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

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Апрель 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

Язык: Английский

Portable six-channel laser speckle system for simultaneous measurement of cerebral blood flow and volume with potential applications in characterization of brain injury DOI Creative Commons
Simon Mahler, Yu Xi Huang,

Max Ismagilov

и другие.

Neurophotonics, Год журнала: 2025, Номер 12(01)

Опубликована: Янв. 24, 2025

SignificanceCerebral blood flow (CBF) and cerebral volume (CBV) are key metrics for regional cerebrovascular monitoring. Simultaneous, non-invasive measurement of CBF CBV at different brain locations would advance monitoring pave the way injury detection as current diagnostic methods often constrained by high costs, limited sensitivity, reliance on subjective symptom reporting.AimWe aim to develop a multi-channel optical system measuring regions simultaneously with cost-effective, reliable, scalable capable detecting potential differences in across brain.ApproachThe is based speckle contrast spectroscopy consists laser diodes board cameras, which have been both tested investigated safe use human head. Apart from universal serial bus connection camera, entire system, including its battery power source, integrated into wearable headband powered 9-V batteries.ResultsThe temporal dynamics cohort five healthy subjects were synchronized exhibited similar cardiac period waveforms all six channels. The our six-channel physiological sequelae was explored two subjects, one moderate significant structural damage, where six-point measurements referenced magnetic resonance imaging (MRI) scans.ConclusionsWe viable multi-point instrument CBV. Its cost-effectiveness allows baseline be established prior populations risk injury.

Язык: Английский

Процитировано

1
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

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Апрель 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

Язык: Английский

Процитировано

0