Implementation of a Conditional Latent Diffusion-Based Generative Model to Synthetically Create Unlabeled Histopathological Images

Generative image models have revolutionized artificial intelligence by enabling the synthesis of high-quality, realistic images. These models utilize deep learning techniques to learn complex data distributions and generate novel images that closely resemble the training dataset. Recent advancements...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Bioengineering (Basel) Jg. 12; H. 7; S. 764
Hauptverfasser: Rumman, Mahfujul Islam, Ono, Naoaki, Ohuchida, Kenoki, Nasution, Ahmad Kamal, Alqaaf, Muhammad, Altaf-Ul-Amin, Md, Kanaya, Shigehiko
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland MDPI AG 15.07.2025
MDPI
Schlagworte:
Artificial intelligence
Automation
Clustering
Datasets
Deep learning
Diagnostic imaging
Diffusion
Diffusion models
Efficiency
encoder-decoder architectures
Generative adversarial networks
Generative artificial intelligence
Health aspects
Histology, Pathological
Histopathology
histopathology image processing
image generation
Image processing
Image quality
Investigations
Machine learning
Privacy
Synthetic data
Technology application
Japan
encoder-decoder architectures
deep learning
histopathology image processing
image generation
diffusion models
artificial intelligence
ISSN:2306-5354, 2306-5354
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Generative image models have revolutionized artificial intelligence by enabling the synthesis of high-quality, realistic images. These models utilize deep learning techniques to learn complex data distributions and generate novel images that closely resemble the training dataset. Recent advancements, particularly in diffusion models, have led to remarkable improvements in image fidelity, diversity, and controllability. In this work, we investigate the application of a conditional latent diffusion model in the healthcare domain. Specifically, we trained a latent diffusion model using unlabeled histopathology images. Initially, these images were embedded into a lower-dimensional latent space using a Vector Quantized Generative Adversarial Network (VQ-GAN). Subsequently, a diffusion process was applied within this latent space, and clustering was performed on the resulting latent features. The clustering results were then used as a conditioning mechanism for the diffusion model, enabling conditional image generation. Finally, we determined the optimal number of clusters using cluster validation metrics and assessed the quality of the synthetic images through quantitative methods. To enhance the interpretability of the synthetic image generation process, expert input was incorporated into the cluster assignments.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2306-5354
2306-5354
DOI:10.3390/bioengineering12070764