Foundation model-powered deep learning of endometrial histology for predicting the cumulative live birth of an in vitro fertilization cycle
8 affiliations
- 1Department of Obstetrics and Gynaecology, School of Clinical Medicine, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong SAR, China
- 2InnoHK Centre for Translational Stem Cell Biology, The Hong Kong Science and Technology Park, Hong Kong SAR, China
- 3Shenzhen Key Laboratory of Fertility Regulation, The University of Hong Kong Shenzhen Hospital, Shenzhen, China
- 4Department of Electrical and Electronic Engineering, The University of Hong Kong
- 5Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada
- 6Vector Institute for Artificial Intelligence, Toronto, Canada
- 7Canadian Institute for Advanced Research (CIFAR) Artificial Intelligence Chair, Toronto, Canada
- 8School of Biomedical Sciences, The University of Hong Kong, Hong Kong SAR, China
Abstract
Objective and reproducible assessment of endometrial receptivity is essential for optimizing in vitro fertilization (IVF) success, yet traditional histological dating suffers from observer variability. This study investigated whether deep learning of hematoxylin and eosin histology images could support cumulative live birth prediction in IVF. An end-to-end ResNet-18 was compared with a UNI2-h-based pipeline, using UNI2-h as a frozen feature extractor. Ten-fold cross-validation ensembles were developed from natural-cycle endometrial biopsies and evaluated in an internal held-out cohort with live birth outcomes. Additional phase-based evaluation was performed, which tested the performance in distinguishing LH + 7 versus non-LH + 7 phases. A luminal epithelium (LE)-focused design was also assessed to examine whether concentrating on maternal-embryo interface could improve fertility-oriented learning. The whole-slide ResNet-18 model performed well in internal outcome-based testing but near random in external phase-based testing. In contrast, the UNI2-h model with mean pooling and a multilayer perceptron classifier showed less divergent performance, with ensembled AUROCs of 0.74 ± 0.03 in internal outcome-based evaluation, and 0.90 ± 0.05 in external phase-based testing. Despite a smaller training set, LE-focused models retained comparable performance. In internal outcome-based testing, LE-focused ResNet-18 and UNI2-h models achieved AUROCs of 0.71 ± 0.03 and 0.74 ± 0.09 respectively. External phase-based testing yielded AUROCs of 0.80 ± 0.16 for ResNet-18, and 0.84 ± 0.06 for UNI2-h. Grad-CAM review of LE-focused ResNet-18 models showed attention commonly on LE-alone or mixed with adjacent stroma. In multimodal analyses, integrated models incorporating histology significantly outperformed the clinical metadata-only model. Integrated model’s feature weighting showed dominant histology outputs, smaller contributions from estradiol and maternal age, and negligible contributions from progesterone, endometrial thickness, and BMI. These findings support histology-based AI for fertility-oriented endometrial assessment and highlight biologically informed design and repurposed foundation models as promising bases for clinically meaningful prediction. Author summary: Clinicians still lack an objective way to assess whether the endometrium is in an optimal state to support a successful pregnancy. Traditional histological assessment relies on pathologists’ interpretations and vary among observers, while newer molecular tests remain costly and uncertain reliability. In this study, we explored whether artificial intelligence (AI) could extract useful fertility-related information from routine endometrial histology slides. We compared a conventional training approach with a more modern strategy that repurposed an existing AI model with pre-existing histology knowledge. Two testing cohorts, including an internal cohort based on live-birth outcomes and an external cohort evaluated on luteal-phase classification were included. The repurposed approach showed more consistent performance between the two testing cohorts, while the conventional approach fell to near-random in the external phase-based cohort. We also tested whether focusing on endometrial luminal epithelium, where the embryo first makes contact, could improve prediction. Surprisingly, luminal epithelium-focused models performed comparably to the whole-slide approach despite using far fewer training images. These findings support AI-based histology analysis as a promising approach that warrants further refinement for more objective endometrial assessments. Combining foundation models with biologically informed design could provide a useful direction for future fertility-related diagnostics.
Related
- Cumulative-incidence crossover and conditional mortality after definitive surgery for endometrial cancer: a population-based competing-risk analysis
- Spatially guided translation from histology images to transcriptomic profiles using foundation model-driven contrastive learning
- Predicting malignant histology in small renal masses: the role of anatomical and radiological nephrometry scores.
- Predicting concurrent endometrial carcinoma in women with endometrial intraepithelial neoplasia without preoperative suspicion of malignancy
- Predicting cumulative live birth after IVF with growth hormone supplementation: the role of pretreatment duration and machine learning-based models.
BibTeX
@article{xu2026foundation,
title = {{Foundation model-powered deep learning of endometrial histology for predicting the cumulative live birth of an in vitro fertilization cycle}},
author = {Nianbo Xu and Andy Chun Hang Chen and Hanzhang Ruan and Donglin Yang and Renjie Liao and Xiaojuan Qi and Sze Wan Fong and Dandan Cao and Lu Yu and Yuanhua Huang and William Shu Biu Yeung and Ernest Hung Yu Ng and Yin Lau Lee},
journal = {PLOS Digital Health},
year = {2026},
month = sep,
doi = {10.1371/journal.pdig.0001744},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001744},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Foundation model-powered deep learning of endometrial histology for predicting the cumulative live birth of an in vitro fertilization cycle
AU - Nianbo Xu
AU - Andy Chun Hang Chen
AU - Hanzhang Ruan
AU - Donglin Yang
AU - Renjie Liao
AU - Xiaojuan Qi
AU - Sze Wan Fong
AU - Dandan Cao
AU - Lu Yu
AU - Yuanhua Huang
AU - William Shu Biu Yeung
AU - Ernest Hung Yu Ng
AU - Yin Lau Lee
PY - 2026
DA - 2026/09/28
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001744
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001744
AB - Objective and reproducible assessment of endometrial receptivity is essential for optimizing in vitro fertilization (IVF) success, yet traditional histological dating suffers from observer variability. This study investigated whether deep learning of hematoxylin and eosin histology images could support cumulative live birth prediction in IVF. An end-to-end ResNet-18 was compared with a UNI2-h-based pipeline, using UNI2-h as a frozen feature extractor. Ten-fold cross-validation ensembles were developed from natural-cycle endometrial biopsies and evaluated in an internal held-out cohort with live birth outcomes. Additional phase-based evaluation was performed, which tested the performance in distinguishing LH + 7 versus non-LH + 7 phases. A luminal epithelium (LE)-focused design was also assessed to examine whether concentrating on maternal-embryo interface could improve fertility-oriented learning. The whole-slide ResNet-18 model performed well in internal outcome-based testing but near random in external phase-based testing. In contrast, the UNI2-h model with mean pooling and a multilayer perceptron classifier showed less divergent performance, with ensembled AUROCs of 0.74 ± 0.03 in internal outcome-based evaluation, and 0.90 ± 0.05 in external phase-based testing. Despite a smaller training set, LE-focused models retained comparable performance. In internal outcome-based testing, LE-focused ResNet-18 and UNI2-h models achieved AUROCs of 0.71 ± 0.03 and 0.74 ± 0.09 respectively. External phase-based testing yielded AUROCs of 0.80 ± 0.16 for ResNet-18, and 0.84 ± 0.06 for UNI2-h. Grad-CAM review of LE-focused ResNet-18 models showed attention commonly on LE-alone or mixed with adjacent stroma. In multimodal analyses, integrated models incorporating histology significantly outperformed the clinical metadata-only model. Integrated model’s feature weighting showed dominant histology outputs, smaller contributions from estradiol and maternal age, and negligible contributions from progesterone, endometrial thickness, and BMI. These findings support histology-based AI for fertility-oriented endometrial assessment and highlight biologically informed design and repurposed foundation models as promising bases for clinically meaningful prediction. Author summary: Clinicians still lack an objective way to assess whether the endometrium is in an optimal state to support a successful pregnancy. Traditional histological assessment relies on pathologists’ interpretations and vary among observers, while newer molecular tests remain costly and uncertain reliability. In this study, we explored whether artificial intelligence (AI) could extract useful fertility-related information from routine endometrial histology slides. We compared a conventional training approach with a more modern strategy that repurposed an existing AI model with pre-existing histology knowledge. Two testing cohorts, including an internal cohort based on live-birth outcomes and an external cohort evaluated on luteal-phase classification were included. The repurposed approach showed more consistent performance between the two testing cohorts, while the conventional approach fell to near-random in the external phase-based cohort. We also tested whether focusing on endometrial luminal epithelium, where the embryo first makes contact, could improve prediction. Surprisingly, luminal epithelium-focused models performed comparably to the whole-slide approach despite using far fewer training images. These findings support AI-based histology analysis as a promising approach that warrants further refinement for more objective endometrial assessments. Combining foundation models with biologically informed design could provide a useful direction for future fertility-related diagnostics.
SN - 2767-3170
ER -