Cloud-Based Brain Magnetic Resonance Image Segmentation and Parcellation System for Individualized Prediction of Cognitive Worsening
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
For patients with cognitive disorders and dementia, accurate prognosis of cognitive worsening is critical to their ability to prepare for the future, in collaboration with health-care providers. Despite multiple efforts to apply computational brain magnetic resonance image (MRI) analysis in predicting cognitive worsening, with several successes, brain MRI is not routinely quantified in clinical settings to guide prognosis and clinical decision-making. To encourage the clinical use of a cutting-edge image segmentation method, we developed a prediction model as part of an established web-based cloud platform, MRICloud. The model was built in a training dataset from Alzheimer’s Disease Neuroimaging Initiative (ADNI) where baseline MRI scans were combined with clinical data over time. Each MRI was parcellated into 265 anatomical units based on the MRICloud fully automated image segmentation function, to measure the volume of each parcel. The Mini Mental State Examination (MMSE) was used as a measure of cognitive function. The normalized volume of 265 parcels, combined with baseline MMSE score, age, and sex were input variables for a Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis, with MMSE change in the subsequent two years as the target for prediction. A leave-one-out analysis performed on the training dataset estimated a correlation coefficient of 0.64 between true and predicted MMSE change. A receiver operating characteristic (ROC) analysis estimated a sensitivity of 0.88 and a specificity of 0.76 in predicting substantial cognitive worsening after two years, defined as MMSE decline of ≥4 points. This MRICloud prediction model was then applied to a test dataset of clinically acquired MRIs from the Johns Hopkins Memory and Alzheimer’s Treatment Center (MATC), a clinical care setting. In the latter setting, the model had both sensitivity and specificity of 1.0 in predicting substantial cognitive worsening. While the MRICloud prediction model demonstrated promise as a platform on which computational MRI findings can easily be extended to clinical use, further study with a larger number of patients is needed for validation.
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 | 0.001 | 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