Disentangled PET Lesion Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gatsak, Tanya, Abhishek, Kumar, Yedder, Hanene Ben, Taghanaki, Saeid Asgari, Hamarneh, Ghassan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916466204344320
author Gatsak, Tanya
Abhishek, Kumar
Yedder, Hanene Ben
Taghanaki, Saeid Asgari
Hamarneh, Ghassan
author_facet Gatsak, Tanya
Abhishek, Kumar
Yedder, Hanene Ben
Taghanaki, Saeid Asgari
Hamarneh, Ghassan
contents PET imaging is an invaluable tool in clinical settings as it captures the functional activity of both healthy anatomy and cancerous lesions. Developing automatic lesion segmentation methods for PET images is crucial since manual lesion segmentation is laborious and prone to inter- and intra-observer variability. We propose PET-Disentangler, a 3D disentanglement method that uses a 3D UNet-like encoder-decoder architecture to disentangle disease and normal healthy anatomical features with losses for segmentation, reconstruction, and healthy component plausibility. A critic network is used to encourage the healthy latent features to match the distribution of healthy samples and thus encourages these features to not contain any lesion-related features. Our quantitative results show that PET-Disentangler is less prone to incorrectly declaring healthy and high tracer uptake regions as cancerous lesions, since such uptake pattern would be assigned to the disentangled healthy component.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01758
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Disentangled PET Lesion Segmentation
Gatsak, Tanya
Abhishek, Kumar
Yedder, Hanene Ben
Taghanaki, Saeid Asgari
Hamarneh, Ghassan
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
PET imaging is an invaluable tool in clinical settings as it captures the functional activity of both healthy anatomy and cancerous lesions. Developing automatic lesion segmentation methods for PET images is crucial since manual lesion segmentation is laborious and prone to inter- and intra-observer variability. We propose PET-Disentangler, a 3D disentanglement method that uses a 3D UNet-like encoder-decoder architecture to disentangle disease and normal healthy anatomical features with losses for segmentation, reconstruction, and healthy component plausibility. A critic network is used to encourage the healthy latent features to match the distribution of healthy samples and thus encourages these features to not contain any lesion-related features. Our quantitative results show that PET-Disentangler is less prone to incorrectly declaring healthy and high tracer uptake regions as cancerous lesions, since such uptake pattern would be assigned to the disentangled healthy component.
title Disentangled PET Lesion Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.01758