Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features
The current process of embryo selection in in vitro fertilization is based on morphological criteria; embryos are manually evaluated by embryologists under subjective assessment. In this study, a deep learning-based pipeline was developed to classify the viability of embryos using combined inputs, i...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/1/13 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588285380132864 |
|---|---|
| author | Krittapat Onthuam Norrawee Charnpinyo Kornrapee Suthicharoenpanich Supphaset Engphaiboon Punnarai Siricharoen Ronnapee Chaichaowarat Chanakarn Suebthawinkul |
| author_facet | Krittapat Onthuam Norrawee Charnpinyo Kornrapee Suthicharoenpanich Supphaset Engphaiboon Punnarai Siricharoen Ronnapee Chaichaowarat Chanakarn Suebthawinkul |
| author_sort | Krittapat Onthuam |
| collection | DOAJ |
| description | The current process of embryo selection in in vitro fertilization is based on morphological criteria; embryos are manually evaluated by embryologists under subjective assessment. In this study, a deep learning-based pipeline was developed to classify the viability of embryos using combined inputs, including microscopic images of embryos and additional features, such as patient age and developed pseudo-features, including a continuous interpretation of Istanbul grading scores by predicting the embryo stage, inner cell mass, and trophectoderm. For viability prediction, convolution-based transferred learning models were employed, multiple pretrained models were compared, and image preprocessing techniques and hyperparameter optimization via Optuna were utilized. In addition, a custom weight was trained using a self-supervised learning framework known as the Simple Framework for Contrastive Learning of Visual Representations (SimCLR) in cooperation with generated images using generative adversarial networks (GANs). The best model was developed from the EfficientNet-B0 model using preprocessed images combined with pseudo-features generated using separate EfficientNet-B0 models, and optimized by Optuna to tune the hyperparameters of the models. The designed model’s F1 score, accuracy, sensitivity, and area under curve (AUC) were 65.02%, 69.04%, 56.76%, and 66.98%, respectively. This study also showed an advantage in accuracy and a similar AUC when compared with the recent ensemble method. |
| format | Article |
| id | doaj-art-85b32f57dcab46ffa63e39932504d7fe |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-85b32f57dcab46ffa63e39932504d7fe2025-01-24T13:36:16ZengMDPI AGJournal of Imaging2313-433X2025-01-011111310.3390/jimaging11010013Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional FeaturesKrittapat Onthuam0Norrawee Charnpinyo1Kornrapee Suthicharoenpanich2Supphaset Engphaiboon3Punnarai Siricharoen4Ronnapee Chaichaowarat5Chanakarn Suebthawinkul6International School of Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandInternational School of Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandInternational School of Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandInternational School of Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandDepartment of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandInternational School of Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandDepartment of Obstetrics and Gynecology, Faculty of Medicine, Chulalongkorn University, Bangkok 10330, ThailandThe current process of embryo selection in in vitro fertilization is based on morphological criteria; embryos are manually evaluated by embryologists under subjective assessment. In this study, a deep learning-based pipeline was developed to classify the viability of embryos using combined inputs, including microscopic images of embryos and additional features, such as patient age and developed pseudo-features, including a continuous interpretation of Istanbul grading scores by predicting the embryo stage, inner cell mass, and trophectoderm. For viability prediction, convolution-based transferred learning models were employed, multiple pretrained models were compared, and image preprocessing techniques and hyperparameter optimization via Optuna were utilized. In addition, a custom weight was trained using a self-supervised learning framework known as the Simple Framework for Contrastive Learning of Visual Representations (SimCLR) in cooperation with generated images using generative adversarial networks (GANs). The best model was developed from the EfficientNet-B0 model using preprocessed images combined with pseudo-features generated using separate EfficientNet-B0 models, and optimized by Optuna to tune the hyperparameters of the models. The designed model’s F1 score, accuracy, sensitivity, and area under curve (AUC) were 65.02%, 69.04%, 56.76%, and 66.98%, respectively. This study also showed an advantage in accuracy and a similar AUC when compared with the recent ensemble method.https://www.mdpi.com/2313-433X/11/1/13deep learningembryo imageembryo morphologyCNNsGANsin vitro fertilization |
| spellingShingle | Krittapat Onthuam Norrawee Charnpinyo Kornrapee Suthicharoenpanich Supphaset Engphaiboon Punnarai Siricharoen Ronnapee Chaichaowarat Chanakarn Suebthawinkul Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features Journal of Imaging deep learning embryo image embryo morphology CNNs GANs in vitro fertilization |
| title | Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features |
| title_full | Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features |
| title_fullStr | Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features |
| title_full_unstemmed | Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features |
| title_short | Combined Input Deep Learning Pipeline for Embryo Selection for In Vitro Fertilization Using Light Microscopic Images and Additional Features |
| title_sort | combined input deep learning pipeline for embryo selection for in vitro fertilization using light microscopic images and additional features |
| topic | deep learning embryo image embryo morphology CNNs GANs in vitro fertilization |
| url | https://www.mdpi.com/2313-433X/11/1/13 |
| work_keys_str_mv | AT krittapatonthuam combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures AT norraweecharnpinyo combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures AT kornrapeesuthicharoenpanich combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures AT supphasetengphaiboon combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures AT punnaraisiricharoen combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures AT ronnapeechaichaowarat combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures AT chanakarnsuebthawinkul combinedinputdeeplearningpipelineforembryoselectionforinvitrofertilizationusinglightmicroscopicimagesandadditionalfeatures |