RT journal article
T1 Automated Mouse Pupil Size Measurement System to Assess Locus Coeruleus Activity with a Deep Learning-Based Approach
A1 Lara Doña, Alejandro
A1 Torres Sánchez, Sonia
A1 Priego Torres, Blanca María
A1 Berrocoso Domínguez, Esther María
A1 Sánchez Morillo, Daniel
A2 Ingeniería en AutomáticaElectrónica, Arquitectura y Redes de Computadores
A2 Psicología
K1 pupillometry
K1 locus coeruleus
K1 pupil size
K1 image processing
K1 deep learning
K1 machine learning
AB Strong evidence from studies on primates and rodents shows that changes in pupildiameter may reflect neural activity in the locus coeruleus (LC). Pupillometry is the only availablenon-invasive technique that could be used as a reliable and easily accessible real-time biomarker ofchanges in the in vivo activity of the LC. However, the application of pupillometry to preclinicalresearch in rodents is not yet fully standardized. A lack of consensus on the technical specificationsof some of the components used for image recording or positioning of the animal and cameras havebeen recorded in recent scientific literature. In this study, a novel pupillometry system to indirectlyassess, in real-time, the function of the LC in anesthetized rodents is presented. The system comprisesa deep learning SOLOv2 instance-based fast segmentation framework and a platform designed toplace the experimental subject, the video cameras for data acquisition, and the light source. Theperformance of the proposed setup was assessed and compared to other baseline methods usinga validation and an external test set. In the latter, the calculated intersection over the union was0.93 and the mean absolute percentage error was 1.89% for the selected method. The Bland–Altmananalysis depicted an excellent agreement. The results confirmed a high accuracy that makes thesystem suitable for real-time pupil size tracking, regardless of the pupil’s size, light intensity, orany features typical of the recording process in sedated mice. The framework could be used in anyneurophysiological study with sedated or fixed-head animals.
PB MDPI
SN 1424-8220
YR 2021
FD 2021-11
LK http://hdl.handle.net/10498/26106
UL http://hdl.handle.net/10498/26106
LA eng
NO This study was supported by grants co-financed by the "Fondo Europeo de Desarrollo Regional" (FEDER)-UE "A way to build Europe" from the "Ministerio de Economia y Competitividad" (MINECO: RTI2018-099778-B-I00); the "Programa Operativo de Andalucia FEDER, Iniciativa Territorial Integrada ITI 2014-2020 Consejeria Salud, Junta de Andalucia" (PI-0080-2017); the "Plan Andaluz de Investigacion, Desarrollo e Innovacion (PAIDI 2020), Consejeria de Economia, Conocimiento, Empresas y Universidad, Junta de Andalucia (P20_00958)"; the European Union's Horizon 2020 Research and Innovation Programme under the Marie Sklodowska-Curie grant agreement N degrees 955684; the "Instituto de Investigacion e Innovacion en Ciencias Biomedicas de Cadiz (LI19/06IN-CO22; IN-CO09; IN-CO07)"; the "Consejeria de Economia, Innovacion, Ciencia y Empleo de la Junta de Andalucia" (CTS-510 and TIC-212); the "Centro de Investigacion Biomedica en Red de Salud Mental-CIBERSAM" (CB/07/09/0033); and the "Universidad de Cadiz, contrato predoctoral fpuUCA 2019".
DS Repositorio Institucional de la Universidad de Cádiz
RD 08-nov-2026