Multitasking Embedding for Embryo Blastocyst Grading Prediction (MEmEBG)
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914473559719936 |
|---|---|
| author | Angabini, Nahid Khoshk Tajgardan, Mohsen Madhavan, Mahesh Varzaneh, Zahra Asghari Khoshkangini, Reza Ebner, Thomas |
| author_facet | Angabini, Nahid Khoshk Tajgardan, Mohsen Madhavan, Mahesh Varzaneh, Zahra Asghari Khoshkangini, Reza Ebner, Thomas |
| contents | Reliable evaluation of blastocyst quality is critical for the success of in vitro fertilization (IVF) treatments. Current embryo grading practices primarily rely on visual assessment of morphological features, which introduces subjectivity, inter-embryologist variability, and challenges in standardizing quality assurance. In this study, we propose a multitask embedding-based approach for the automated analysis and prediction of key blastocyst components, including the trophectoderm (TE), inner cell mass (ICM), and blastocyst expansion (EXP). The method leverages biological and physical characteristics extracted from images of day-5 human embryos. A pretrained ResNet-18 architecture, enhanced with an embedding layer, is employed to learn discriminative representations from a limited dataset and to automatically identify TE and ICM regions along with their corresponding grades, structures that are visually similar and inherently difficult to distinguish. Experimental results demonstrate the promise of the multitask embedding approach and potential for robust and consistent blastocyst quality assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multitasking Embedding for Embryo Blastocyst Grading Prediction (MEmEBG) Angabini, Nahid Khoshk Tajgardan, Mohsen Madhavan, Mahesh Varzaneh, Zahra Asghari Khoshkangini, Reza Ebner, Thomas Computer Vision and Pattern Recognition Artificial Intelligence Reliable evaluation of blastocyst quality is critical for the success of in vitro fertilization (IVF) treatments. Current embryo grading practices primarily rely on visual assessment of morphological features, which introduces subjectivity, inter-embryologist variability, and challenges in standardizing quality assurance. In this study, we propose a multitask embedding-based approach for the automated analysis and prediction of key blastocyst components, including the trophectoderm (TE), inner cell mass (ICM), and blastocyst expansion (EXP). The method leverages biological and physical characteristics extracted from images of day-5 human embryos. A pretrained ResNet-18 architecture, enhanced with an embedding layer, is employed to learn discriminative representations from a limited dataset and to automatically identify TE and ICM regions along with their corresponding grades, structures that are visually similar and inherently difficult to distinguish. Experimental results demonstrate the promise of the multitask embedding approach and potential for robust and consistent blastocyst quality assessment. |
| title | Multitasking Embedding for Embryo Blastocyst Grading Prediction (MEmEBG) |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.13217 |