GAN generated model observer for one class detection in SPECT imaging

Disha D. Rao; Maximilian P. Reymann; Patrick Faley; Francesc Massanes; Wesley Gohn; Alexander H. Vija

doi:10.1117/12.2582113

15 February 2021 GAN generated model observer for one class detection in SPECT imaging

Disha D. Rao, Maximilian P. Reymann, Patrick Faley, Francesc Massanes, Wesley Gohn, Alexander H. Vija

Proceedings Volume 11599, Medical Imaging 2021: Image Perception, Observer Performance, and Technology Assessment; 115990G (2021) https://doi.org/10.1117/12.2582113
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Model observers are mathematical models used to perform a specific task, such as lesion detection. In this document, we will restrict ourselves to ideal model observers, which do not try to mimic human performance but try to perform perfect classification. However, we will not be following the usual definition of ideal model observer, which describes the model observer as a statistical classifier between two classes. Instead we will define a GAN network and train it to generate images from class H₀, without lesions, and then use the discriminator of the GAN network as a model observer. Our method relies on pix2pix, which is a type of conditional GAN, the network is first trained to generate SPECT reconstructions-like data from the corresponding CT images. Later, the discriminator is used on simulated lesions to validate is usage as a classifier

Conference Presentation

Citation Download Citation

Disha D. Rao, Maximilian P. Reymann, Patrick Faley, Francesc Massanes, Wesley Gohn, and Alexander H. Vija "GAN generated model observer for one class detection in SPECT imaging", Proc. SPIE 11599, Medical Imaging 2021: Image Perception, Observer Performance, and Technology Assessment, 115990G (15 February 2021); https://doi.org/10.1117/12.2582113

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available