Exploring non-invasive sexing of early chick embryos in intact eggs using Laser Speckle Contrast Imaging (LSCI) and Deep Neural Network (DNN) DOI Creative Commons
Simon Mahler, Ajat Shatru Arora,

Carol Readhead

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Abstract The ability to image blood flow in early-stage avian embryos has significant applications developmental biology, drug and vaccine testing, as well determining sex differentiation. In this project, we used our recently developed laser speckle contrast imaging (LSCI) system non-invasively extraembryonic vessels these images attempt early identification of chick embryos. Specifically, captured from 1,251 living chicken between day three four incubation. We then applied deep neural network (DNN) models evaluate whether it is possible differentiate based on vascular patterns. Using ResNetBiT YOLOv5 models, results indicate that differentiation vessel was not achievable with sufficiently high accuracy or statistical significance for practical use. had a five-fold cross-validated average 59%±5% (fold-wise p-value, p ≤ 0.3) at 3 61%±3% (fold-wise, 0.04) 4. 55%±3% 53%±3% 0.5) Our findings suggest using pattern alone inconclusive reliable

Language: Английский

Exploring non-invasive sexing of early chick embryos in intact eggs using Laser Speckle Contrast Imaging (LSCI) and Deep Neural Network (DNN) DOI Creative Commons
Simon Mahler, Ajat Shatru Arora,

Carol Readhead

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Abstract The ability to image blood flow in early-stage avian embryos has significant applications developmental biology, drug and vaccine testing, as well determining sex differentiation. In this project, we used our recently developed laser speckle contrast imaging (LSCI) system non-invasively extraembryonic vessels these images attempt early identification of chick embryos. Specifically, captured from 1,251 living chicken between day three four incubation. We then applied deep neural network (DNN) models evaluate whether it is possible differentiate based on vascular patterns. Using ResNetBiT YOLOv5 models, results indicate that differentiation vessel was not achievable with sufficiently high accuracy or statistical significance for practical use. had a five-fold cross-validated average 59%±5% (fold-wise p-value, p ≤ 0.3) at 3 61%±3% (fold-wise, 0.04) 4. 55%±3% 53%±3% 0.5) Our findings suggest using pattern alone inconclusive reliable

Language: Английский

Citations

0