Referee report. For: Accurate cytogenetic biodosimetry through automated dicentric chromosome curation and metaphase cell selection [version 1; referees: 1 approved]
Bibliographic record
Abstract
Accurate digital image analysis of abnormal microscopic structures relies on high quality images and on minimizing the rates of false positive (FP) and negative objects in images. Cytogenetic biodosimetry detects dicentric chromosomes (DCs) that arise from exposure to ionizing radiation, and determines radiation dose received based on DC frequency. Improvements in automated DC recognition increase the accuracy of dose estimates by reclassifying FP DCs as monocentric chromosomes or chromosome fragments. We also present image segmentation methods to rank high quality digital metaphase images and eliminate suboptimal metaphase cells. A set of chromosome morphology segmentation methods selectively filtered out FP DCs arising primarily from sister chromatid separation, chromosome fragmentation, and cellular debris. This reduced FPs by an average of 55% and was highly specific to these abnormal structures (≥97.7%) in three samples. Additional filters selectively removed images with incomplete, highly overlapped, or missing metaphase cells, or with poor overall chromosome morphologies that increased FP rates. Image selection is optimized and FP DCs are minimized by combining multiple feature based segmentation filters and a novel image sorting procedure based on the known distribution of chromosome lengths. Applying the same image segmentation filtering procedures to both calibration and test samples reduced the average dose estimation error from 0.4 Gy to <0.2 Gy, obviating the need to first manually review these images. This reliable and scalable solution enables batch processing for multiple samples of unknown dose, and meets current requirements for triage radiation biodosimetry of high quality metaphase cell preparations.
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 | 0.007 | 0.067 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.004 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.006 | 0.003 |
| Insufficient payload (model declined to judge) | 0.552 | 0.305 |
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".