Generating Synthetic Human Blastocyst Images for In-Vitro Fertilization Blastocyst Grading

• URL: http://arxiv.org/abs/2511.18204v1
• Date: Sat, 22 Nov 2025 22:27:01 GMT
• Title: Generating Synthetic Human Blastocyst Images for In-Vitro Fertilization Blastocyst Grading
• Authors: Pavan Narahari, Suraj Rajendran, Lorena Bori, Jonas E. Malmsten, Qiansheng Zhan, Zev Rosenwaks, Nikica Zaninovic, Iman Hajirasouliha,
• Abstract summary: The success of in vitro fertilization (IVF) at many clinics relies on the accurate morphological assessment of day 5 blastocysts.<n>We present the Diffusion Based Imaging Model for Artificial Blastocysts framework, a set of latent diffusion models trained to generate high-fidelity, novel day 5 blastocyst images.<n>Our results show that DIA models generate realistic images that embryologists could not reliably distinguish from real images.
• Score: 0.08994003055762607
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The success of in vitro fertilization (IVF) at many clinics relies on the accurate morphological assessment of day 5 blastocysts, a process that is often subjective and inconsistent. While artificial intelligence can help standardize this evaluation, models require large, diverse, and balanced datasets, which are often unavailable due to data scarcity, natural class imbalance, and privacy constraints. Existing generative embryo models can mitigate these issues but face several limitations, such as poor image quality, small training datasets, non-robust evaluation, and lack of clinically relevant image generation for effective data augmentation. Here, we present the Diffusion Based Imaging Model for Artificial Blastocysts (DIA) framework, a set of latent diffusion models trained to generate high-fidelity, novel day 5 blastocyst images. Our models provide granular control by conditioning on Gardner-based morphological categories and z-axis focal depth. We rigorously evaluated the models using FID, a memorization metric, an embryologist Turing test, and three downstream classification tasks. Our results show that DIA models generate realistic images that embryologists could not reliably distinguish from real images. Most importantly, we demonstrated clear clinical value. Augmenting an imbalanced dataset with synthetic images significantly improved classification accuracy (p < 0.05). Also, adding synthetic images to an already large, balanced dataset yielded statistically significant performance gains, and synthetic data could replace up to 40% of real data in some cases without a statistically significant loss in accuracy. DIA provides a robust solution for mitigating data scarcity and class imbalance in embryo datasets. By generating novel, high-fidelity, and controllable synthetic images, our models can improve the performance, fairness, and standardization of AI embryo assessment tools.

Related papers

• Medical Image Classification on Imbalanced Data Using ProGAN and SMA-Optimized ResNet: Application to COVID-19 [1.270952934304684]
  This study proposes a progressive generative adversarial network to generate synthetic data to supplement the real ones.<n>The proposed model achieves 95.5% and 98.5% accuracy for 4-class and 2-class imbalanced classification problems, respectively.
  arXiv  Detail & Related papers  (2025-12-30T13:26:01Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• SkinDualGen: Prompt-Driven Diffusion for Simultaneous Image-Mask Generation in Skin Lesions [0.0]
  We propose a novel method that leverages the pretrained Stable Diffusion-2.0 model to generate high-quality synthetic skin lesion images.<n>A hybrid dataset combining real and synthetic data markedly enhances the performance of classification and segmentation models.
  arXiv  Detail & Related papers  (2025-07-26T15:00:37Z)
• CytoDiff: AI-Driven Cytomorphology Image Synthesis for Medical Diagnostics [0.9350583142732543]
  We introduce CytoDiff, a stable diffusion model fine-tuned with LoRA weights and guided by few-shot samples that generates high-fidelity synthetic white blood cell images.<n>Using a small, highly imbalanced real dataset, the addition of 5,000 synthetic images per class improved ResNet classifier accuracy from 27% to 78% (+51%)<n>Similarly, CLIP-based classification accuracy increased from 62% to 77% (+15%)
  arXiv  Detail & Related papers  (2025-07-07T14:49:05Z)
• Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis [55.959002385347645]
  Latent Drifting enables diffusion models to be conditioned for medical images fitted for the complex task of counterfactual image generation.<n>We evaluate our method on three public longitudinal benchmark datasets of brain MRI and chest X-rays for counterfactual image generation.
  arXiv  Detail & Related papers  (2024-12-30T01:59:34Z)
• Merging synthetic and real embryo data for advanced AI predictions [69.07284335967019]
  We train two generative models using two datasets-one we created and made publicly available, and one existing public dataset-to generate synthetic embryo images at various cell stages.<n>These were combined with real images to train classification models for embryo cell stage prediction.<n>Our results demonstrate that incorporating synthetic images alongside real data improved classification performance, with the model achieving 97% accuracy compared to 94.5% when trained solely on real data.
  arXiv  Detail & Related papers  (2024-12-02T08:24:49Z)
• Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses [2.9362519537872647]
  We release M-SYNTH, a dataset of cohorts with four breast fibroglandular density distributions imaged at different exposure levels. We find that model performance decreases with increasing breast density and increases with higher mass density, as expected. As exposure levels decrease, AI model performance drops with the highest performance achieved at exposure levels lower than the nominal recommended dose for the breast type.
  arXiv  Detail & Related papers  (2023-10-27T21:14:30Z)
• UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception [62.71374902455154]
  We leverage recent advancements in neural rendering to improve static and dynamic novelview UAV-based image rendering. We demonstrate a considerable performance boost when a state-of-the-art detection model is optimized primarily on hybrid sets of real and synthetic data.
  arXiv  Detail & Related papers  (2023-10-25T00:20:37Z)
• Augmenting medical image classifiers with synthetic data from latent diffusion models [12.077733447347592]
  We show that latent diffusion models can scalably generate images of skin disease. We generate and analyze a new dataset of 458,920 synthetic images produced using several generation strategies.
  arXiv  Detail & Related papers  (2023-08-23T22:34:49Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild [98.48284827503409]
  We develop a textitunified BIQA model and an approach of training it for both synthetic and realistic distortions. We employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs. Experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild.
  arXiv  Detail & Related papers  (2020-05-28T13:35:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.