Centromere detection of human metaphase chromosome images using a candidate based method
Bibliographic record
Abstract
Accurate detection of the human metaphase chromosome centromere is a critical element of cytogenetic diagnostic techniques, including chromosome enumeration, karyotyping and radiation biodosimetry. Existing centromere detection methods tends to perform poorly in the presence of irregular boundaries, shape variations and premature sister chromatid separation. We present a centromere detection algorithm that uses a novel contour partitioning technique to generate centromere candidates followed by a machine learning approach to select the best candidate that enhances the detection accuracy. The contour partitioning technique evaluates various combinations of salient points along the chromosome boundary using a novel feature set and is able to identify telomere regions as well as detect and correct for sister chromatid separation. This partitioning is used to generate a set of centromere candidates which are then evaluated based on a second set of proposed features. The proposed algorithm outperforms previously published algorithms and is shown to do so with a larger set of chromosome images. A highlight of the proposed algorithm is the ability to rank this set of centromere candidates and create a centromere confidence metric which may be used in post-detection analysis. When tested with a larger metaphase chromosome database consisting of 1400 chromosomes collected from 40 metaphase cell images, the proposed algorithm was able to accurately localize 1220 centromere locations yielding a detection accuracy of 87%.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".