Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound

Testicular histology based on testicular biopsy is an important factor for determining appropriate testicular sperm extraction surgery and predicting sperm retrieval outcomes in patients with azoospermia. Therefore, we developed a deep learning (DL) model to establish the associations between testic...

Full description

Saved in:
Bibliographic Details
Main Authors: Jia-Ying Hu, Zhen-Zhe Lin, Li Ding, Zhi-Xing Zhang, Wan-Ling Huang, Sha-Sha Huang, Bin Li, Xiao-Yan Xie, Ming-De Lu, Chun-Hua Deng, Hao-Tian Lin, Yong Gao, Zhu Wang
Format: Article
Language:English
Published: Wolters Kluwer Medknow Publications 2025-03-01
Series:Asian Journal of Andrology
Subjects:
Online Access:https://journals.lww.com/10.4103/aja202480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850069135433662464
author Jia-Ying Hu
Zhen-Zhe Lin
Li Ding
Zhi-Xing Zhang
Wan-Ling Huang
Sha-Sha Huang
Bin Li
Xiao-Yan Xie
Ming-De Lu
Chun-Hua Deng
Hao-Tian Lin
Yong Gao
Zhu Wang
author_facet Jia-Ying Hu
Zhen-Zhe Lin
Li Ding
Zhi-Xing Zhang
Wan-Ling Huang
Sha-Sha Huang
Bin Li
Xiao-Yan Xie
Ming-De Lu
Chun-Hua Deng
Hao-Tian Lin
Yong Gao
Zhu Wang
author_sort Jia-Ying Hu
collection DOAJ
description Testicular histology based on testicular biopsy is an important factor for determining appropriate testicular sperm extraction surgery and predicting sperm retrieval outcomes in patients with azoospermia. Therefore, we developed a deep learning (DL) model to establish the associations between testicular grayscale ultrasound images and testicular histology. We retrospectively included two-dimensional testicular grayscale ultrasound from patients with azoospermia (353 men with 4357 images between July 2017 and December 2021 in The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China) to develop a DL model. We obtained testicular histology during conventional testicular sperm extraction. Our DL model was trained based on ultrasound images or fusion data (ultrasound images fused with the corresponding testicular volume) to distinguish spermatozoa presence in pathology (SPP) and spermatozoa absence in pathology (SAP) and to classify maturation arrest (MA) and Sertoli cell-only syndrome (SCOS) in patients with SAP. Areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were used to analyze model performance. DL based on images achieved an AUC of 0.922 (95% confidence interval [CI]: 0.908–0.935), a sensitivity of 80.9%, a specificity of 84.6%, and an accuracy of 83.5% in predicting SPP (including normal spermatogenesis and hypospermatogenesis) and SAP (including MA and SCOS). In the identification of SCOS and MA, DL on fusion data yielded better diagnostic performance with an AUC of 0.979 (95% CI: 0.969–0.989), a sensitivity of 89.7%, a specificity of 97.1%, and an accuracy of 92.1%. Our study provides a noninvasive method to predict testicular histology for patients with azoospermia, which would avoid unnecessary testicular biopsy.
format Article
id doaj-art-e483934f5f294a618e09b8fde27fd1bc
institution DOAJ
issn 1008-682X
1745-7262
language English
publishDate 2025-03-01
publisher Wolters Kluwer Medknow Publications
record_format Article
series Asian Journal of Andrology
spelling doaj-art-e483934f5f294a618e09b8fde27fd1bc2025-08-20T02:47:51ZengWolters Kluwer Medknow PublicationsAsian Journal of Andrology1008-682X1745-72622025-03-0127225426010.4103/aja202480Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasoundJia-Ying HuZhen-Zhe LinLi DingZhi-Xing ZhangWan-Ling HuangSha-Sha HuangBin LiXiao-Yan XieMing-De LuChun-Hua DengHao-Tian LinYong GaoZhu WangTesticular histology based on testicular biopsy is an important factor for determining appropriate testicular sperm extraction surgery and predicting sperm retrieval outcomes in patients with azoospermia. Therefore, we developed a deep learning (DL) model to establish the associations between testicular grayscale ultrasound images and testicular histology. We retrospectively included two-dimensional testicular grayscale ultrasound from patients with azoospermia (353 men with 4357 images between July 2017 and December 2021 in The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China) to develop a DL model. We obtained testicular histology during conventional testicular sperm extraction. Our DL model was trained based on ultrasound images or fusion data (ultrasound images fused with the corresponding testicular volume) to distinguish spermatozoa presence in pathology (SPP) and spermatozoa absence in pathology (SAP) and to classify maturation arrest (MA) and Sertoli cell-only syndrome (SCOS) in patients with SAP. Areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were used to analyze model performance. DL based on images achieved an AUC of 0.922 (95% confidence interval [CI]: 0.908–0.935), a sensitivity of 80.9%, a specificity of 84.6%, and an accuracy of 83.5% in predicting SPP (including normal spermatogenesis and hypospermatogenesis) and SAP (including MA and SCOS). In the identification of SCOS and MA, DL on fusion data yielded better diagnostic performance with an AUC of 0.979 (95% CI: 0.969–0.989), a sensitivity of 89.7%, a specificity of 97.1%, and an accuracy of 92.1%. Our study provides a noninvasive method to predict testicular histology for patients with azoospermia, which would avoid unnecessary testicular biopsy.https://journals.lww.com/10.4103/aja202480azoospermiadeep learningmale infertilitytesticular histologyultrasound
spellingShingle Jia-Ying Hu
Zhen-Zhe Lin
Li Ding
Zhi-Xing Zhang
Wan-Ling Huang
Sha-Sha Huang
Bin Li
Xiao-Yan Xie
Ming-De Lu
Chun-Hua Deng
Hao-Tian Lin
Yong Gao
Zhu Wang
Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound
Asian Journal of Andrology
azoospermia
deep learning
male infertility
testicular histology
ultrasound
title Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound
title_full Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound
title_fullStr Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound
title_full_unstemmed Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound
title_short Prediction of testicular histology in azoospermia patients through deep learning-enabled two-dimensional grayscale ultrasound
title_sort prediction of testicular histology in azoospermia patients through deep learning enabled two dimensional grayscale ultrasound
topic azoospermia
deep learning
male infertility
testicular histology
ultrasound
url https://journals.lww.com/10.4103/aja202480
work_keys_str_mv AT jiayinghu predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT zhenzhelin predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT liding predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT zhixingzhang predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT wanlinghuang predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT shashahuang predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT binli predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT xiaoyanxie predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT mingdelu predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT chunhuadeng predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT haotianlin predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT yonggao predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound
AT zhuwang predictionoftesticularhistologyinazoospermiapatientsthroughdeeplearningenabledtwodimensionalgrayscaleultrasound