Automated chick gender determination using optical coherence tomography and deep learning

Chick gender classification is crucial for optimizing poultry production, yet traditional methods such as vent sexing and ultrasound remain limited by human expertise, labor intensity, and insufficient resolution. This study introduces a novel approach that integrates Optical Coherence Tomography (O...

Full description

Saved in:
Bibliographic Details
Main Authors: Jadsada Saetiew, Papawit Nongkhunsan, Jiraporn Saenjae, Rapeephat Yodsungnoen, Amonrat Molee, Sirichok Jungthawan, Ittipon Fongkaew, Panomsak Meemon
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Poultry Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S003257912500272X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850272655323693056
author Jadsada Saetiew
Papawit Nongkhunsan
Jiraporn Saenjae
Rapeephat Yodsungnoen
Amonrat Molee
Sirichok Jungthawan
Ittipon Fongkaew
Panomsak Meemon
author_facet Jadsada Saetiew
Papawit Nongkhunsan
Jiraporn Saenjae
Rapeephat Yodsungnoen
Amonrat Molee
Sirichok Jungthawan
Ittipon Fongkaew
Panomsak Meemon
author_sort Jadsada Saetiew
collection DOAJ
description Chick gender classification is crucial for optimizing poultry production, yet traditional methods such as vent sexing and ultrasound remain limited by human expertise, labor intensity, and insufficient resolution. This study introduces a novel approach that integrates Optical Coherence Tomography (OCT) and deep learning to enable high-resolution, non-invasive chick sexing. Unlike conventional imaging techniques, OCT provides micrometer-scale visualization of cloacal structures, allowing precise differentiation between male and female chicks based on internal anatomical markers. We developed a custom convolutional neural network (CNN) optimized for OCT data, incorporating asymmetric image resizing and enhanced feature extraction to improve classification accuracy. Our model achieved 79 % accuracy, outperforming conventional architectures such as Inception (63 %) and VGG-16 (74 %), highlighting the importance of a tailored, domain-specific model. This is the first study to integrate OCT with deep learning for automated chick sexing, demonstrating a scalable, real-time alternative to expert-dependent vent sexing. With further advancements in imaging and machine learning, our approach has the potential to transform chick sexing in commercial hatcheries, reducing reliance on skilled labor while enhancing classification efficiency and precision.
format Article
id doaj-art-1ba6e2a51c76455f97a4b610b1fdf548
institution OA Journals
issn 0032-5791
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Poultry Science
spelling doaj-art-1ba6e2a51c76455f97a4b610b1fdf5482025-08-20T01:51:44ZengElsevierPoultry Science0032-57912025-05-01104510503310.1016/j.psj.2025.105033Automated chick gender determination using optical coherence tomography and deep learningJadsada Saetiew0Papawit Nongkhunsan1Jiraporn Saenjae2Rapeephat Yodsungnoen3Amonrat Molee4Sirichok Jungthawan5Ittipon Fongkaew6Panomsak Meemon7School of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Integrated Science and Innovation, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Animal Technology and Innovation, Institute of Agricultural, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, ThailandSchool of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Muang, Nakhon ratchasima 30000, Thailand; Corresponding author.Chick gender classification is crucial for optimizing poultry production, yet traditional methods such as vent sexing and ultrasound remain limited by human expertise, labor intensity, and insufficient resolution. This study introduces a novel approach that integrates Optical Coherence Tomography (OCT) and deep learning to enable high-resolution, non-invasive chick sexing. Unlike conventional imaging techniques, OCT provides micrometer-scale visualization of cloacal structures, allowing precise differentiation between male and female chicks based on internal anatomical markers. We developed a custom convolutional neural network (CNN) optimized for OCT data, incorporating asymmetric image resizing and enhanced feature extraction to improve classification accuracy. Our model achieved 79 % accuracy, outperforming conventional architectures such as Inception (63 %) and VGG-16 (74 %), highlighting the importance of a tailored, domain-specific model. This is the first study to integrate OCT with deep learning for automated chick sexing, demonstrating a scalable, real-time alternative to expert-dependent vent sexing. With further advancements in imaging and machine learning, our approach has the potential to transform chick sexing in commercial hatcheries, reducing reliance on skilled labor while enhancing classification efficiency and precision.http://www.sciencedirect.com/science/article/pii/S003257912500272XChick gender classificationVent sexingOptical coherence tomographyDeep learningMachine learning
spellingShingle Jadsada Saetiew
Papawit Nongkhunsan
Jiraporn Saenjae
Rapeephat Yodsungnoen
Amonrat Molee
Sirichok Jungthawan
Ittipon Fongkaew
Panomsak Meemon
Automated chick gender determination using optical coherence tomography and deep learning
Poultry Science
Chick gender classification
Vent sexing
Optical coherence tomography
Deep learning
Machine learning
title Automated chick gender determination using optical coherence tomography and deep learning
title_full Automated chick gender determination using optical coherence tomography and deep learning
title_fullStr Automated chick gender determination using optical coherence tomography and deep learning
title_full_unstemmed Automated chick gender determination using optical coherence tomography and deep learning
title_short Automated chick gender determination using optical coherence tomography and deep learning
title_sort automated chick gender determination using optical coherence tomography and deep learning
topic Chick gender classification
Vent sexing
Optical coherence tomography
Deep learning
Machine learning
url http://www.sciencedirect.com/science/article/pii/S003257912500272X
work_keys_str_mv AT jadsadasaetiew automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT papawitnongkhunsan automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT jirapornsaenjae automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT rapeephatyodsungnoen automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT amonratmolee automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT sirichokjungthawan automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT ittiponfongkaew automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning
AT panomsakmeemon automatedchickgenderdeterminationusingopticalcoherencetomographyanddeeplearning