Fully Automated, Semiautomated, and Manual Morphometric Analysis of Corneal Subbasal Nerve Plexus in Individuals With and Without Diabetes
Bibliographic record
Abstract
PURPOSE: The aim of the study was to determine the association, agreement, and detection capability of manual, semiautomated, and fully automated methods of corneal nerve fiber length (CNFL) quantification of the human corneal subbasal nerve plexus (SNP). METHODS: Thirty-three participants with diabetes and 17 healthy controls underwent laser scanning corneal confocal microscopy. Eight central images of the SNP were selected for each participant and analyzed using manual (CCMetrics), semiautomated (NeuronJ), and fully automated (ACCMetrics) software to quantify the CNFL. RESULTS: For the entire cohort, mean CNFL values quantified by CCMetrics, NeuronJ, and ACCMetrics were 17.4 ± 4.3 mm/mm, 16.0 ± 3.9 mm/mm, and 16.5 ± 3.6 mm/mm, respectively (P < 0.01). CNFL quantified using CCMetrics was significantly higher than those obtained by NeuronJ and ACCMetrics (P < 0.05). The 3 methods were highly correlated (correlation coefficients 0.87-0.98, P < 0.01). The intraclass correlation coefficients were 0.87 for ACCMetrics versus NeuronJ and 0.86 for ACCMetrics versus CCMetrics. Bland-Altman plots showed good agreement between the manual, semiautomated, and fully automated analyses of CNFL. A small underestimation of CNFL was observed using ACCMetrics with increasing the amount of nerve tissue. All 3 methods were able to detect CNFL depletion in diabetic participants (P < 0.05) and in those with peripheral neuropathy as defined by the Toronto criteria, compared with healthy controls (P < 0.05). CONCLUSIONS: Automated quantification of CNFL provides comparable neuropathy detection ability to manual and semiautomated methods. Because of its speed, objectivity, and consistency, fully automated analysis of CNFL might be advantageous in studies of diabetic neuropathy.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".