Enhancing Dementia Imaging in Low‐and‐Middle Income Countries Through Training of Skilled MRI Personnel
Bibliographic record
Abstract
BACKGROUND: In tandem with the ever-increasing aging population in low- and middle- income countries (LMICs), the burden of dementia is rising across LMICs. Magnetic resonance imaging (MRI) is essential in diagnosis to evaluate different dementia subtypes. However, most LMICs have limited access to MRI and lack trained MRI personnel to make accurate diagnoses. Here, we provide update on the Scan With Me (SWiM) training program [1] aimed at upskilling MRI radiographers from LMICs to optimize MRI acquisition on their limited infrastructure and produce high-quality images including advanced dementia MRI techniques. METHOD: SWiM is a free train-the-trainer capacity-building initiative of the Consortium for Advancement of MRI Education and Research in Africa (CAMERA). SWiM implements RAD-AID's Teach-Try-Use strategy, which combines virtual learning resources, live expert case-based lectures, and hands-on vendor-led practical scanning sessions to train a team of radiographers who work together as a network to enhance their skills and collectively train others [2]. The curriculum (Figure 1) guides participants from basic to advanced brain imaging over 8 weeks. Two cases of patients with dementia, simulated from LMIC published case reports were used for as capstone projects. This guided participants to develop brain imaging protocols tailored from standards (e.g., ADNI) and optimized on their scanners for dementia imaging. RESULT: The second program ran from August to September 2024, with special focus on dementia imaging and hands-on imaging sessions at 5 clinics in Kenya and Nigeria, and one trainer site in Chile. 96 radiographers from 29 imaging facilities in 18 LMIC countries received 70 hours of specialized training, observerships, and peer-to-peer engagements (Figure 2). Basic to advanced MRI techniques adapted from ADNI were acquired from the two African sites using optimized protocols (Figure 3). The LMIC-optimized scan protocols from participants are being curated and will be shared openly on protocols.io for others to use. CONCLUSION: SWiM aims to establish a collaborative network of experts in imaging centers in LMICs, enabling them to collect robust datasets that can inform clinical care and support the development of imaging tools for advancing prevention and treatment strategies. [1] event.fourwaves.com/swim [2] Mumuni AN, et al.,. J Am Coll Radiol. 2024 21(8):1222-1234.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.004 |
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".