Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures
ABSTRACT The recognition of oocytes, in their maturational stages, allow estimate the ovarian development and the type of spawning of a species. Although, distinguishing oocytes on histological images requires a visual and subjective interpretation by the specialist. With the development of deep lea...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidade Federal do Ceará
2025-01-01
|
| Series: | Revista Ciência Agronômica |
| Subjects: | |
| Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902025000100638&lng=en&tlng=en |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592457112485888 |
|---|---|
| author | Yanna Leidy Ketley Fernandes Cruz Ewaldo Eder Carvalho Santana Isa Rosete Araujo Nascimento Antonio Fhillipi Maciel Silva Raimunda Nonata Fortes Carvalho Neta José Ribamar de Souza Torres-Junior |
| author_facet | Yanna Leidy Ketley Fernandes Cruz Ewaldo Eder Carvalho Santana Isa Rosete Araujo Nascimento Antonio Fhillipi Maciel Silva Raimunda Nonata Fortes Carvalho Neta José Ribamar de Souza Torres-Junior |
| author_sort | Yanna Leidy Ketley Fernandes Cruz |
| collection | DOAJ |
| description | ABSTRACT The recognition of oocytes, in their maturational stages, allow estimate the ovarian development and the type of spawning of a species. Although, distinguishing oocytes on histological images requires a visual and subjective interpretation by the specialist. With the development of deep learning techniques, automatic object detection has become an important mechanism for this task. However, studies that use deep learning techniques have not been widely explored for the analysis of fish oocyte samples so far. In this paper, we propose the use of YOLO, a family of convolutional neural networks, for oocyte morphology detection of Centropomus undecimalis fish. The research uses an image database with 5,680 oocytes with different maturation stadiums (PV - pre-vitellogenesis, VI - early vitellogenesis and VF - late vitellogenesis), in histological images, divided into training, testing and validation, and detection performed by YOLOv3, YOLOv4, and YOLOv5 architectures. The results obtained were promising, highlighting that the YOLOv5l model, in the detection of oocytes of the VF class, reached the best values in the metrics precision, recall, mAP@.5 and mAP@.95 with 85.4%, 95.3%, 95.7%, and 75.9%, respectively. When considering all classes, YOLOv5l was the model that obtained the best results in the analyzed metrics. |
| format | Article |
| id | doaj-art-7927291be2f245bfa97b31daff30f14c |
| institution | Kabale University |
| issn | 1806-6690 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Universidade Federal do Ceará |
| record_format | Article |
| series | Revista Ciência Agronômica |
| spelling | doaj-art-7927291be2f245bfa97b31daff30f14c2025-01-21T07:43:10ZengUniversidade Federal do CearáRevista Ciência Agronômica1806-66902025-01-015610.5935/1806-6690.20250038Fish oocyte morphology detection using neural networks: a comparison of YOLO architecturesYanna Leidy Ketley Fernandes Cruzhttps://orcid.org/0000-0003-4143-8167Ewaldo Eder Carvalho Santanahttps://orcid.org/0000-0002-8894-5353Isa Rosete Araujo Nascimentohttps://orcid.org/0000-0003-0170-765XAntonio Fhillipi Maciel Silvahttps://orcid.org/0000-0002-0410-0768Raimunda Nonata Fortes Carvalho Netahttps://orcid.org/0000-0002-3519-5237José Ribamar de Souza Torres-Juniorhttps://orcid.org/0000-0002-6356-6517ABSTRACT The recognition of oocytes, in their maturational stages, allow estimate the ovarian development and the type of spawning of a species. Although, distinguishing oocytes on histological images requires a visual and subjective interpretation by the specialist. With the development of deep learning techniques, automatic object detection has become an important mechanism for this task. However, studies that use deep learning techniques have not been widely explored for the analysis of fish oocyte samples so far. In this paper, we propose the use of YOLO, a family of convolutional neural networks, for oocyte morphology detection of Centropomus undecimalis fish. The research uses an image database with 5,680 oocytes with different maturation stadiums (PV - pre-vitellogenesis, VI - early vitellogenesis and VF - late vitellogenesis), in histological images, divided into training, testing and validation, and detection performed by YOLOv3, YOLOv4, and YOLOv5 architectures. The results obtained were promising, highlighting that the YOLOv5l model, in the detection of oocytes of the VF class, reached the best values in the metrics precision, recall, mAP@.5 and mAP@.95 with 85.4%, 95.3%, 95.7%, and 75.9%, respectively. When considering all classes, YOLOv5l was the model that obtained the best results in the analyzed metrics.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902025000100638&lng=en&tlng=enMaturational phasesHistological imagesArtificial intelligenceConvolutional Neural NetworksCentropomus undecimalis |
| spellingShingle | Yanna Leidy Ketley Fernandes Cruz Ewaldo Eder Carvalho Santana Isa Rosete Araujo Nascimento Antonio Fhillipi Maciel Silva Raimunda Nonata Fortes Carvalho Neta José Ribamar de Souza Torres-Junior Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures Revista Ciência Agronômica Maturational phases Histological images Artificial intelligence Convolutional Neural Networks Centropomus undecimalis |
| title | Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures |
| title_full | Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures |
| title_fullStr | Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures |
| title_full_unstemmed | Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures |
| title_short | Fish oocyte morphology detection using neural networks: a comparison of YOLO architectures |
| title_sort | fish oocyte morphology detection using neural networks a comparison of yolo architectures |
| topic | Maturational phases Histological images Artificial intelligence Convolutional Neural Networks Centropomus undecimalis |
| url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902025000100638&lng=en&tlng=en |
| work_keys_str_mv | AT yannaleidyketleyfernandescruz fishoocytemorphologydetectionusingneuralnetworksacomparisonofyoloarchitectures AT ewaldoedercarvalhosantana fishoocytemorphologydetectionusingneuralnetworksacomparisonofyoloarchitectures AT isarosetearaujonascimento fishoocytemorphologydetectionusingneuralnetworksacomparisonofyoloarchitectures AT antoniofhillipimacielsilva fishoocytemorphologydetectionusingneuralnetworksacomparisonofyoloarchitectures AT raimundanonatafortescarvalhoneta fishoocytemorphologydetectionusingneuralnetworksacomparisonofyoloarchitectures AT joseribamardesouzatorresjunior fishoocytemorphologydetectionusingneuralnetworksacomparisonofyoloarchitectures |