Development of machine learning schemes for segmentation, characterisation, and evolution prediction of white matter hyperintensities in structural brain MRI
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
White matter hyperintensities (WMH) are neuroradiological features seen in T2 Fluid-Attenuated Inversion Recovery (T2-FLAIR) brain magnetic resonance imaging (MRI) and have been commonly associated with stroke, ageing, dementia, and Alzheimer’s disease (AD) progression. As a marker of neuro-degenerative disease, WMH may change over time and follow the clinical condition of the patient. In contrast to the early longitudinal studies of WMH, recent studies have suggested that the progression of WMH may be a dynamic, non-linear process where different clusters of WMH may shrink, stay unchanged, or grow. In this thesis, these changes are referred to as the “evolution of WMH”. The main objective of this thesis is to develop machine learning methods for prediction of WMH evolution in structural brain MRI from one-time (baseline) assessment. Predicting the evolution of WMH is challenging because the rate and direction of WMH evolution varies greatly across previous studies. Furthermore, the evolution of WMH is a non-deterministic problem because some clinical factors that possibly influence it are still not known. In this thesis, different learning schemes of deep learning algorithm and data modalities are proposed to produce the best estimation of WMH evolution. Furthermore, a scheme to simulate the non-deterministic nature of WMH evolution, named auxiliary input, was also proposed. In addition to the development of prediction model for WMH evolution, machine learning methods for segmentation of early WMH, characterisation of WMH, and simulation of WMH progression and regression are also developed as parts of this thesis.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it