Towards Automation in IVF: Pre-Clinical Validation of a Deep Learning-Based Embryo Grading System during PGT-A Cycles

Abstract

Preimplantation genetic testing for aneuploidies (PGT-A) is arguably the most effective embryo selection strategy. Nevertheless, it requires greater workload, costs, and expertise. Therefore, a quest towards user-friendly, non-invasive strategies is ongoing. Although insufficient to replace PGT-A, embryo morphological evaluation is significantly associated with embryonic competence, but scarcely reproducible. Recently, artificial intelligence-powered analyses have been proposed to objectify and automate image evaluations. iDAScore v1.0 is a deep-learning model based on a 3D convolutional neural network trained on time-lapse videos from implanted and non-implanted blastocysts. It is a decision support system for ranking blastocysts without manual input. This retrospective, pre-clinical, external validation included 3604 blastocysts and 808 euploid transfers from 1232 cycles. All blastocysts were retrospectively assessed through the iDAScore v1.0; therefore, it did not influence embryologists’ decision-making process. iDAScore v1.0 was significantly associated with embryo morphology and competence, although AUCs for euploidy and live-birth prediction were 0.60 and 0.66, respectively, which is rather comparable to embryologists’ performance. Nevertheless, iDAScore v1.0 is objective and reproducible, while embryologists’ evaluations are not. In a retrospective simulation, iDAScore v1.0 would have ranked euploid blastocysts as top quality in 63% of cases with one or more euploid and aneuploid blastocysts, and it would have questioned embryologists’ ranking in 48% of cases with two or more euploid blastocysts and one or more live birth. Therefore, iDAScore v1.0 may objectify embryologists’ evaluations, but randomized controlled trials are required to assess its clinical value.

Enhancing clinical utility: deep learning-based embryo scoring model for non-invasive aneuploidy prediction

“…In contrast, notable differences in KIDScore and Gardner criteria were evident primarily among younger patients. Another study reported AUCs of 0.60 for iDAScore in predicting euploidy, comparable to embryologists' performance [23]. In our investigation, the combined AUC for euploidy prediction incorporating iDAScore and clinical/embryonic factors reached 0.688.…”

Preimplantation genetic testing: A remarkable history of pioneering, technical challenges, innovations, and ethical considerations

“…Morphological assessments have been widely used to increase the odds of selecting highest quality embryos for transfer, but are subjective and can have other limitations. Recent efforts have attempted to improve morphological assessment using artificial intelligence (AI) to increase objectivity and reproducibility in embryos (Cimadomo et al, 2023). These methods show promising associations with euploidy, but require further development, which could be facilitated by the availability of training data for less favorable embryo morphologies (Cimadomo et al, 2023).…”

“…Recent efforts have attempted to improve morphological assessment using artificial intelligence (AI) to increase objectivity and reproducibility in embryos (Cimadomo et al, 2023). These methods show promising associations with euploidy, but require further development, which could be facilitated by the availability of training data for less favorable embryo morphologies (Cimadomo et al, 2023). Higher accuracy may be achieved with AI coupled to time-lapse video to identify euploid blastocysts, and the use of static images combined with time-lapse video data and AI combined with other data can improve accuracy to above 80% (Salih et al, 2023).…”

Criteria for implementing artificial intelligence systems in reproductive medicine

“…All the mentioned references are depicted in Figure 1. Machine learning models are listed in Table 1 [6,7,10,17,18,[27][28][29][31][32][33][34][35][36][37], while those corresponding to the deep learning subset can be found in Table 2 [8,9,[11][12][13][14][15][16][19][20][21][22][23][24]26,[38][39][40][41][42][43]. In these tables, the AI models are described with their sample size, results and limitations.…”