Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance
BACKGROUND: Preimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main dra...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | AJOG Global Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666577823000503 |
| _version_ | 1797807210132144128 |
|---|---|
| author | Gunawan Bondan Danardono, SKom, BEng Nining Handayani, DVM, MBiomed Claudio Michael Louis, SKom, BEng Arie Adrianus Polim, MD, SpOG, DMAS, MBHRE Batara Sirait, SpOG Gusti Periastiningrum, SSi Szeifoul Afadlal, PhD Arief Boediono, DVM Ivan Sini, MD, FRANZOG, GDRM, MMIS, SpOG |
| author_facet | Gunawan Bondan Danardono, SKom, BEng Nining Handayani, DVM, MBiomed Claudio Michael Louis, SKom, BEng Arie Adrianus Polim, MD, SpOG, DMAS, MBHRE Batara Sirait, SpOG Gusti Periastiningrum, SSi Szeifoul Afadlal, PhD Arief Boediono, DVM Ivan Sini, MD, FRANZOG, GDRM, MMIS, SpOG |
| author_sort | Gunawan Bondan Danardono, SKom, BEng |
| collection | DOAJ |
| description | BACKGROUND: Preimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main drawbacks of preimplantation genetic testing for aneuploidy include its relatively invasive approach and the lack of research studies on the long-term effects of preimplantation genetic testing for aneuploidy. OBJECTIVE: Computer-assisted predictive modeling through machine learning and deep learning algorithms has been proposed to minimize the use of invasive preimplantation genetic testing for aneuploidy. The capability to predict morphologic characteristics of embryo ploidy status creates a meaningful support system for decision-making before further treatment. STUDY DESIGN: Image processing is a component in developing a predictive model specialized in image classification through which a model is able to differentiate images based on unique features. Image processing is obtained through image augmentation to capture segmented embryos and perform feature extraction. Furthermore, multiple machine learning and deep learning algorithms were used to create prediction-based modeling, and all of the prediction models undergo similar model performance assessments to determine the best model prediction algorithm. RESULTS: An efficient artificial intelligence model that can predict embryo ploidy status was developed using image processing through a histogram of oriented gradient and then followed by principal component analysis. The gradient boosting algorithm showed an advantage against other algorithms and yielded an accuracy of 0.74, an aneuploid precision of 0.83, and an aneuploid predictive value (recall) of 0.84. CONCLUSION: This research study proved that machine-assisted technology perceives the embryo differently than human observation and determined that further research on in vitro fertilization is needed. The study finding serves as a basis for developing a better computer-assisted prediction model. |
| first_indexed | 2024-03-13T06:19:08Z |
| format | Article |
| id | doaj.art-e8dedfcb033c46cfae23482eeb6fb39f |
| institution | Directory Open Access Journal |
| issn | 2666-5778 |
| language | English |
| last_indexed | 2024-03-13T06:19:08Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | AJOG Global Reports |
| spelling | doaj.art-e8dedfcb033c46cfae23482eeb6fb39f2023-06-10T04:28:39ZengElsevierAJOG Global Reports2666-57782023-08-0133100209Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a GlanceGunawan Bondan Danardono, SKom, BEng0Nining Handayani, DVM, MBiomed1Claudio Michael Louis, SKom, BEng2Arie Adrianus Polim, MD, SpOG, DMAS, MBHRE3Batara Sirait, SpOG4Gusti Periastiningrum, SSi5Szeifoul Afadlal, PhD6Arief Boediono, DVM7Ivan Sini, MD, FRANZOG, GDRM, MMIS, SpOG8IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Corresponding author: Gunawan Bondan Danardono, SKom, BEng.IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Morula IVF Jakarta Clinic, Jakarta, Indonesia (Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Department of Obstetrics and Gynecology, School of Medicine and Health Sciences, Atma Jaya Catholic University of Indonesia, Jakarta, Indonesia (Dr Polim)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Morula IVF Jakarta Clinic, Jakarta, Indonesia (Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Faculty of Medicine, Department of Obstetrics and Gynaecology, Universitas Kristen Indonesia, Jakarta, Indonesia (Dr Sirait)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Morula IVF Jakarta Clinic, Jakarta, Indonesia (Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Morula IVF Jakarta Clinic, Jakarta, Indonesia (Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Morula IVF Jakarta Clinic, Jakarta, Indonesia (Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Department of Anatomy, Physiology, and Pharmacology, Bogor Agricultural Institute University, Bogor, Indonesia (Dr Boediono)IRSI Research and Training Centre, Jakarta, Indonesia (Mr Danardono, Ms Handayani, Mr Louis, Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini); Morula IVF Jakarta Clinic, Jakarta, Indonesia (Drs Polim and Sirait, Ms Periastiningrum, and Mr Afadlal, Drs Boediono, and Sini)BACKGROUND: Preimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main drawbacks of preimplantation genetic testing for aneuploidy include its relatively invasive approach and the lack of research studies on the long-term effects of preimplantation genetic testing for aneuploidy. OBJECTIVE: Computer-assisted predictive modeling through machine learning and deep learning algorithms has been proposed to minimize the use of invasive preimplantation genetic testing for aneuploidy. The capability to predict morphologic characteristics of embryo ploidy status creates a meaningful support system for decision-making before further treatment. STUDY DESIGN: Image processing is a component in developing a predictive model specialized in image classification through which a model is able to differentiate images based on unique features. Image processing is obtained through image augmentation to capture segmented embryos and perform feature extraction. Furthermore, multiple machine learning and deep learning algorithms were used to create prediction-based modeling, and all of the prediction models undergo similar model performance assessments to determine the best model prediction algorithm. RESULTS: An efficient artificial intelligence model that can predict embryo ploidy status was developed using image processing through a histogram of oriented gradient and then followed by principal component analysis. The gradient boosting algorithm showed an advantage against other algorithms and yielded an accuracy of 0.74, an aneuploid precision of 0.83, and an aneuploid predictive value (recall) of 0.84. CONCLUSION: This research study proved that machine-assisted technology perceives the embryo differently than human observation and determined that further research on in vitro fertilization is needed. The study finding serves as a basis for developing a better computer-assisted prediction model.http://www.sciencedirect.com/science/article/pii/S2666577823000503artificial intelligenceimage processingin vitro fertilizationnoninvasive embryo assessmentpreimplantation genetic testing for aneuploidploidy status |
| spellingShingle | Gunawan Bondan Danardono, SKom, BEng Nining Handayani, DVM, MBiomed Claudio Michael Louis, SKom, BEng Arie Adrianus Polim, MD, SpOG, DMAS, MBHRE Batara Sirait, SpOG Gusti Periastiningrum, SSi Szeifoul Afadlal, PhD Arief Boediono, DVM Ivan Sini, MD, FRANZOG, GDRM, MMIS, SpOG Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance AJOG Global Reports artificial intelligence image processing in vitro fertilization noninvasive embryo assessment preimplantation genetic testing for aneuploid ploidy status |
| title | Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance |
| title_full | Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance |
| title_fullStr | Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance |
| title_full_unstemmed | Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance |
| title_short | Embryo ploidy status classification through computer-assisted morphology assessmentAJOG MFM at a Glance |
| title_sort | embryo ploidy status classification through computer assisted morphology assessmentajog mfm at a glance |
| topic | artificial intelligence image processing in vitro fertilization noninvasive embryo assessment preimplantation genetic testing for aneuploid ploidy status |
| url | http://www.sciencedirect.com/science/article/pii/S2666577823000503 |
| work_keys_str_mv | AT gunawanbondandanardonoskombeng embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT nininghandayanidvmmbiomed embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT claudiomichaellouisskombeng embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT arieadrianuspolimmdspogdmasmbhre embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT batarasiraitspog embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT gustiperiastiningrumssi embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT szeifoulafadlalphd embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT ariefboedionodvm embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance AT ivansinimdfranzoggdrmmmisspog embryoploidystatusclassificationthroughcomputerassistedmorphologyassessmentajogmfmataglance |