An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy

Abstract B-ultrasound results are widely used in early pregnancy loss (EPL) prediction, but there are inevitable intra-observer and inter-observer errors in B-ultrasound results especially in early pregnancy, which lead to inconsistent assessment of embryonic status, and thus affect the judgment of...

Full description

Saved in:
Bibliographic Details
Main Authors: Lijue Liu, Yuan Zang, Huimu Zheng, Siya Li, Yu Song, Xue Feng, Xiyuan Zhang, Yaoxu Li, Lulu Cao, Guanglin Zhou, Tingting Dong, Qi Huang, Teng Pan, Jinhai Deng, Danling Cheng
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-11518-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344459881316352
author Lijue Liu
Yuan Zang
Huimu Zheng
Siya Li
Yu Song
Xue Feng
Xiyuan Zhang
Yaoxu Li
Lulu Cao
Guanglin Zhou
Tingting Dong
Qi Huang
Teng Pan
Jinhai Deng
Danling Cheng
author_facet Lijue Liu
Yuan Zang
Huimu Zheng
Siya Li
Yu Song
Xue Feng
Xiyuan Zhang
Yaoxu Li
Lulu Cao
Guanglin Zhou
Tingting Dong
Qi Huang
Teng Pan
Jinhai Deng
Danling Cheng
author_sort Lijue Liu
collection DOAJ
description Abstract B-ultrasound results are widely used in early pregnancy loss (EPL) prediction, but there are inevitable intra-observer and inter-observer errors in B-ultrasound results especially in early pregnancy, which lead to inconsistent assessment of embryonic status, and thus affect the judgment of EPL. To address this, we need a rapid and accurate model to predict pregnancy loss in the first trimester. This study aimed to construct an artificial intelligence model to automatically extract biometric parameters from ultrasound videos of early embryos and predict pregnancy loss. This can effectively eliminate the measurement error of B-ultrasound results, accurately predict EPL, and provide decision support for doctors with relatively little clinical experience. A total of 630 ultrasound videos from women with early singleton pregnancies of gestational age between 6 and 10 weeks were used for training. A two-stage artificial intelligence model was established. First, some biometric parameters such as gestational sac areas (GSA), yolk sac diameter (YSD), crown rump length (CRL) and fetal heart rate (FHR), were extract from ultrasound videos by a deep neural network named A3F-net, which is a modified neural network based on U-Net designed by ourselves. Then an ensemble learning model predicted pregnancy loss risk based on these features. Dice, IOU and Precision were used to evaluate the measurement results, and sensitivity, AUC etc. were used to evaluate the predict results. The fetal heart rate was compared with those measured by doctors, and the accuracy of results was compared with other AI models. In the biometric features measurement stage, the precision of GSA, YSD and CRL of A3F-net were 98.64%, 96.94% and 92.83%, it was the highest compared to other 2 models. Bland-Altman analysis did not show systematic deviations between doctors and AI. The mean and standard deviation of the mean relative error between doctors and the AI model was 0.060 ± 0.057. In the EPL prediction stage, the ensemble learning models demonstrated excellent performance, with CatBoost being the best-performing model, achieving a precision of 98.0% and an AUC of 0.969 (95% CI: 0.962–0.975). In this study, a hybrid AI model to predict EPL was established. First, a deep neural network automatically measured the biometric parameters from ultrasound video to ensure the consistency and accuracy of the measurements, then a machine learning model predicted EPL risk to support doctors making decisions. The use of our established AI model in EPL prediction has the potential to assist physicians in making more accurate and timely clinical decision in clinical application.
format Article
id doaj-art-c3ff30cc5ebd49488aa49659611588ca
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c3ff30cc5ebd49488aa49659611588ca2025-08-20T03:42:40ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-11518-5An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancyLijue Liu0Yuan Zang1Huimu Zheng2Siya Li3Yu Song4Xue Feng5Xiyuan Zhang6Yaoxu Li7Lulu Cao8Guanglin Zhou9Tingting Dong10Qi Huang11Teng Pan12Jinhai Deng13Danling Cheng14School of Automation, Central South UniversitySchool of Automation, Central South UniversityLonggang District Maternity & Child Healthcare Hospital of Shenzhen City (Longgang Maternity and Child Institute of Shantou University Medical College)CAS Blue Bay Cloud Technology (Guangdong) Co., Ltd.Department of Otolaryngology, Head & Neck Surgery, Peking University First HospitalDepartment of Respiratory and Critical Care Medicine, Tianjin Chest HospitalDepartment of Dermatology, Hunan Engineering Research Center of Skin Health and Disease, Hunan Key Laboratory of Skin Cancer and Psoriasis, Xiangya HospitalClinical Research Center (CRC), Medical Pathology Center (MPC), Cancer Early Diagnosis and Treatment Center (CEDTC) and Translational Medicine Research Center (TMRC), School of Medicine, Chongqing University Three Gorges Hospital, Chongqing UniversityDepartment of Rheumatology and Immunology, Peking University People’s Hospital and Beijing Key Laboratory for Rheumatism Mechanism and Immune Diagnosis (BZ0135)Longgang District Maternity & Child Healthcare Hospital of Shenzhen City (Longgang Maternity and Child Institute of Shantou University Medical College)Longgang District Maternity & Child Healthcare Hospital of Shenzhen City (Longgang Maternity and Child Institute of Shantou University Medical College)Longgang District Maternity & Child Healthcare Hospital of Shenzhen City (Longgang Maternity and Child Institute of Shantou University Medical College)Longgang District Maternity & Child Healthcare Hospital of Shenzhen City (Longgang Maternity and Child Institute of Shantou University Medical College)Richard Dimbleby Department of Cancer Research, Comprehensive Cancer Centre, Kings College LondonLonggang District Maternity & Child Healthcare Hospital of Shenzhen City (Longgang Maternity and Child Institute of Shantou University Medical College)Abstract B-ultrasound results are widely used in early pregnancy loss (EPL) prediction, but there are inevitable intra-observer and inter-observer errors in B-ultrasound results especially in early pregnancy, which lead to inconsistent assessment of embryonic status, and thus affect the judgment of EPL. To address this, we need a rapid and accurate model to predict pregnancy loss in the first trimester. This study aimed to construct an artificial intelligence model to automatically extract biometric parameters from ultrasound videos of early embryos and predict pregnancy loss. This can effectively eliminate the measurement error of B-ultrasound results, accurately predict EPL, and provide decision support for doctors with relatively little clinical experience. A total of 630 ultrasound videos from women with early singleton pregnancies of gestational age between 6 and 10 weeks were used for training. A two-stage artificial intelligence model was established. First, some biometric parameters such as gestational sac areas (GSA), yolk sac diameter (YSD), crown rump length (CRL) and fetal heart rate (FHR), were extract from ultrasound videos by a deep neural network named A3F-net, which is a modified neural network based on U-Net designed by ourselves. Then an ensemble learning model predicted pregnancy loss risk based on these features. Dice, IOU and Precision were used to evaluate the measurement results, and sensitivity, AUC etc. were used to evaluate the predict results. The fetal heart rate was compared with those measured by doctors, and the accuracy of results was compared with other AI models. In the biometric features measurement stage, the precision of GSA, YSD and CRL of A3F-net were 98.64%, 96.94% and 92.83%, it was the highest compared to other 2 models. Bland-Altman analysis did not show systematic deviations between doctors and AI. The mean and standard deviation of the mean relative error between doctors and the AI model was 0.060 ± 0.057. In the EPL prediction stage, the ensemble learning models demonstrated excellent performance, with CatBoost being the best-performing model, achieving a precision of 98.0% and an AUC of 0.969 (95% CI: 0.962–0.975). In this study, a hybrid AI model to predict EPL was established. First, a deep neural network automatically measured the biometric parameters from ultrasound video to ensure the consistency and accuracy of the measurements, then a machine learning model predicted EPL risk to support doctors making decisions. The use of our established AI model in EPL prediction has the potential to assist physicians in making more accurate and timely clinical decision in clinical application.https://doi.org/10.1038/s41598-025-11518-5Deep learningMachine learningUltrasound videosFirst trimesterPregnancy loss prediction
spellingShingle Lijue Liu
Yuan Zang
Huimu Zheng
Siya Li
Yu Song
Xue Feng
Xiyuan Zhang
Yaoxu Li
Lulu Cao
Guanglin Zhou
Tingting Dong
Qi Huang
Teng Pan
Jinhai Deng
Danling Cheng
An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
Scientific Reports
Deep learning
Machine learning
Ultrasound videos
First trimester
Pregnancy loss prediction
title An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
title_full An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
title_fullStr An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
title_full_unstemmed An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
title_short An AI method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
title_sort ai method to predict pregnancy loss by extracting biological indicators from embryo ultrasound recordings in early pregnancy
topic Deep learning
Machine learning
Ultrasound videos
First trimester
Pregnancy loss prediction
url https://doi.org/10.1038/s41598-025-11518-5
work_keys_str_mv AT lijueliu anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT yuanzang anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT huimuzheng anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT siyali anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT yusong anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT xuefeng anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT xiyuanzhang anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT yaoxuli anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT lulucao anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT guanglinzhou anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT tingtingdong anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT qihuang anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT tengpan anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT jinhaideng anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT danlingcheng anaimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT lijueliu aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT yuanzang aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT huimuzheng aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT siyali aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT yusong aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT xuefeng aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT xiyuanzhang aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT yaoxuli aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT lulucao aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT guanglinzhou aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT tingtingdong aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT qihuang aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT tengpan aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT jinhaideng aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy
AT danlingcheng aimethodtopredictpregnancylossbyextractingbiologicalindicatorsfromembryoultrasoundrecordingsinearlypregnancy