85 Tibiotarsus cortical bone area: Opportunities and challenges to define novel leg health traits in purebred male turkeys (Meleagris gallopavo) using computed tomography.
Bibliographic record
Abstract
Abstract Compromised leg health is one of the prominent causes of pre-slaughter mortality and culling in meat-type poultry selected for rapid growth and heavy body weight. While poor leg health raises animal welfare concerns and can cause lameness, bone deformities and fractures, it also leads to economic losses from carcass condemnation at slaughter due to broken bone fragments in leg muscles. Thus, inclusion of leg health parameters in breeding programs is crucial to ensure a simultaneous improvement of livability and performance. Routine measurements of gait and feet defect scoring can be laborious, time intensive and fail to pinpoint in-depth information regarding the animal’s bone health. This highlights the importance of using non-invasive technology such as advanced computed tomography (CT) to phenotype individuals for novel leg health traits and accelerate breeding progress in populations. The objective of this study was to define novel leg health traits through utilization of CT scans of purebred male turkeys to explore first insights in the possibility to breed for such traits. Tibiotarsus cortical fraction (CF) was defined as the percentage of the pixel dense area (cortical bone) relative to the total number of pixels of the tibiotarsus. CF could serve as a potential indicator of bone strength and architecture. A small group of 15 purebred male turkeys were scanned at 16 weeks old and these scans were used to train and test a panoptic segmentation deep learning model implemented in a custom script using Python 3.11. Five random axial plane slices were chosen from each animal (75 slices total) and manually annotated for right (RL) and left (LL) legs using the Labelme software. The model was then trained using transfer learning techniques utilized from the Facebook AI Research’s (FAIR) library platform, Detectron 2. The training was performed using 64 annotated slices, and the 11 remaining annotated slices were used for model testing, detection, segmentation and calculation of the bone area. Preliminary results indicate an average of RL CF of 52.16%, with an average confidence level of 83%. Similarly, an average LL CF of 52.24% was observed, with an estimated confidence level of 76%. A follow-up study will include the application of deep learning models to two purebred male turkey lines with complete CT scans. The preliminary findings highlight the possibility of exploring additional novel CT-derived leg health traits, to ensure animal welfare, livability and sustainability, while increasing genetic gain in commercial turkey populations.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 | 0.000 |
| 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".