Computer-Based Image Analysis for Plus Disease Diagnosis in Retinopathy of Prematurity
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
Presence of plus disease in retinopathy of prematurity (ROP) is an important criterion for identifying ROP requiring treatment. Plus disease is defined by a standard published photograph selected more than 20 years ago by expert consensus. However, diagnosis of plus disease has been shown to be subjective and qualitative. Computer-based image analysis using quantitative methods has potential to improve the objectivity of plus disease diagnosis. The objective was to review the published literature involving computer-based image analysis for ROP diagnosis. The PubMed and Cochrane library databases were searched for the keywords "retinopathy of prematurity" AND "image analysis" AND/OR "plus disease." Reference lists of retrieved articles were searched to identify additional relevant studies. All relevant English-language studies were reviewed. There are four main computer-based systems-ROPtool (area under the receiver operating characteristic curve [AUROC], plus tortuosity 0.95, plus dilation 0.87), RISA (AUROC, arteriolar TI 0.71, venular diameter 0.82), Vessel Map (AUROC, arteriolar dilation 0.75, venular dilation 0.96), and CAIAR (AUROC, arteriole tortuosity 0.92, venular dilation 0.91)-attempting to objectively analyze vessel tortuosity and dilation in plus disease in ROP. Some show promise for identification of plus disease using quantitative methods. This has potential to improve the diagnosis of plus disease and may contribute to the management of ROP using both traditional binocular indirect ophthalmoscopy and image-based telemedicine approaches.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.008 | 0.004 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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