segcsvd <sub>WMH</sub> : A convolutional neural network-based tool for quantifying white matter hyperintensities in heterogeneous patient cohorts
Bibliographic record
Abstract
Abstract White matter hyperintensities (WMH) of presumed vascular origin are an MRI-based biomarker of cerebral small vessel disease (CSVD). WMH are associated with accelerated cognitive decline and increased risk of stroke and dementia, and are commonly observed in aging, vascular cognitive impairment, Alzheimer’s and Parkinson’s disease, and related dementias. The accurate, reliable, and rapid measurement of WMH in large-scale multi-site clinical studies with heterogeneous patient populations remains challenging. The diversity of MRI protocols and image characteristics across different studies as well as the diverse nature of WMH, in terms of their highly variable shape, size, distribution, and underlying pathology, adds additional complexity to this task. Here, we present segcsvd WMH , a novel convolutional neural network-based tool for quantifying WMH. segcsvd WMH is specifically designed for accurate and robust performance when applied to diverse clinical patient datasets. Central to the development of this tool is the curation of a large patient dataset (>700 scans) sourced from seven multi-site studies, encompassing a wide range of clinical populations, WMH burden, and imaging parameters. The performance of segcsvd WMH is evaluated against three widely used WMH segmentation tools, where we demonstrate significantly enhanced accuracy and robustness across a range of challenging conditions and datasets.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".