Unsupervised tumor detection in Dynamic PET/CT imaging of the prostate.

Authors:
Valerie White
Valerie White
University of British Columbia
Canada
Shay Golan
Shay Golan
Institute of Urology
Israel
Jack Baniel
Jack Baniel
Institute of Urology
Israel
Hanna Bernstine
Hanna Bernstine
Beilinson Hospital
Israel
David Groshar
David Groshar
Technion-Israel Institute of Technology
Israel

Med Image Anal 2019 Jul 6;55:27-40. Epub 2019 Apr 6.

School of Computer Science, Tel Aviv University, Tel Aviv, Israel.

Early detection and localization of prostate tumors pose a challenge to the medical community. Several imaging techniques, including PET, have shown some success. But no robust and accurate solution has yet been reached. This work aims to detect prostate cancer foci in Dynamic PET images using an unsupervised learning approach. The proposed method extracts three feature classes from 4D imaging data that include statistical, kinetic biological and deep features that are learned by a deep stacked convolutional autoencoder. Anomalies, which are classified as tumors, are detected in feature space using density estimation. The proposed algorithm generates promising results for sufficiently large cancer foci in real PET scans imaging where the foci is not viewed by the tomographic devices used for detection.

Download full-text PDF

Source
https://linkinghub.elsevier.com/retrieve/pii/S13618415183030
Publisher Site
http://dx.doi.org/10.1016/j.media.2019.04.001DOI Listing
July 2019
4 Reads

Publication Analysis

Top Keywords

cancer foci
8
learning approach
4
algorithm generates
4
unsupervised learning
4
approach proposed
4
proposed method
4
three feature
4
extracts three
4
proposed algorithm
4
method extracts
4
images unsupervised
4
generates promising
4
aims detect
4
work aims
4
promising large
4
reached work
4
anomalies classified
4
prostate cancer
4
feature classes
4
dynamic pet
4

Similar Publications