A machine learning model for predicting fertilization following short‐term insemination using embryo images
Abstract Purpose This study established a machine learning model (MLM) trained on embryo images to predict fertilization following short‐term insemination for early rescue ICSI and compared its predictive performance with the embryologist's manual classification. Methods Embryo images at 4.5 an...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Reproductive Medicine and Biology |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/rmb2.12649 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849233420352225280 |
|---|---|
| author | Masato Saito Hirofumi Haraguchi Ikumi Nakajima Shinya Fukuda Chenghua Zhu Norio Masuya Kazunori Matsumoto Yuya Yoshikawa Tomoki Tanaka Satoshi Kishigami Leona Matsumoto |
| author_facet | Masato Saito Hirofumi Haraguchi Ikumi Nakajima Shinya Fukuda Chenghua Zhu Norio Masuya Kazunori Matsumoto Yuya Yoshikawa Tomoki Tanaka Satoshi Kishigami Leona Matsumoto |
| author_sort | Masato Saito |
| collection | DOAJ |
| description | Abstract Purpose This study established a machine learning model (MLM) trained on embryo images to predict fertilization following short‐term insemination for early rescue ICSI and compared its predictive performance with the embryologist's manual classification. Methods Embryo images at 4.5 and 8 h post‐insemination were preprocessed into vectors using ResNet50. The Light Gradient Boosting Machine (Light GBM) was employed for training vectors. Fertilization in the test dataset was assessed by MLM, with seven senior and 11 junior embryologists. Predictive metrics were analyzed using repeated measures ANOVA and paired t‐tests. Results Comparing MLM, senior embryologists, and junior embryologists, significant differences were observed in accuracy (0.71 ± 0.01, 0.75 ± 0.05, 0.61 ± 0.05), recall (0.84 ± 0.02, 0.84 ± 0.10, 0.61 ± 0.07), F1‐score (0.78 ± 0.01, 0.81 ± 0.04, 0.66 ± 0.04), and area under the curve (0.73 ± 0.0 3, 0.73 ± 0.06, 0.61 ± 0.07), the MLM outperforming junior embryologists with <1 year of experience. No significant differences were observed between the MLM and senior embryologists with over 5 years of experience. Conclusions MLM can effectively predict fertilization following short‐term insemination by analyzing cytoplasmic changes in images. These results underscore the potential to enhance clinical decision‐making and improve patient outcomes. |
| format | Article |
| id | doaj-art-9ef6b5dc936f4dea89bb4d5bc65149dc |
| institution | Kabale University |
| issn | 1445-5781 1447-0578 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Reproductive Medicine and Biology |
| spelling | doaj-art-9ef6b5dc936f4dea89bb4d5bc65149dc2025-08-20T06:16:47ZengWileyReproductive Medicine and Biology1445-57811447-05782025-01-01241n/an/a10.1002/rmb2.12649A machine learning model for predicting fertilization following short‐term insemination using embryo imagesMasato Saito0Hirofumi Haraguchi1Ikumi Nakajima2Shinya Fukuda3Chenghua Zhu4Norio Masuya5Kazunori Matsumoto6Yuya Yoshikawa7Tomoki Tanaka8Satoshi Kishigami9Leona Matsumoto10Matsumoto Ladies IVF Clinic Tokyo JapanMatsumoto Ladies IVF Clinic Tokyo JapanMatsumoto Ladies IVF Clinic Tokyo JapanMatsumoto Ladies IVF Clinic Tokyo JapanMatsumoto Ladies IVF Clinic Tokyo JapanMatsumoto Ladies IVF Clinic Tokyo JapanMatsumoto Ladies IVF Clinic Tokyo JapanSoftware Technology and Artificial Intelligence Research Laboratory Chiba Institute of Technology Chiba JapanMatsumoto Ladies IVF Clinic Tokyo JapanDepartment of Integrated Applied Life Science University of Yamanashi Yamanashi JapanMatsumoto Ladies IVF Clinic Tokyo JapanAbstract Purpose This study established a machine learning model (MLM) trained on embryo images to predict fertilization following short‐term insemination for early rescue ICSI and compared its predictive performance with the embryologist's manual classification. Methods Embryo images at 4.5 and 8 h post‐insemination were preprocessed into vectors using ResNet50. The Light Gradient Boosting Machine (Light GBM) was employed for training vectors. Fertilization in the test dataset was assessed by MLM, with seven senior and 11 junior embryologists. Predictive metrics were analyzed using repeated measures ANOVA and paired t‐tests. Results Comparing MLM, senior embryologists, and junior embryologists, significant differences were observed in accuracy (0.71 ± 0.01, 0.75 ± 0.05, 0.61 ± 0.05), recall (0.84 ± 0.02, 0.84 ± 0.10, 0.61 ± 0.07), F1‐score (0.78 ± 0.01, 0.81 ± 0.04, 0.66 ± 0.04), and area under the curve (0.73 ± 0.0 3, 0.73 ± 0.06, 0.61 ± 0.07), the MLM outperforming junior embryologists with <1 year of experience. No significant differences were observed between the MLM and senior embryologists with over 5 years of experience. Conclusions MLM can effectively predict fertilization following short‐term insemination by analyzing cytoplasmic changes in images. These results underscore the potential to enhance clinical decision‐making and improve patient outcomes.https://doi.org/10.1002/rmb2.12649cytoplasmearly rescue ICSIfertilizationmachine learningshort‐term insemination |
| spellingShingle | Masato Saito Hirofumi Haraguchi Ikumi Nakajima Shinya Fukuda Chenghua Zhu Norio Masuya Kazunori Matsumoto Yuya Yoshikawa Tomoki Tanaka Satoshi Kishigami Leona Matsumoto A machine learning model for predicting fertilization following short‐term insemination using embryo images Reproductive Medicine and Biology cytoplasm early rescue ICSI fertilization machine learning short‐term insemination |
| title | A machine learning model for predicting fertilization following short‐term insemination using embryo images |
| title_full | A machine learning model for predicting fertilization following short‐term insemination using embryo images |
| title_fullStr | A machine learning model for predicting fertilization following short‐term insemination using embryo images |
| title_full_unstemmed | A machine learning model for predicting fertilization following short‐term insemination using embryo images |
| title_short | A machine learning model for predicting fertilization following short‐term insemination using embryo images |
| title_sort | machine learning model for predicting fertilization following short term insemination using embryo images |
| topic | cytoplasm early rescue ICSI fertilization machine learning short‐term insemination |
| url | https://doi.org/10.1002/rmb2.12649 |
| work_keys_str_mv | AT masatosaito amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT hirofumiharaguchi amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT ikuminakajima amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT shinyafukuda amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT chenghuazhu amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT noriomasuya amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT kazunorimatsumoto amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT yuyayoshikawa amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT tomokitanaka amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT satoshikishigami amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT leonamatsumoto amachinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT masatosaito machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT hirofumiharaguchi machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT ikuminakajima machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT shinyafukuda machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT chenghuazhu machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT noriomasuya machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT kazunorimatsumoto machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT yuyayoshikawa machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT tomokitanaka machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT satoshikishigami machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages AT leonamatsumoto machinelearningmodelforpredictingfertilizationfollowingshortterminseminationusingembryoimages |