Improving Generation and Evaluation of Long Image Sequences for Embryo Development Prediction
-
Published:2024-01-23
Issue:3
Volume:13
Page:476
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Celard Pedro123ORCID, Seara Vieira Adrián123ORCID, Sorribes-Fdez José Manuel123ORCID, Iglesias Eva Lorenzo123ORCID, Borrajo Lourdes123ORCID
Affiliation:
1. Department of Computer Science, ESEI-Escuela Superior de Ingeniería Informática, Universidade de Vigo, Edificio Politécnico, Campus Universitario As Lagoas s/n, 32004 Ourense, Spain 2. CINBIO, Nanomaterials and Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain 3. SING, Next Generation Computer Systems Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, 36312 Vigo, Spain
Abstract
Generating synthetic time series data, such as videos, presents a formidable challenge as complexity increases when it is necessary to maintain a specific distribution of shown stages. One such case is embryonic development, where prediction and categorization are crucial for anticipating future outcomes. To address this challenge, we propose a Siamese architecture based on diffusion models to generate predictive long-duration embryonic development videos and an evaluation method to select the most realistic video in a non-supervised manner. We validated this model using standard metrics, such as Fréchet inception distance (FID), Fréchet video distance (FVD), structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and mean squared error (MSE). The proposed model generates videos of up to 197 frames with a size of 128×128, considering real input images. Regarding the quality of the videos, all results showed improvements over the default model (FID = 129.18, FVD = 802.46, SSIM = 0.39, PSNR = 28.63, and MSE = 97.46). On the coherence of the stages, a global stage mean squared error of 9.00 was achieved versus the results of 13.31 and 59.3 for the default methods. The proposed technique produces more accurate videos and successfully removes cases that display sudden movements or changes.
Funder
Conselleria de Cultura, Educación e Universidade Xunta de Galicia
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference70 articles.
1. Galić, I., Habijan, M., Leventić, H., and Romić, K. (2023). Machine learning empowering personalized medicine: A comprehensive review of medical image analysis methods. Electronics, 12. 2. A survey on deep learning applied to medical images: From simple artificial neural networks to generative models;Celard;Neural Comput. Appl.,2023 3. Bhalla, D., Rangarajan, K., Chandra, T., Banerjee, S., and Arora, C. (2023). Reproducibility and explainability of deep learning in mammography: A systematic review of literature. Indian J. Radiol. Imaging. 4. Sultan, S.M., Mollika, M.T., Fahim, S.A., Alam, T., Mohammed, A.F.Y., and Islam, T. (2023, January 2–4). Automated cell counting system using improved implicit activation based U-Net (IA-U-Net). Proceedings of the 2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS), Tainan, Taiwan. 5. Use of Deep Neural Networks in the detection and automated classification of lesions using clinical images in ophthalmology, dermatology, and oral medicine—A systematic review;Gomes;J. Digit. Imaging,2023
|
|