Automated Morphological Grading of Human Blastocysts From Multi-Focus Images
Bibliographic record
Abstract
This paper reports, for the first time, automated grading of human blastocysts (day-5 embryos) from multi-focus images. Based on a novel attention module, a convolutional neural network (CNN) was developed to predict the morphological grade of a blastocyst. The attention module integrates high-level features extracted from the blastocyst’s multi-focus images. Experimental results revealed that multi-focus blastocyst images help improve the grading accuracies than a single blastocyst image. Comparisons of the accuracy achieved by the model and the average accuracy of five embryologists demonstrated that the proposed model can outperform embryologists in the morphological grading of blastocysts (88% versus 86% for development stage prediction, 83% versus 79% for inner cell mass grade prediction, 89% versus 82% for trophectoderm grade prediction).Note to Practitioners—This work was motivated by the subjectivity and significant intra-and inter-evaluator variations in manual morphological grading of blastocysts. Existing approaches to automate the grading process mainly use a single blastocyst image although multi-focus images captured at different focal planes reveal more morphological features of a blastocyst than a single blastocyst image. This paper describes a new CNN-based method using multi-focus images to improve the grading accuracy. The accuracy of the proposed method was verified on multi-focus images of human blastocysts captured by a standard time-lapse incubator at fixed focal depths ($-$45$\mu$m,$-$30$\mu$m,$-$15$\mu$m, 0$\mu$m, 15$\mu$m, 30$\mu$m, 45$\mu$m).
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".