Pregnancy diagnosis in sows: enzyme immuno assay measurement of oestrone sulphate in plasma on day 25–30 after insemination in comparison to ultrasound scanning on day 28

Wiel, D.F.M. van de; Vos, E.A.; Brake, J.H.A. Te; Lende, T. van der

doi:10.1016/0301-6226(92)90003-m

Cited by 8 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results support the potential of a generalized use of the model in various farm conditions and ultimately its employment in machine learning for an automated prediction of litter size as a routine on-farm procedure [ 9 , 17 ]. The usefulness of such a prediction is highlighted by various researchers using RTU technology for counting the gestated litters in other species [ 10 , 11 , 12 , 13 ], or by measuring oestrone sulphate blood levels in sows [ 14 , 15 ]. However, the large litters in pigs are difficult to predict accurately by counting with ultrasonography, and the use of RTU for determining the potential numbers of piglets in a litter is not advised [ 27 ].…”

Section: Discussionmentioning

confidence: 99%

“…Estimation of the expected litter size by the thorough examination of transabdominal or transrectal RTU imagingwas studied in species such as the snowshoe hare, the dog, as well as sheep and goats [ 10 , 11 , 12 , 13 ]. In the pig, research on the prediction of litter size focuses on measuring maternal oestrone sulphate blood levels [ 14 , 15 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of a Numerical, Real-Time Ultrasound Imaging Model for the Prediction of Litter Size in Pregnant Sows, with Machine Learning

Kousenidis

Kirtsanis

Karageorgiou

et al. 2022

Animals

View full text Add to dashboard Cite

The present study aimed to evaluate the accuracy of a numerical model, quantifying real-time ultrasonographic (RTU) images of pregnant sows, to predict litter size. The time of the test with the least error was also considered. A number of 4165 pregnancies in Farm 1 and 438 in Farm 2 were diagnosed twice, with the quality of the RTU images translated into rated-scale values (RSV1 and RSV2). When a deep neural network (DNN) was trained, the evaluation of the method showed that the prediction of litter size can be performed with little error. Root square mean error (RMSE) for training, validation with data from Farm 1, and testing on the data from Farm 2 were 0.91, 0.97, and 1.05, respectively. Corresponding mean absolute errors (MAE) were 2.27, 2.41, and 2.58. Time appeared to be a critical factor for the accuracy of the model. The smallest MAE was achieved when the RTU was performed at days 20–22. It is concluded that a numerical, RTU imaging model is a prominent predictor of litter size, when a DNN is used. Therefore, early routinely evaluated RTU images of pregnant sows can predict litter size, with machine learning, in an automated manner and provide a useful tool for the efficient management of pregnant sows.

show abstract