journal h-index 37 (OpenAlex, 2026-10-29) |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 1 / 5 | Rated “low” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 4 / 5 | 2025 — within 3 year(s) of the newest study here |
| Sample size | 0 / 4 | Participant count not stated — scores zero (not stated in the record — scored 0) |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 0 / 3 | Not stated whether this was studied in people — scores zero (not stated in the record — scored 0) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 2 / 7 | Cited 5 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 1.7 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 2 / 6 | Cited 1.9× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 1 / 4 | Cited 5 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 0 / 4 | Last-listed author Olga Salykova: h-index 3 (OpenAlex, whole career) |
| Institution's track record | 0 / 3 | Kostanay State University A Baitursynov: institution h-index 37 (OpenAlex) |
| Multi-centre collaboration | 1 / 3 | OpenAlex lists 3 institution(s) in 1 country |
| Indexed in PubMed | 1 / 2 | Not in PubMed, but has a DOI |
| Free to read | 2 / 2 | Free to read |
| Total | 32 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.1080/21681163.2025.2556687
- Original source →
- Free full text: Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.
APA 7th
Ryspayeva, M., & Salykova, O. (2025). Multi-domain synthetic medical image generation and dataset balancing with DGAN-WP-TL. Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization. https://doi.org/10.1080/21681163.2025.2556687
Vancouver
Ryspayeva M, Salykova O. Multi-domain synthetic medical image generation and dataset balancing with DGAN-WP-TL. Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization. 2025. doi:10.1080/21681163.2025.2556687.
BibTeX
@article{ryspayeva2025-fe985741,
author = {Ryspayeva, Marya and Salykova, Olga},
title = {{Multi-domain synthetic medical image generation and dataset balancing with DGAN-WP-TL}},
journal = {Computer Methods in Biomechanics and Biomedical Engineering Imaging \& Visualization},
year = {2025},
doi = {10.1080/21681163.2025.2556687},
url = {https://doi.org/10.1080/21681163.2025.2556687}
}
Related studies in Brain scans and imaging
Also in Brain scans and imaging
114 studies in the library are filed under Brain scans and imaging with no topic tag they share with another; these are this study's neighbours in a fixed tour of them. The Brain scans and imaging hub.