Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis

Sperm morphology is crucial in semen analysis for diagnosing male infertility. To reduce limitations in visual assessment, such as variability in biological conditions and the biologist’s experience, developing computer-based sperm analysis techniques is imperative. In this study, a total...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdulsamet Aktas, Gorkem Serbes, Merve Huner Yigit, Nizamettin Aydin, Hakki Uzun, Hamza Osman Ilhan
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10812754/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846099897904791552
author Abdulsamet Aktas
Gorkem Serbes
Merve Huner Yigit
Nizamettin Aydin
Hakki Uzun
Hamza Osman Ilhan
author_facet Abdulsamet Aktas
Gorkem Serbes
Merve Huner Yigit
Nizamettin Aydin
Hakki Uzun
Hamza Osman Ilhan
author_sort Abdulsamet Aktas
collection DOAJ
description Sperm morphology is crucial in semen analysis for diagnosing male infertility. To reduce limitations in visual assessment, such as variability in biological conditions and the biologist’s experience, developing computer-based sperm analysis techniques is imperative. In this study, a total of 49345 RGB sperm morphology patches were obtained using the proposed image acquisition technique and three different Diff-Quick staining methods: BesLab, Histoplus, and GBL. The images were labeled by experts under 18 classes, including sperm head, neck, and tail abnormality types, along with a normal class. The head category includes amorphous, tapered, double, pyriform, pin, vacuolated, narrow acrosome, and round. The neck category encompasses thin, thick, twisted, and asymmetrical. The tail category includes double, curly, long, short, and twisted. The Efficient-V2-Medium achieved accuracy rates of 65.05% and 67.42% on the BesLab and Histoplus datasets, respectively, while the GBL dataset yielded an accuracy of 63.58% using the Efficient-V2-Small. This study experimentally demonstrates that the Histoplus staining method is more suitable for deep learning-based automated analysis systems. As a reference for future studies, 35 different deep learning architectures were trained on the proposed dataset, establishing a classification baseline. The results show that the dataset can be successfully applied to complex deep learning models. Additionally, it addresses the absence of a large-scale sperm morphology analysis public datasets and can serve as a standard benchmark for future studies.
format Article
id doaj-art-8251350310654dbd81278cbef09fa1a9
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8251350310654dbd81278cbef09fa1a92024-12-31T00:01:05ZengIEEEIEEE Access2169-35362024-01-011219607019609110.1109/ACCESS.2024.352164310812754Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology AnalysisAbdulsamet Aktas0https://orcid.org/0000-0003-0746-7693Gorkem Serbes1https://orcid.org/0000-0003-4591-7368Merve Huner Yigit2https://orcid.org/0000-0001-8988-4321Nizamettin Aydin3https://orcid.org/0000-0003-0022-2247Hakki Uzun4https://orcid.org/0000-0002-5189-3166Hamza Osman Ilhan5https://orcid.org/0000-0002-1753-2703Department of Computer Engineering, Marmara University, İstanbul, TürkiyeDepartment of Biomedical Engineering, Yildiz Technical University, İstanbul, TürkiyeDepartment of Biochemistry, Recep Tayyip Erdoğan University, Rize, TürkiyeDepartment of Computer Engineering, Istanbul Technical University, İstanbul, TürkiyeDepartment of Urology, Faculty of Medicine, Recep Tayyip Erdoğan University, Rize, TürkiyeDepartment of Computer Engineering, Yildiz Technical University, Ã2°stanbul, TürkiyeSperm morphology is crucial in semen analysis for diagnosing male infertility. To reduce limitations in visual assessment, such as variability in biological conditions and the biologist’s experience, developing computer-based sperm analysis techniques is imperative. In this study, a total of 49345 RGB sperm morphology patches were obtained using the proposed image acquisition technique and three different Diff-Quick staining methods: BesLab, Histoplus, and GBL. The images were labeled by experts under 18 classes, including sperm head, neck, and tail abnormality types, along with a normal class. The head category includes amorphous, tapered, double, pyriform, pin, vacuolated, narrow acrosome, and round. The neck category encompasses thin, thick, twisted, and asymmetrical. The tail category includes double, curly, long, short, and twisted. The Efficient-V2-Medium achieved accuracy rates of 65.05% and 67.42% on the BesLab and Histoplus datasets, respectively, while the GBL dataset yielded an accuracy of 63.58% using the Efficient-V2-Small. This study experimentally demonstrates that the Histoplus staining method is more suitable for deep learning-based automated analysis systems. As a reference for future studies, 35 different deep learning architectures were trained on the proposed dataset, establishing a classification baseline. The results show that the dataset can be successfully applied to complex deep learning models. Additionally, it addresses the absence of a large-scale sperm morphology analysis public datasets and can serve as a standard benchmark for future studies.https://ieeexplore.ieee.org/document/10812754/Dataset benchmarkdeep learningdiff-quick staining methodsinfertility diagnosissperm morphology analysistransformer
spellingShingle Abdulsamet Aktas
Gorkem Serbes
Merve Huner Yigit
Nizamettin Aydin
Hakki Uzun
Hamza Osman Ilhan
Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis
IEEE Access
Dataset benchmark
deep learning
diff-quick staining methods
infertility diagnosis
sperm morphology analysis
transformer
title Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis
title_full Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis
title_fullStr Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis
title_full_unstemmed Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis
title_short Hi-LabSpermMorpho: A Novel Expert-Labeled Dataset With Extensive Abnormality Classes for Deep Learning-Based Sperm Morphology Analysis
title_sort hi labspermmorpho a novel expert labeled dataset with extensive abnormality classes for deep learning based sperm morphology analysis
topic Dataset benchmark
deep learning
diff-quick staining methods
infertility diagnosis
sperm morphology analysis
transformer
url https://ieeexplore.ieee.org/document/10812754/
work_keys_str_mv AT abdulsametaktas hilabspermmorphoanovelexpertlabeleddatasetwithextensiveabnormalityclassesfordeeplearningbasedspermmorphologyanalysis
AT gorkemserbes hilabspermmorphoanovelexpertlabeleddatasetwithextensiveabnormalityclassesfordeeplearningbasedspermmorphologyanalysis
AT mervehuneryigit hilabspermmorphoanovelexpertlabeleddatasetwithextensiveabnormalityclassesfordeeplearningbasedspermmorphologyanalysis
AT nizamettinaydin hilabspermmorphoanovelexpertlabeleddatasetwithextensiveabnormalityclassesfordeeplearningbasedspermmorphologyanalysis
AT hakkiuzun hilabspermmorphoanovelexpertlabeleddatasetwithextensiveabnormalityclassesfordeeplearningbasedspermmorphologyanalysis
AT hamzaosmanilhan hilabspermmorphoanovelexpertlabeleddatasetwithextensiveabnormalityclassesfordeeplearningbasedspermmorphologyanalysis