Identification of Human Sperm based on Morphology Using the You Only Look Once Version 4 Algorithm

Aristoteles, -; Syarif, Admi; Sutyarso, -; Lumbanraja, Favorisen Rosyking; Hidayatullah, Arbi

doi:10.14569/ijacsa.2022.0130752

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regardless of applications or the types of cells to analyze, the first technical step for deep learning models is often to visually identify and locate an object (oocyte [33,34], sperm [35][36][37][38][39], and embryo [20,[40][41][42]) in images. Different clinics, however, use different image acquisition conditions (e.g., microscope brands and models, imaging modes [43][44][45], magnifications [9,33], illumination intensity, and camera resolutions [13][14][15]39] etc. ), as evident in Table 1.…”

Section: Introductionmentioning

confidence: 99%

Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Wang,

Jin,

Jiang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Deep learning has been increasingly investigated for assisting clinical in vitro fertilization (IVF). The first technical step in many tasks is to visually detect and locate sperm, oocytes, and embryos in images. For clinical deployment of such deep learning models, different clinics use different image acquisition hardware and different sample preprocessing protocols, raising the concern over whether the reported accuracy of a deep learning model by one clinic could be reproduced in another clinic. Here we aim to investigate the effect of each imaging factor on the reproducibility of object detection models, using sperm analysis as a pilot example. Methods: Ablation studies were performed using state-of-the-art models for detecting human sperm to quantitatively assess how model precision (false-positive detection) and recall (missed detection) were affected by imaging magnification, imaging mode, and sample preprocessing protocols. The results led to the hypothesis that the richness of image acquisition conditions in a training dataset deterministically affects model reproducibility. The hypothesis was tested by first enriching the training dataset with a wide range of imaging conditions, then validated through internal blind tests on new samples and external multi-center clinical validations. Results: Ablation experiments revealed that removing subsets of data from the training dataset significantly reduced model precision. Removing raw sample images from the training dataset caused the largest drop in model precision, whereas removing 20x images caused the largest drop in model recall. by incorporating different imaging and sample preprocessing conditions into a rich training dataset, the model achieved an intraclass correlation coefficient (ICC) of 0.97 (95% CI: 0.94-0.99) for precision, and an ICC of 0.97 (95% CI: 0.93-0.99) for recall. Multi-center clinical validation showed no significant differences in model precision or recall across different clinics and applications. Conclusions: The results validated the hypothesis that the richness of data in the training dataset is a key factor impacting model reproducibility. These findings highlight the importance of diversity in a training dataset for model evaluation and suggest that future deep learning models in andrology and reproductive medicine should incorporate comprehensive feature sets for enhanced reproducibility across clinics.

show abstract

Section: Introductionmentioning

confidence: 99%

Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Wang,

Jin,

Jiang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Meanwhile, in the era of the Industrial Revolution like now, nursing students must be able to adapt to existing technological advances. In research [14], it is said that technological developments really need further development to get better results, in order to get accurate results. Therefore, this research aims to develop an information system for information system for monitoring the nursing process with the addition of an expert system that uses the forward chaining method as a nursing diagnosis tool based on android application, to help nursing students in learning and improving the ability of the nursing process as well as assisting lecturers in monitoring the process carried out by prospective students.…”

Section: Introductionmentioning

confidence: 99%

Development of Nursing Process Expert System for Android-based Nursing Student Learning

Kusuma,

Irawati

et al. 2023

IJACSA

View full text Add to dashboard Cite

Nurses are professionals who provide health services using a scientific process called nursing. In nursing, problem-solving uses the nursing process which is a critical thinking method, nurses must analyze the data found in patients to diagnose and determine the results and appropriate intervention plans. Prospective nursing students are required to be able to apply the nursing process in carrying out nursing care according to existing nursing standards, of course, with supervision by nursing experts to improve the quality of medical services. This study aims to develop an android application with the help of an expert system as a nursing diagnosis tool, which helps nursing students learn the nursing process and helps lecturers monitor the nursing process carried out by nursing students. This research uses 116 symptom data, 22 diagnosis data, 60 intervention data, 8 type data, and 864 description data. The results of this research are in the form of an expert system with an android-based forward chaining method that has been tested using the black box testing method.

show abstract

Testing the generalizability and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Wang,

Jin,

Jiang

et al. 2024

Reprod Biol Endocrinol

View full text Add to dashboard Cite

Background Deep learning has been increasingly investigated for assisting clinical in vitro fertilization (IVF). The first technical step in many tasks is to visually detect and locate sperm, oocytes, and embryos in images. For clinical deployment of such deep learning models, different clinics use different image acquisition hardware and different sample preprocessing protocols, raising the concern over whether the reported accuracy of a deep learning model by one clinic could be reproduced in another clinic. Here we aim to investigate the effect of each imaging factor on the generalizability of object detection models, using sperm analysis as a pilot example. Methods Ablation studies were performed using state-of-the-art models for detecting human sperm to quantitatively assess how model precision (false-positive detection) and recall (missed detection) were affected by imaging magnification, imaging mode, and sample preprocessing protocols. The results led to the hypothesis that the richness of image acquisition conditions in a training dataset deterministically affects model generalizability. The hypothesis was tested by first enriching the training dataset with a wide range of imaging conditions, then validated through internal blind tests on new samples and external multi-center clinical validations. Results Ablation experiments revealed that removing subsets of data from the training dataset significantly reduced model precision. Removing raw sample images from the training dataset caused the largest drop in model precision, whereas removing 20x images caused the largest drop in model recall. by incorporating different imaging and sample preprocessing conditions into a rich training dataset, the model achieved an intraclass correlation coefficient (ICC) of 0.97 (95% CI: 0.94-0.99) for precision, and an ICC of 0.97 (95% CI: 0.93-0.99) for recall. Multi-center clinical validation showed no significant differences in model precision or recall across different clinics and applications. Conclusions The results validated the hypothesis that the richness of data in the training dataset is a key factor impacting model generalizability. These findings highlight the importance of diversity in a training dataset for model evaluation and suggest that future deep learning models in andrology and reproductive medicine should incorporate comprehensive feature sets for enhanced generalizability across clinics.

show abstract

Identification of Human Sperm based on Morphology Using the You Only Look Once Version 4 Algorithm

Cited by 4 publications

References 17 publications

Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Development of Nursing Process Expert System for Android-based Nursing Student Learning

Testing the generalizability and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Contact Info

Product

Resources

About