Home › Research › Vascular contributions
WMH ‐ DualTasker : A Weakly Supervised Deep Learning Model for Automated White Matter Hyperintensities Segmentation and Visual Rating Prediction
Yilei Wu, Zijian Dong, Hongwei Li, Yao Feng Victor Chong, Fang Ji, Joanna Su Xian Chong, Nathanael Ren Jie Tang, Saima Hilal et al.. Human Brain Mapping, 2025-04-15
Topic: Brain proteins, microglia and lab models
White matter hyperintensities (WMH) are neuroimaging markers linked to an elevated risk of cognitive decline. WMH severity is typically assessed via visual rating scales and through volumetric segmentation. While visual rating scales are commonly used in clinical practice, they offer limited descriptive power. In contrast, supervised volumetric segmentation requires manually annotated masks, which are labor-intensive and challenging to scale for large studies. Therefore, our goal was to develop an automated deep-learning model that can provide accurate and holistic quantification of WMH severity with minimal supervision. We developed WMH-DualTasker, a deep learning model that simultaneously performs voxel-wise segmentation and visual rating score prediction. The model employs self-supervised learning with transformation-invariant consistency constraints, using WMH visual ratings (ARWMC scale, range 0-30) from clinical settings as the sole supervisory signal. Additionally, we assessed its clinical utility by applying it to identify individuals with mild cognitive impairment (MCI) and to predict dementia conversion. The volumetric quantification performance of WMH-DualTasker was either superior to or on par with existing supervised methods, as demonstrated on the MICCAI-WMH dataset (N = 60, Dice = 0.602) and the SINGER dataset (N = 64, Dice = 0.608). Furthermore, the model exhibited strong agreement with clinical visual rating scales on an external dataset (SINGER, MAE = 1.880, K = 0.77). Importantly, WMH severity metrics derived from WMH-DualTasker improved predictive performance beyond conventional clinical features for MCI classification (AUC = 0.718, p < 0.001) and MCI conversion prediction (AUC = 0.652, p < 0.001) using the ADNI dataset. WMH-DualTasker substantially reduces the reliance on labor-intensive manual annotations, facilitating more efficient and scalable quantification of WMH severity in large-scale population studies. This innovative approach has the potential to advance preventive and precision medicine by enhancing the assessment and management of vascular cognitive impairment associated with WMH.
Key findings
- The volumetric quantification performance of WMH-DualTasker was either superior to or on par with existing supervised methods, as demonstrated on the MICCAI-WMH dataset (N = 60, Dice = 0.602) and the SINGER dataset (N = 64, Dice = 0.608).
- This innovative approach has the potential to advance preventive and precision medicine by enhancing the assessment and management of vascular cognitive impairment associated with WMH.
Why it matters
This study describes a deep learning model that automatically measures white matter hyperintensity severity from brain scans using visual ratings as the only supervisory signal. The authors say this approach has the potential to advance preventive and precision medicine by improving assessment of vascular cognitive impairment, but it is a tool for measurement rather than a treatment or cure.
Study details
- Participants60
- Effect sizeAUC = 0.718; AUC = 0.652
- Evidence strengthLow
How this study scored 48/100
Published in a peer-reviewed journal. Scored zero for study design and randomised / blinded because the record does not state it. We have no data on senior author's track record, so that was left out: it earned 46 of the 96 points we could judge it on, which is 48 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Human Brain Mapping) |
| Journal's citation record | 3 / 4 | Human Brain Mapping: journal h-index 271 (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 | 1 / 4 | 60 participants |
| Effect reported | 3 / 3 | Effect reported with a statistic (interval, p-value, ratio or similar) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 1 / 7 | Cited 4 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 1.3 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 2 / 6 | Cited 1.5× 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 4 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | — / 4 | Senior author's record not available — left out of this score |
| Institution's track record | 3 / 3 | Harvard University: institution h-index 3,235 (OpenAlex) |
| Multi-centre collaboration | 2 / 3 | OpenAlex lists 8 institution(s) in 2 countries |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 40260707) |
| Free to read | 2 / 2 | Free to read |
| Points | 46 / 96 | Scored on 19 of 20 parts. We have no data for the rest, so they are left out: 46 of the 96 points we could judge it on is 48 out of 100. |
| Total | 48 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
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. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
APA 7th
Wu, Y., Dong, Z., Li, H., Chong, Y. F. V., Ji, F., Chong, J. S. X., et al. (2025). WMH ‐ DualTasker : A Weakly Supervised Deep Learning Model for Automated White Matter Hyperintensities Segmentation and Visual Rating Prediction. Human Brain Mapping. https://doi.org/10.1002/hbm.70212
Vancouver
Wu Y, Dong Z, Li H, Chong YFV, Ji F, Chong JSX, et al. WMH ‐ DualTasker : A Weakly Supervised Deep Learning Model for Automated White Matter Hyperintensities Segmentation and Visual Rating Prediction. Human Brain Mapping. 2025. doi:10.1002/hbm.70212. PMID: 40260707.
BibTeX
@article{wu2025-40260707,
author = {Wu, Yilei and Dong, Zijian and Li, Hongwei and Chong, Yao Feng Victor and Ji, Fang and Chong, Joanna Su Xian and Tang, Nathanael Ren Jie and Hilal, Saima and others},
title = {{WMH ‐ DualTasker : A Weakly Supervised Deep Learning Model for Automated White Matter Hyperintensities Segmentation and Visual Rating Prediction}},
journal = {Human Brain Mapping},
year = {2025},
doi = {10.1002/hbm.70212},
pmid = {40260707},
url = {https://doi.org/10.1002/hbm.70212}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Related studies in Vascular contributions
Also tagged “cerebral”
900 studies in the library carry the topic tag “cerebral”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 900 tagged studies.