An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization
Abstract Medical Assisted Reproduction proved its efficacy to treat the vast majority forms of infertility. One of the key procedures in this treatment is the selection and transfer of the embryo with the highest developmental potential. To assess this potential, clinical embryologists routinely wor...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-05-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-023-02182-3 |
| _version_ | 1797827700530872320 |
|---|---|
| author | Florian Kromp Raphael Wagner Basak Balaban Véronique Cottin Irene Cuevas-Saiz Clara Schachner Peter Fancsovits Mohamed Fawzy Lukas Fischer Necati Findikli Borut Kovačič Dejan Ljiljak Iris Martínez-Rodero Lodovico Parmegiani Omar Shebl Xie Min Thomas Ebner |
| author_facet | Florian Kromp Raphael Wagner Basak Balaban Véronique Cottin Irene Cuevas-Saiz Clara Schachner Peter Fancsovits Mohamed Fawzy Lukas Fischer Necati Findikli Borut Kovačič Dejan Ljiljak Iris Martínez-Rodero Lodovico Parmegiani Omar Shebl Xie Min Thomas Ebner |
| author_sort | Florian Kromp |
| collection | DOAJ |
| description | Abstract Medical Assisted Reproduction proved its efficacy to treat the vast majority forms of infertility. One of the key procedures in this treatment is the selection and transfer of the embryo with the highest developmental potential. To assess this potential, clinical embryologists routinely work with static images (morphological assessment) or short video sequences (time-lapse annotation). Recently, Artificial Intelligence models were utilized to support the embryo selection procedure. Even though they have proven their great potential in different in vitro fertilization settings, there is still considerable room for improvement. To support the advancement of algorithms in this research field, we built a dataset consisting of static blastocyst images and additional annotations. As such, Gardner criteria annotations, depicting a morphological blastocyst rating scheme, and collected clinical parameters are provided. The presented dataset is intended to be used to train deep learning models on static morphological images to predict Gardner’s criteria and clinical outcomes such as live birth. A benchmark of human expert’s performance in annotating Gardner criteria is provided. |
| first_indexed | 2024-04-09T12:52:33Z |
| format | Article |
| id | doaj.art-47ec9beecbdf4b669c29b963835bdb6d |
| institution | Directory Open Access Journal |
| issn | 2052-4463 |
| language | English |
| last_indexed | 2024-04-09T12:52:33Z |
| publishDate | 2023-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj.art-47ec9beecbdf4b669c29b963835bdb6d2023-05-14T11:07:46ZengNature PortfolioScientific Data2052-44632023-05-011011810.1038/s41597-023-02182-3An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilizationFlorian Kromp0Raphael Wagner1Basak Balaban2Véronique Cottin3Irene Cuevas-Saiz4Clara Schachner5Peter Fancsovits6Mohamed Fawzy7Lukas Fischer8Necati Findikli9Borut Kovačič10Dejan Ljiljak11Iris Martínez-Rodero12Lodovico Parmegiani13Omar Shebl14Xie Min15Thomas Ebner16Software Competence Center Hagenberg, Data ScienceSoftware Competence Center Hagenberg, Data ScienceAmerican Hospital of Istanbul, In vitro fertilization labViollier AG, Assisted Reproduction TechnologiesHospital General Universitario de Valencia, In vitro fertilization labSoftware Competence Center Hagenberg, Data ScienceSemmelweis University, Department of Obstetrics and Gynecology, Division of Assisted ReproductionIbnSina and Banon IVF Centers, In vitro fertilization labSoftware Competence Center Hagenberg, Data ScienceBahceci Fulya IVF Centre Istanbul, In vitro fertilization labUniversity Medical Centre Maribor, Department of Reproductive Medicine and Gynecological EndocrinologySestre Milosrdnice University Hospital Center, Department of Gynecology and ObstetricsUniversitat Autònoma de Barcelona, Laboratori de Fecundació In VitroNext Fertility GynePro - NextClinic InternationalKepler University Linz, Department of Gynecology, Obstetrics and Gynecological EndocrinologyUniversity Hospital Zurich, Department of Reproductive EndocrinologyKepler University Linz, Department of Gynecology, Obstetrics and Gynecological EndocrinologyAbstract Medical Assisted Reproduction proved its efficacy to treat the vast majority forms of infertility. One of the key procedures in this treatment is the selection and transfer of the embryo with the highest developmental potential. To assess this potential, clinical embryologists routinely work with static images (morphological assessment) or short video sequences (time-lapse annotation). Recently, Artificial Intelligence models were utilized to support the embryo selection procedure. Even though they have proven their great potential in different in vitro fertilization settings, there is still considerable room for improvement. To support the advancement of algorithms in this research field, we built a dataset consisting of static blastocyst images and additional annotations. As such, Gardner criteria annotations, depicting a morphological blastocyst rating scheme, and collected clinical parameters are provided. The presented dataset is intended to be used to train deep learning models on static morphological images to predict Gardner’s criteria and clinical outcomes such as live birth. A benchmark of human expert’s performance in annotating Gardner criteria is provided.https://doi.org/10.1038/s41597-023-02182-3 |
| spellingShingle | Florian Kromp Raphael Wagner Basak Balaban Véronique Cottin Irene Cuevas-Saiz Clara Schachner Peter Fancsovits Mohamed Fawzy Lukas Fischer Necati Findikli Borut Kovačič Dejan Ljiljak Iris Martínez-Rodero Lodovico Parmegiani Omar Shebl Xie Min Thomas Ebner An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization Scientific Data |
| title | An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization |
| title_full | An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization |
| title_fullStr | An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization |
| title_full_unstemmed | An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization |
| title_short | An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization |
| title_sort | annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization |
| url | https://doi.org/10.1038/s41597-023-02182-3 |
| work_keys_str_mv | AT floriankromp anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT raphaelwagner anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT basakbalaban anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT veroniquecottin anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT irenecuevassaiz anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT claraschachner anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT peterfancsovits anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT mohamedfawzy anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT lukasfischer anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT necatifindikli anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT borutkovacic anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT dejanljiljak anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT irismartinezrodero anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT lodovicoparmegiani anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT omarshebl anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT xiemin anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT thomasebner anannotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT floriankromp annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT raphaelwagner annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT basakbalaban annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT veroniquecottin annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT irenecuevassaiz annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT claraschachner annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT peterfancsovits annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT mohamedfawzy annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT lukasfischer annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT necatifindikli annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT borutkovacic annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT dejanljiljak annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT irismartinezrodero annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT lodovicoparmegiani annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT omarshebl annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT xiemin annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization AT thomasebner annotatedhumanblastocystdatasettobenchmarkdeeplearningarchitecturesforinvitrofertilization |