MFIF-Net: A Multi-Focal Image Fusion Network for Implantation Outcome Prediction of Blastocyst

Yi Cheng, Tingting Chen, Yaojun Hu, Xiangqian Meng, Zuozhu Liu, Danny Chen, Jian Wu, Haochao Ying
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:250-262, 2024.

Abstract

Accurately predicting implantation outcomes based on blastocyst developmental potential is valuable in in-vitro fertilization (IVF). Clinically, embryologists analyze multiple focal-plane images (FP-images) to comprehensively assess embryo grades, which is extremely cumbersome and easily prone to inconsistency. Developing automatic computer-aided methods for analyzing embryo images is highly desirable. However, effectively fusing multiple FP-images for prediction remains a largely under-explored issue. To this end, we propose a novel Multiple Focal-plane Image Fusion Network, called MFIF-Net, to predict implantation outcomes of blastocyst. Specifically, our MFIF-Net consists of two sub-networks: a Core Image Generation Network (CI-Gen) and a Key Feature Fusion Network (KFFNet). In CI-Gen, we fuse multiple FP-images to generate a core image by pixel-wise weighting since different FP-images can have different focus positions. To further capture key features in each FP-image, we propose KFFNet to extract key information from the FP-images again and fuse them with the core image. In KFFNet, a Fusion Module is designed to capture key information of each FP-image, for which Squeeze Multi-Headed Attention is developed to exchange features and mitigate computationally intensive issues in attention. Comprehensive experiments validate the superiority and the rationality of our MFIF-Net approach over state-of-the-art methods in various metrics. Ablation studies also confirm the positive impact of each component in our MFIF-Net.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-cheng24a, title = {MFIF-Net: A Multi-Focal Image Fusion Network for Implantation Outcome Prediction of Blastocyst}, author = {Cheng, Yi and Chen, Tingting and Hu, Yaojun and Meng, Xiangqian and Liu, Zuozhu and Chen, Danny and Wu, Jian and Ying, Haochao}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {250--262}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/cheng24a/cheng24a.pdf}, url = {https://proceedings.mlr.press/v250/cheng24a.html}, abstract = {Accurately predicting implantation outcomes based on blastocyst developmental potential is valuable in in-vitro fertilization (IVF). Clinically, embryologists analyze multiple focal-plane images (FP-images) to comprehensively assess embryo grades, which is extremely cumbersome and easily prone to inconsistency. Developing automatic computer-aided methods for analyzing embryo images is highly desirable. However, effectively fusing multiple FP-images for prediction remains a largely under-explored issue. To this end, we propose a novel Multiple Focal-plane Image Fusion Network, called MFIF-Net, to predict implantation outcomes of blastocyst. Specifically, our MFIF-Net consists of two sub-networks: a Core Image Generation Network (CI-Gen) and a Key Feature Fusion Network (KFFNet). In CI-Gen, we fuse multiple FP-images to generate a core image by pixel-wise weighting since different FP-images can have different focus positions. To further capture key features in each FP-image, we propose KFFNet to extract key information from the FP-images again and fuse them with the core image. In KFFNet, a Fusion Module is designed to capture key information of each FP-image, for which Squeeze Multi-Headed Attention is developed to exchange features and mitigate computationally intensive issues in attention. Comprehensive experiments validate the superiority and the rationality of our MFIF-Net approach over state-of-the-art methods in various metrics. Ablation studies also confirm the positive impact of each component in our MFIF-Net.} }
Endnote
%0 Conference Paper %T MFIF-Net: A Multi-Focal Image Fusion Network for Implantation Outcome Prediction of Blastocyst %A Yi Cheng %A Tingting Chen %A Yaojun Hu %A Xiangqian Meng %A Zuozhu Liu %A Danny Chen %A Jian Wu %A Haochao Ying %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-cheng24a %I PMLR %P 250--262 %U https://proceedings.mlr.press/v250/cheng24a.html %V 250 %X Accurately predicting implantation outcomes based on blastocyst developmental potential is valuable in in-vitro fertilization (IVF). Clinically, embryologists analyze multiple focal-plane images (FP-images) to comprehensively assess embryo grades, which is extremely cumbersome and easily prone to inconsistency. Developing automatic computer-aided methods for analyzing embryo images is highly desirable. However, effectively fusing multiple FP-images for prediction remains a largely under-explored issue. To this end, we propose a novel Multiple Focal-plane Image Fusion Network, called MFIF-Net, to predict implantation outcomes of blastocyst. Specifically, our MFIF-Net consists of two sub-networks: a Core Image Generation Network (CI-Gen) and a Key Feature Fusion Network (KFFNet). In CI-Gen, we fuse multiple FP-images to generate a core image by pixel-wise weighting since different FP-images can have different focus positions. To further capture key features in each FP-image, we propose KFFNet to extract key information from the FP-images again and fuse them with the core image. In KFFNet, a Fusion Module is designed to capture key information of each FP-image, for which Squeeze Multi-Headed Attention is developed to exchange features and mitigate computationally intensive issues in attention. Comprehensive experiments validate the superiority and the rationality of our MFIF-Net approach over state-of-the-art methods in various metrics. Ablation studies also confirm the positive impact of each component in our MFIF-Net.
APA
Cheng, Y., Chen, T., Hu, Y., Meng, X., Liu, Z., Chen, D., Wu, J. & Ying, H.. (2024). MFIF-Net: A Multi-Focal Image Fusion Network for Implantation Outcome Prediction of Blastocyst. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:250-262 Available from https://proceedings.mlr.press/v250/cheng24a.html.

Related Material