TY - GEN
T1 - Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides Through Variational Autoencoder based Image Compression
AU - Nasr, Mohammad Sadegh
AU - Hajighasemi, Amir
AU - Koomey, Paul
AU - Malidarreh, Parisa Boodaghi
AU - Robben, Michael
AU - Saurav, Jillur Rahman
AU - Shang, Helen H.
AU - Huber, Manfred
AU - Luber, Jacob M.
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - Histopathology cancer slides
KW - autoencoder
KW - clinical image search
KW - image compression
KW - latent space
UR - http://www.scopus.com/inward/record.url?scp=85172163256&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85172163256&partnerID=8YFLogxK
U2 - 10.1109/ISBI53787.2023.10230343
DO - 10.1109/ISBI53787.2023.10230343
M3 - Conference contribution
AN - SCOPUS:85172163256
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
PB - IEEE Computer Society
T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Y2 - 18 April 2023 through 21 April 2023
ER -