• Home
  • Search
  • P–260 Towards better explainable deep learning models for embryo selection in ART
  • https://doi.org/10.1093/humrep/deab130.259Copy DOI Icon

P–260 Towards better explainable deep learning models for embryo selection in ART

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Abstract Study question Can heatmaps generated by occlusion explain the patterns learned by deep learning (DL) models classifying the embryo viability in ART? Summary answer Occlusion experiments generate heatmaps that reveal which regions in frames of time-lapse video (TLV) are more discriminative for classification and prediction by the DL models. What is known already DL has widely been explored in ART for embryo selection. Depending upon input (video or image), different DL models classifying embryo viability are developed. However, whether the prediction is based on actual input features or random guessing is unknown. The embryo selection in ART is subjective. If the intention is using DL models’ prediction to transfer, freeze or discard the embryo, explanations of how they interpret embryonic development features brings transparency and trust. In other areas, heatmaps are used for explaining DL predictions. The heatmaps can be a tool to understand patterns learned by DL models for embryo selection. Study design, size, duration We trained two separate DL models for predicting the presence of fetal heartbeat for the transferred embryos. We further used occlusion generated heatmaps to explain the predictions. For training, retrospective data was used. The input dataset consisted of 136 TLVs and corresponding patient data for 132 participants (128: single embryo transfers and 8: double embryo transfer) from both IVF and ICSI treatment. Each video was assessed by an embryologist. Participants/materials, setting, methods DL models (A as ResNet–18, B as VGG16) are trained for predicting the presence of fetal heartbeat on a single frame extracted from TLV after day three or later. Model A has a better recall (0.7) compared to B (0.5). Heatmaps explain the reason behind models’ recall rate by visually representing patterns learned by them. Using occlusion filter size 30*30 with stride 14 and size 50*50 with stride 25, we generate heatmaps for both models. Main results and the role of chance The heatmaps generated using occlusion can represent visually the patterns discovered by the DL models when predicting the presence of a fetal heartbeat. Using occlusion filter size 30*30 with stride 14, we verified that Model B has lower recall because the heatmaps show that the model finds redundant features present outside the embryo region in many input frames. It could be interpreted that either the model has not learned relevant patterns or is more robust to noise. This representation of DL models equips us in better decision-making, whether to consider or discard the prediction or rather train the model further, preprocess training data or change network architecture. The heatmaps revealed that for frames where significant patterns learned by the models are within the embryo region, more weight was given to specific features like the inner cell mass, trophectoderm and some parts within the zona pellucida. Moreover, the heat maps generated using occlusion are independent of the underlying model’s architecture as the same experiment settings were used for both models. For occlusion filter size 50*50 with stride 25, the expanse of input regions (in or outside the embryo) considered relevant could be visualized for both models A and B. Limitations, reasons for caution Heatmaps generated by occluding input regions give a visual representation of features in individual frames not directly on videos. Explaining DL models by heatmaps besides occlusion, other techniques (Grad-Cam) exist but were not evaluated. Furthermore, there is no quantitative measure for evaluating whether heatmaps are a good explanation or not. Wider implications of the findings: The heatmaps make the patterns discovered by DL models visually recognized and bring forth the prominent portions of embryo regions. This will again improve understanding and trust in DL models’ predictions. Visual representation of DL models using heatmaps enables interpreting a prediction, performing model analysis and determining scope for improvement. Trial registration number Not applicable

Similar Papers
  • Research Article

P-137 A deep learning model using time-lapse imaging data to predict successful clinical pregnancy and embryo euploidy

  • Jul 03, 2024
  • Human Reproduction
  • R Maekawa +3
  • Dissertation

Backdoor in deep learning: new threats and opportunities

  • Jan 01, 2025
  • Kangjie Chen
  • Research Article

Abstract 184: The utility of deep metric learning for breast cancer identification on mammographic images

  • Jul 01, 2021
  • Cancer Research
  • Justin Du +8
  • PDF
  • Research Article
  • Citations23

Explainable artificial intelligence (XAI) for predicting the need for intubation in methanol-poisoned patients: a study comparing deep and machine learning models

  • Jul 08, 2024
  • Scientific Reports
  • Khadijeh Moulaei +14
  • Research Article

P-172 Retrospective comparison of deep learning versus logistic regression for selecting the best embryo for transfer

  • Jun 01, 2025
  • Human Reproduction
  • T Vermilyea +1
  • Research Article
  • Citations319

Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer.

  • May 21, 2019
  • Human reproduction (Oxford, England)
  • D Tran +3
  • Research Article
  • Citations1

Deep multi-instance learning model based on gadoxetic acid-enhanced MRI for predicting microvascular invasion of hepatocellular carcinoma: a multicenter, retrospective study

  • Oct 22, 2025
  • BMC Cancer
  • Yi Luo +7
  • Research Article
  • Citations37

Explainable artificial intelligence for stroke prediction through comparison of deep learning and machine learning models

  • Dec 28, 2024
  • Scientific Reports
  • Khadijeh Moulaei +5
  • PDF
  • Research Article
  • Citations12

Development and validation of deep learning algorithms for automated eye laterality detection with anterior segment photography

  • Jan 12, 2021
  • Scientific Reports
  • Ce Zheng +9
  • PDF
  • Research Article
  • Citations26

Cross-institutional evaluation of deep learning and radiomics models in predicting microvascular invasion in hepatocellular carcinoma: validity, robustness, and ultrasound modality efficacy comparison

  • Oct 22, 2024
  • Cancer Imaging
  • Weibin Zhang +7
  • Research Article
  • Citations3

Robust RNA secondary structure prediction with a mixture of deep learning and physics-based experts.

  • Jan 06, 2025
  • Biology methods & protocols
  • Xiangyun Qiu
  • Research Article
  • Citations2

Optimizing Deep Learning Models for Luminal and Nonluminal Breast Cancer Classification Using Multidimensional ROI in DCE‐MRI—A Multicenter Study

  • May 01, 2025
  • Cancer Medicine
  • Zhenfeng Huang +8
  • PDF
  • Research Article
  • Citations44

A deep learning approach identifies new ECG features in congenital long QT syndrome

  • May 03, 2022
  • BMC Medicine
  • Simona Aufiero +8
  • Research Article
  • Citations29

Spatial modelling of soil salinity: deep or shallow learning models?

  • Mar 23, 2021
  • Environmental Science and Pollution Research
  • Aliakbar Mohammadifar +3
  • Research Article
  • Citations14

Deep learning and machine learning in CT-based COPD diagnosis: Systematic review and meta-analysis.

  • Apr 01, 2025
  • International journal of medical informatics
  • Qian Wu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.