Validation of new proprietary software (r-Algo) for predicting meatchemical composition from ultrasound images of skeletal musclesin live animals: Pectoralis major muscles of broiler chickens
Bibliographic record
Abstract
The objective of this study was to validate a novel computerized method of ultrasound image analysis to determine chemical composition of pectoralis major muscles in broiler chickens.Ultrasonograms of pectoral muscles in the longitudinal and transverse planes were obtained from 40 birds just before slaughter.All chemical constituents of muscle samples were determined with the validated laboratory techniques, and the results served as a benchmark for developing the present algorithmic estimates of chicken meat composition.An inhouse developed algorithm (r-Algo) was used to normalize the ultrasonograms and to identify pixel intensity ranges for which linear correlations between mean numerical pixel values and the content of various chemical constituents were the strongest (based on the values of correlation coefficients), using a stepwise sequestration of ultrasound bitmaps.Percentages of chemical constituents were the dependent (accepted) variables and the results of echotextural analyses (luminance or pixel intensity), carried out with a commercially available image analysis software (ImageProPlus ® ), were the explanatory variables.The predictive regression equations were determined in 30 randomly selected algorithm-training experimental units, and their accuracy was tested in a subset of 10 birds allocated to the algorithm-validation group.Significant determination coefficients were found for all chemical constituents studied, with the accuracy ranging from 62.70% (linoleic acid, transverse plane, pixel range of 141-142) to 96.65% (total hypocholesterolemic acids, longitudinal plane, pixel range of 136-150).The present validation results indicate that accurate prediction of muscle chemical composition using echotextural image analyses is feasible after identifying specific pixel intensity ranges.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.006 |
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".