Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nasr, Mohammad Sadegh, Hajighasemi, Amir, Koomey, Paul, Malidarreh, Parisa Boodaghi, Robben, Michael, Saurav, Jillur Rahman, Shang, Helen H., Huber, Manfred, Luber, Jacob M.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917558706241536
author Nasr, Mohammad Sadegh
Hajighasemi, Amir
Koomey, Paul
Malidarreh, Parisa Boodaghi
Robben, Michael
Saurav, Jillur Rahman
Shang, Helen H.
Huber, Manfred
Luber, Jacob M.
author_facet Nasr, Mohammad Sadegh
Hajighasemi, Amir
Koomey, Paul
Malidarreh, Parisa Boodaghi
Robben, Michael
Saurav, Jillur Rahman
Shang, Helen H.
Huber, Manfred
Luber, Jacob M.
contents In this paper, we introduce a Variational Autoencoder (VAE) based training approach that can compress and decompress cancer pathology slides at a compression ratio of 1:512, which is better than the previously reported state of the art (SOTA) in the literature, while still maintaining accuracy in clinical validation tasks. The compression approach was tested on more common computer vision datasets such as CIFAR10, and we explore which image characteristics enable this compression ratio on cancer imaging data but not generic images. We generate and visualize embeddings from the compressed latent space and demonstrate how they are useful for clinical interpretation of data, and how in the future such latent embeddings can be used to accelerate search of clinical imaging data.
format Preprint
id arxiv_https___arxiv_org_abs_2303_13332
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
Nasr, Mohammad Sadegh
Hajighasemi, Amir
Koomey, Paul
Malidarreh, Parisa Boodaghi
Robben, Michael
Saurav, Jillur Rahman
Shang, Helen H.
Huber, Manfred
Luber, Jacob M.
Image and Video Processing
Computer Vision and Pattern Recognition
Quantitative Methods
In this paper, we introduce a Variational Autoencoder (VAE) based training approach that can compress and decompress cancer pathology slides at a compression ratio of 1:512, which is better than the previously reported state of the art (SOTA) in the literature, while still maintaining accuracy in clinical validation tasks. The compression approach was tested on more common computer vision datasets such as CIFAR10, and we explore which image characteristics enable this compression ratio on cancer imaging data but not generic images. We generate and visualize embeddings from the compressed latent space and demonstrate how they are useful for clinical interpretation of data, and how in the future such latent embeddings can be used to accelerate search of clinical imaging data.
title Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
topic Image and Video Processing
Computer Vision and Pattern Recognition
Quantitative Methods
url https://arxiv.org/abs/2303.13332