Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture

Human infertility is considered a serious disease of the the reproductive system that affects more than 10% of couples worldwide,and more than 30% of reported cases are related to men. The crucial step in evaluating male in fertility is a semen analysis, highly dependent on sperm morphology. Howeve...

Full description

Bibliographic Details
Main Author: Melendez Melendez, Roy Kelvin
Other Authors: Beltrán Castañón, César Armando
Format: Dissertation
Language:English
Published: Pontificia Universidad Católica del Perú 2021
Subjects:
Online Access:http://hdl.handle.net/20.500.12404/19908
id ndltd-PUCP-oai-tesis.pucp.edu.pe-20.500.12404-19908
record_format oai_dc
spelling ndltd-PUCP-oai-tesis.pucp.edu.pe-20.500.12404-199082021-09-23T05:14:11Z Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture Melendez Melendez, Roy Kelvin Beltrán Castañón, César Armando Redes neuronales (Computación) Espermatozoides--Análisis http://purl.org/pe-repo/ocde/ford#1.02.01 Human infertility is considered a serious disease of the the reproductive system that affects more than 10% of couples worldwide,and more than 30% of reported cases are related to men. The crucial step in evaluating male in fertility is a semen analysis, highly dependent on sperm morphology. However,this analysis is done at the laboratory manually and depends mainly on the doctor’s experience. Besides,it is laborious, and there is also a high degree of interlaboratory variability in the results. This article proposes applying a specialized convolutional neural network architecture (U-Net),which focuses on the segmentation of sperm cells in micrographs to overcome these problems.The results showed high scores for the model segmentation metrics such as precisión (93%), IoU score (86%),and DICE score of 93%. Moreover,we can conclude that U-net architecture turned out to be a good option to carry out the segmentation of sperm cells. 2021-08-11T16:48:25Z 2021-08-11T16:48:25Z 2021 2021-08-11 info:eu-repo/semantics/masterThesis http://hdl.handle.net/20.500.12404/19908 eng info:eu-repo/semantics/openAccess Atribución-NoComercial-CompartirIgual 2.5 Perú http://creativecommons.org/licenses/by-nc-sa/2.5/pe/ application/pdf Pontificia Universidad Católica del Perú PE Pontificia Universidad Católica del Perú Repositorio de Tesis - PUCP
collection NDLTD
language English
format Dissertation
sources NDLTD
topic Redes neuronales (Computación)
Espermatozoides--Análisis
http://purl.org/pe-repo/ocde/ford#1.02.01
spellingShingle Redes neuronales (Computación)
Espermatozoides--Análisis
http://purl.org/pe-repo/ocde/ford#1.02.01
Melendez Melendez, Roy Kelvin
Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
description Human infertility is considered a serious disease of the the reproductive system that affects more than 10% of couples worldwide,and more than 30% of reported cases are related to men. The crucial step in evaluating male in fertility is a semen analysis, highly dependent on sperm morphology. However,this analysis is done at the laboratory manually and depends mainly on the doctor’s experience. Besides,it is laborious, and there is also a high degree of interlaboratory variability in the results. This article proposes applying a specialized convolutional neural network architecture (U-Net),which focuses on the segmentation of sperm cells in micrographs to overcome these problems.The results showed high scores for the model segmentation metrics such as precisión (93%), IoU score (86%),and DICE score of 93%. Moreover,we can conclude that U-net architecture turned out to be a good option to carry out the segmentation of sperm cells.
author2 Beltrán Castañón, César Armando
author_facet Beltrán Castañón, César Armando
Melendez Melendez, Roy Kelvin
author Melendez Melendez, Roy Kelvin
author_sort Melendez Melendez, Roy Kelvin
title Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
title_short Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
title_full Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
title_fullStr Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
title_full_unstemmed Sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
title_sort sperm cell segmentation in digital micrographs based on convolutional neural networks using u-net architecture
publisher Pontificia Universidad Católica del Perú
publishDate 2021
url http://hdl.handle.net/20.500.12404/19908
work_keys_str_mv AT melendezmelendezroykelvin spermcellsegmentationindigitalmicrographsbasedonconvolutionalneuralnetworksusingunetarchitecture
_version_ 1719483546305822720