Multi-model CNN fusion for sperm morphology analysis

Yuzkat, Mecit; İlhan, Hamza Osman; Aydın, Nizamettin

doi:10.1016/j.compbiomed.2021.104790

Cited by 25 publications

(9 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While determining these parameters, we tested the values frequently used in the literature. For example, while determining the minibatch size, we used 4, 8, 16, 32 mini batch sizes in our previous study (Yüzkat et al, 2021), and we generally achieved the best result by using 8 for each data set. In this study, we set the minibatch parameter to 8 according to our preliminary tests.…”

Section: Data Augmentation and Epoch Size Analysismentioning

confidence: 98%

See 1 more Smart Citation

Effects of Color Space Transformations on Classification Performance of Sperm Morphology

Yuzkat¹,

İlhan²,

Aydın³

2021

European Journal of Science and Technology

Self Cite

View full text Add to dashboard Cite

Infertility is defined by the World Health Organization as the inability of a woman to become pregnant even though the couple had sexual intercourse for one year without any protection. Male and/or female factors might be the reasons for infertility. When diagnosing the male factors, sperm specimens are analyzed in a laboratory environment under certain conditions. The morphological abnormality, characteristic motility and concentration of sperm are examined in the analysis called spermiogram. Spermiogram tests can be done manually by doctors, as well as by using computer-assisted sperm analyzing systems. The importance of computer aided analysis is increasing day by day because visual inspection can give different results from person to person and is costly. In this study, the effect of different color spaces as a preprocessing step is investigated to increase the classification performance of a computer based analyzing approach for sperm morphology. Three sperm morphology data sets abbreviated as SMIDS, HuSHeM and SCIAN-Morpho were used in the experimental tests. Data augmentation was applied on the data sets due to the unbalanced distribution of sperm images among the classes and insufficient data. Then, data sets were converted to two well-known color spaces, LAB and HSV to observe the effects of color space in the classification. MobileNetV2 was utilized as the classification model. In order to indicate the effects of color spaces, results were compared with previously published study where no color transform was implemented. The classification of images in LAB and HSV color spaces had better results than RGB images trained under the same conditions. The maximum classification accuracies of 89%, 85% and 68% were obtained for SMIDS, HuSHeM, SCIAN-Morpho data sets by using the color space transform idea, respectively.

show abstract

Section: Data Augmentation and Epoch Size Analysismentioning

confidence: 98%

“…In their study, they created six CNN models and combined the results of the models with fusion methods (hard and soft). They obtained 90.73%, 85.18% and 71.91% accuracy for the SMIDS, HuSHeM and SCIAN-MorphoSpermGS datasets, respectively (Yüzkat et al, 2021).…”

Section: Introductionmentioning

confidence: 98%

Effects of Color Space Transformations on Classification Performance of Sperm Morphology

Yuzkat¹,

İlhan²,

Aydın³

2021

European Journal of Science and Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…4. Enam model deep leaning network, Algoritma Central coordinate tracking, metode deepsperm dengan beberapa parameter [27], [28], [29] Berdasarkan dari banyaknya literatur yang dikumpulkan yakni menggambarkan perkembangan penelitian pada topik reproduksi manusia mulai dari penjelasan secara umum tentang organ reproduksi manusia serta kegunaanya hingga penelitian yang meneliti tingkat kesuburan seseorang terhadap reproduksi manusia menggunakan metode-metode yang berkaitan dengan bidang IT. Reproduksi merupakan menghasilkan keturunan baru dengan tujuan mempertahankan dan melestarikan sehingga agar tetap hidup dan tidak punah, dengan diawali dengan fertilisasi [14].…”

Section: Hasil Dan Pembahasanunclassified

“…Analisa data sperma pria yang dilakukan membutuhkan data dalam jumlah banyak, oleh karena itu digunakan metode Convolutional neural networks (CNNs) untuk menganalisa kumpulan data. Digunakan enam model CNNs untuk menghitung dan menganalisa clasifikasi morfologi pada sperma pria, pada tahap evaluasi digunakan dua teknik gabungan yaitu: hard-voting dan soft-voting dengan memanfaatkan tiga kumpulan data e SMIDS, HuSHeM dan SCIAN-Morpho, evaluasi dilakukan dengan membagi tiga kumpulan data menjadi lima bagian kecil serta menambahkan beberapa data berskala augmentasi dan mini-batch analysis yang menghasilkan 90.73% 85.18% dan 71.91% akurasi mengunakan soft-voting [27].…”

Section: Hasil Dan Pembahasanunclassified

Systematic Review: Perkembangan Machine Learning Pada Sperma Manusia

Aristoteles¹,

Syarif²,

Lumbanraja³

2023

JTI

View full text Add to dashboard Cite

Reproduksi merupakan proses dimana organisme memperbanyak diri yang tujuannya adalah mempertahankan kelangsungan hidup spesiesnya. Penelitian ini bertujuan untuk mengetahui perkembangan reproduksi pada manusia. Studi ini merupakan penyusunan studi literatur yang dilakukan dengan penelusuran di Google dan Google Scholar yang menggunakan kata kunci Sperma, Fertilisasi dan Reproduksi Manusia. Dari hasil penelusuran dan pemahaman jurnal didapatkan artikel yang masuk kedalam kriteria inklusi, bahwa semakin meningkat kemajuan tentang penelitian yang mengaitkan dengan kata kunci fertilisasi, sperma dan juga reproduksi manusia. Terdapat juga faktor-faktor yang bisa mempengaruhi tingkat kesuburan, serta terdapat pula aplikasi yang dapat mendeteksi tingkat kesuburan sperma.

show abstract

“…For this purpose, an emerging and attractive field on human reproduction and embryology is represented by the use of AI, machine learning and deep learning. These technologies are potentially applicable to many aspects of reproductive medicine, as sperm, oocyte and embryo selection, prediction of ART outcome, semen and sperm morphology evaluation (95)(96)(97)(98).…”

Section: Impact Of Sperm Morphology In Assisted Fertilizationmentioning

confidence: 99%

The relevance of sperm morphology in male infertility

Moretti

Signorini

Noto

et al. 2022

Front. Reprod. Health

View full text Add to dashboard Cite

This brief report concerns the role of human sperm morphology assessment in different fields of male infertility: basic research, genetics, assisted reproduction technologies, oxidative stress. One of the best methods in studying sperm morphology is transmission electron microscopy (TEM) that enables defining the concept of sperm pathology and classifying alterations in non-systematic and systematic. Non-systematic sperm defects affect head and tail in variable ratio, whereas the rare systematic defects are characterized by a particular anomaly that marks most sperm of an ejaculate. TEM analysis and fluorescence in situ hybridization represent outstanding methods in the study of sperm morphology and cytogenetic in patients with altered karyotype characterizing their semen quality before intracytoplasmic sperm injection. In recent years, the genetic investigations on systematic sperm defects, made extraordinary progress identifying candidate genes whose mutations induce morphological sperm anomalies. The question if sperm morphology has an impact on assisted fertilization outcome is debated. Nowadays, oxidative stress represents one of the most important causes of altered sperm morphology and function and can be analyzed from two points of view: 1) spermatozoa with cytoplasmic residue produce reactive oxygen species, 2) the pathologies with inflammatory/oxidative stress background cause morphological alterations. Finally, sperm morphology is also considered an important endpoint in in vitro experiments where toxic substances, drugs, antioxidants are tested. We think that the field of sperm morphology is far from being exhausted and needs other research. This parameter can be still considered a valuable indicator of sperm dysfunction both in basic and clinical research.

show abstract

Multi-model CNN fusion for sperm morphology analysis

Cited by 25 publications

References 40 publications

Effects of Color Space Transformations on Classification Performance of Sperm Morphology

Effects of Color Space Transformations on Classification Performance of Sperm Morphology

Systematic Review: Perkembangan Machine Learning Pada Sperma Manusia

The relevance of sperm morphology in male infertility

Contact Info

Product

Resources

About