Abscess detection on bovine livers with a commercial smart imaging system
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Meat processors are responsible for ensuring that animal carcasses are fit for human consumption [1]. Trained meat <br/>inspectors play a crucial role in quality control, identifying and condemning unhealthy tissue, with this process occurring <br/>at line speed. Whilst optimized for reporting of disease conditions for quality assurance processes, the time and tools <br/>currently available to inspectors, or other on-floor staff, restricts the depth of information able to be recorded due to rapid <br/>chain speeds. Impacts to the supply chain due to downgraded product can be significant. For example, abscessed <br/>condemned at around 3% of beef cattle slaughtered [2]. Line speed automated disease assessment therefore offers a <br/>promising layer of objective data for defect capture and producer feedback.Currently, Smart Imaging Systems (SIS) are <br/>used in processing plants for foreign object detection, quality assurance and quality control of meat products. One imaging <br/>modality, hyperspectral cameras, capture light reflected from the meat product, across multiple wavelengths in near <br/>infrared to visible ranges with this data being utilized via Machine learning models to identify multiple visual and <br/>biochemical tissue characteristics [3]. Current in-plant hyperspectral imaging systems include the composition analysis of <br/>meat cuts and control of foreign materials [4]. Automated assessment for abscesses and other offal health conditions, <br/>using imaging systems such as hyperspectral analysis, could therefore expand offal inspection with objective data. To <br/>investigate this, the development of hyperspectral disease detection models using commercially available smart imaging <br/>system was investigated.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| 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 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it