Evaluation of an artificial intelligence-facilitated sperm detection tool in azoospermic samples for use in ICSI.

Goss, DM; Vasilescu, SA; Vasilescu, PA; Cooke, S; Kim, SH; Sacks, GP; Gardner, DK; Warkiani, ME

Evaluation of an artificial intelligence-facilitated sperm detection tool in azoospermic samples for use in ICSI.

Goss, DM Vasilescu, SA Vasilescu, PA Cooke, S Kim, SH Sacks, GP Gardner, DK Warkiani, ME

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Reprod Biomed Online, 2024, 49, (1), pp. 103910
Issue Date:: 2024-07

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (1.12 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Goss, DM
dc.contributor.author	Vasilescu, SA
dc.contributor.author	Vasilescu, PA
dc.contributor.author	Cooke, S
dc.contributor.author	Kim, SH
dc.contributor.author	Sacks, GP
dc.contributor.author	Gardner, DK
dc.contributor.author	Warkiani, ME
dc.date.accessioned	2024-11-19T02:53:05Z
dc.date.available	2024-02-09
dc.date.available	2024-11-19T02:53:05Z
dc.date.issued	2024-07
dc.identifier.citation	Reprod Biomed Online, 2024, 49, (1), pp. 103910
dc.identifier.issn	1472-6483
dc.identifier.issn	1472-6491
dc.identifier.uri	http://hdl.handle.net/10453/181974
dc.description.abstract	RESEARCH QUESTION: Can artificial intelligence (AI) improve the efficiency and efficacy of sperm searches in azoospermic samples? DESIGN: This two-phase proof-of-concept study began with a training phase using eight azoospermic patients (>10,000 sperm images) to provide a variety of surgically collected samples for sperm morphology and debris variation to train a convolutional neural network to identify spermatozoa. Second, side-by-side testing was undertaken on two cohorts of non-obstructive azoospermia patient samples: an embryologist versus the AI identifying all the spermatozoa in the still images (cohort 1, n = 4), and a side-by-side test with a simulated clinical deployment of the AI model with an intracytoplasmic sperm injection microscope and the embryologist performing a search with and without the aid of the AI (cohort 2, n = 4). RESULTS: In cohort 1, the AI model showed an improvement in the time taken to identify all the spermatozoa per field of view (0.02 ± 0.30  ×  10-5s versus 36.10 ± 1.18s, P < 0.0001) and improved recall (91.95 ± 0.81% versus 86.52 ± 1.34%, P < 0.001) compared with an embryologist. From a total of 2660 spermatozoa to find in all the samples combined, 1937 were found by an embryologist and 1997 were found by the AI in less than 1000th of the time. In cohort 2, the AI-aided embryologist took significantly less time per droplet (98.90 ± 3.19 s versus 168.7 ± 7.84 s, P < 0.0001) and found 1396 spermatozoa, while 1274 were found without AI, although no significant difference was observed. CONCLUSIONS: AI-powered image analysis has the potential for seamless integration into laboratory workflows, to reduce the time to identify and isolate spermatozoa from surgical sperm samples from hours to minutes, thus increasing success rates from these treatments.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Reprod Biomed Online
dc.relation.isbasedon	10.1016/j.rbmo.2024.103910
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	1114 Paediatrics and Reproductive Medicine
dc.subject.classification	Obstetrics & Reproductive Medicine
dc.subject.classification	3215 Reproductive medicine
dc.subject.mesh	Humans
dc.subject.mesh	Male
dc.subject.mesh	Azoospermia
dc.subject.mesh	Sperm Injections, Intracytoplasmic
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Spermatozoa
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Proof of Concept Study
dc.subject.mesh	Sperm Retrieval
dc.subject.mesh	Adult
dc.subject.mesh	Spermatozoa
dc.subject.mesh	Humans
dc.subject.mesh	Sperm Injections, Intracytoplasmic
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Adult
dc.subject.mesh	Male
dc.subject.mesh	Azoospermia
dc.subject.mesh	Sperm Retrieval
dc.subject.mesh	Proof of Concept Study
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Humans
dc.subject.mesh	Male
dc.subject.mesh	Azoospermia
dc.subject.mesh	Sperm Injections, Intracytoplasmic
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Spermatozoa
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Proof of Concept Study
dc.subject.mesh	Sperm Retrieval
dc.subject.mesh	Adult
dc.title	Evaluation of an artificial intelligence-facilitated sperm detection tool in azoospermic samples for use in ICSI.
dc.type	Journal Article
utslib.citation.volume	49
utslib.location.activity	Netherlands
utslib.for	1114 Paediatrics and Reproductive Medicine
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Centre for Health Technologies (CHT)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Institute of Biomedical Materials and Devices (IBMD)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Institute of Biomedical Materials and Devices (IBMD)/Associate Member
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2024-11-19T02:53:03Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	49
utslib.citation.issue	1

Abstract:

RESEARCH QUESTION: Can artificial intelligence (AI) improve the efficiency and efficacy of sperm searches in azoospermic samples? DESIGN: This two-phase proof-of-concept study began with a training phase using eight azoospermic patients (>10,000 sperm images) to provide a variety of surgically collected samples for sperm morphology and debris variation to train a convolutional neural network to identify spermatozoa. Second, side-by-side testing was undertaken on two cohorts of non-obstructive azoospermia patient samples: an embryologist versus the AI identifying all the spermatozoa in the still images (cohort 1, n = 4), and a side-by-side test with a simulated clinical deployment of the AI model with an intracytoplasmic sperm injection microscope and the embryologist performing a search with and without the aid of the AI (cohort 2, n = 4). RESULTS: In cohort 1, the AI model showed an improvement in the time taken to identify all the spermatozoa per field of view (0.02 ± 0.30  ×  10-5s versus 36.10 ± 1.18s, P < 0.0001) and improved recall (91.95 ± 0.81% versus 86.52 ± 1.34%, P < 0.001) compared with an embryologist. From a total of 2660 spermatozoa to find in all the samples combined, 1937 were found by an embryologist and 1997 were found by the AI in less than 1000th of the time. In cohort 2, the AI-aided embryologist took significantly less time per droplet (98.90 ± 3.19 s versus 168.7 ± 7.84 s, P < 0.0001) and found 1396 spermatozoa, while 1274 were found without AI, although no significant difference was observed. CONCLUSIONS: AI-powered image analysis has the potential for seamless integration into laboratory workflows, to reduce the time to identify and isolate spermatozoa from surgical sperm samples from hours to minutes, thus increasing success rates from these treatments.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/181974