In vivo estimation of chicken breast and thigh muscle weights using multi-atlas-based elastic registration on computed tomography images DOI
Ádám Csóka, Shelley Simon,

Tamás Péter Farkas

et al.

British Poultry Science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 7

Published: March 21, 2025

1. This study employed an automated estimation method for quantitatively assessing valuable meat parts in broiler chickens. involved the segmentation of computed tomography (CT) images through elastic registration, utilising feature and model selection.2. Sixty Tetra HB colour chickens (30 males 30 females) were randomly selected examined by CT at 10 weeks age (live weight: 2560 ± 400 g). The animals slaughtered, their breast thigh muscles dissected weighed (thigh weights 90 19 g 337 58 Multi-atlas registration was used segmentation, followed extraction (256 features/individual) from images.3. Four different regression analysis techniques (linear, PLS, lasso ridge) with without selection applied to collected data k-fold cross-validation estimating muscle weights. produced significantly better results all cases.4. Among techniques, ridge performed best both groups muscles). These as follows: breast: r2 = 0.993, RMSE 4.87 g; 0.995, 4.03 thigh: 0.976, 2.94 0.965, 3.53 g.5. demonstrated effectiveness method, initially tested on rabbits, accurately robust performance models underscores potential widespread application poultry production, offering a reliable efficient means quantitative assessment.

Language: Английский

Weight prediction method for individual live chickens based on single-view point cloud information DOI
Haikun Zheng, Chuang Ma, Dong Liu

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 234, P. 110232 - 110232

Published: March 8, 2025

Language: Английский

Citations

0
In vivo estimation of chicken breast and thigh muscle weights using multi-atlas-based elastic registration on computed tomography images DOI
Ádám Csóka, Shelley Simon,

Tamás Péter Farkas

et al.

British Poultry Science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 7

Published: March 21, 2025

1. This study employed an automated estimation method for quantitatively assessing valuable meat parts in broiler chickens. involved the segmentation of computed tomography (CT) images through elastic registration, utilising feature and model selection.2. Sixty Tetra HB colour chickens (30 males 30 females) were randomly selected examined by CT at 10 weeks age (live weight: 2560 ± 400 g). The animals slaughtered, their breast thigh muscles dissected weighed (thigh weights 90 19 g 337 58 Multi-atlas registration was used segmentation, followed extraction (256 features/individual) from images.3. Four different regression analysis techniques (linear, PLS, lasso ridge) with without selection applied to collected data k-fold cross-validation estimating muscle weights. produced significantly better results all cases.4. Among techniques, ridge performed best both groups muscles). These as follows: breast: r2 = 0.993, RMSE 4.87 g; 0.995, 4.03 thigh: 0.976, 2.94 0.965, 3.53 g.5. demonstrated effectiveness method, initially tested on rabbits, accurately robust performance models underscores potential widespread application poultry production, offering a reliable efficient means quantitative assessment.

Language: Английский

Citations

0