Deep Learning-Enhanced Diagnosis of Sow Pregnancy Through Low-Frequency Ultrasound Imaging
Animals · 23.01.2025 · 15 (3) · 318
DOI: 10.3390/ani15030318 ↗Kurz gefasst
Fachartikel in der Zeitschrift Animals, online erschienen am 23.01.2025. Verfasst von Tae-Kyeong Kim und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Science, Kangwon National University, Chuncheon 24341, Republic of Korea. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Rural Development Administration.
Abstract (Originalsprache)
The escalating demand for pork highlights the importance of swift and accurate pregnancy diagnosis in sows, a crucial factor in farm profitability. The prevalent use of low-frequency ultrasound devices in this context poses a challenge owing to the suboptimal resolution of the resultant images. This study introduces an innovative approach for sow pregnancy diagnosis using deep learning techniques to analyze low-frequency ultrasound images. Our methodology encompasses the development and comparative analysis of three distinct classification models: ViT-H, ConvNeXt-xlarge, and Xception. These models aim to improve diagnostic accuracy. AutoAugment was used to augment the data to expand the training dataset, thereby enhancing the robustness of the models under varied conditions. Results indicate a notable improvement in diagnostic performance, with the implementation of AutoAugment leading to significant achievements in the models, reflected by AUC values of 0.865, 0.856, and 0.866. These outcomes affirm the viability of deep learning in the effective management of sow pregnancies in livestock farms and suggest potential applications in broader animal husbandry contexts. This research marks a significant contribution to the evolution of agricultural technologies, presenting a scalable and efficacious solution for sow pregnancy diagnosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Data Science, Kangwon National University, Chuncheon 24341, Republic of Korea.
- Swine Science Division, National Institute of Animal Science, Rural Development Administration, Cheonan 31000, Republic of Korea.
- College of Animal Life Sciences, Kangwon National University, Chuncheon 24341, Republic of Korea.
- Department of Electronics Engineering, Interdisciplinary Graduate Program for BIT Medical Convergence, and Department of Data Science, Kangwon National University, Chuncheon 24341, Republic of Korea.
ORCID-Profile: Tae-Kyeong Kim, Yo-Han Choi, Hyun-Ju Park, Yong-Min Kim, Yong-Dae Jeong, Hyun-Chong Cho
Förderung
- National Research Foundation of Korea
- Rural Development Administration
Zitieren
APA
Kim, T. K., Choi, Y. H., Hong, J. S., Park, H. J., Kim, Y. M., Kim, J. E., Lee, J. H., Sa, S. J., Jeong, Y. D., Kim, J. S., & Cho, H. C. (2025). Deep Learning-Enhanced Diagnosis of Sow Pregnancy Through Low-Frequency Ultrasound Imaging. Animals, 15(3), 318. https://doi.org/10.3390/ani15030318
Vancouver
Kim TK, Choi YH, Hong JS, Park HJ, Kim YM, Kim JE, et al. Deep Learning-Enhanced Diagnosis of Sow Pregnancy Through Low-Frequency Ultrasound Imaging. Animals. 2025;15(3):318. doi:10.3390/ani15030318
BibTeX
@article{Kim2025,
author = {Kim, Tae-Kyeong and Choi, Yo-Han and Hong, Jun-Seon and Park, Hyun-Ju and Kim, Yong-Min and Kim, Jo-Eun and Lee, Ji-Hwan and Sa, Soo-Jin and Jeong, Yong-Dae and Kim, Jin-Soo and Cho, Hyun-Chong},
title = {Deep Learning-Enhanced Diagnosis of Sow Pregnancy Through Low-Frequency Ultrasound Imaging},
journal = {Animals},
year = {2025},
volume = {15},
number = {3},
pages = {318},
doi = {10.3390/ani15030318}
}
EUVIMED