Cross-modality synthesis from CT to PET using FCN and GAN networks for improved automated lesion detection. (February 2019)

• Record Type: Journal Article
• Authors: Ben-Cohen, Avi; Klang, Eyal; Raskin, Stephen P.; Soffer, Shelly; Ben-Haim, Simona; Konen, Eli; Amitai, Michal Marianne; Greenspan, Hayit
• Is Part Of: Engineering applications of artificial intelligence. Volume 78(2019)
• Page Start: 186
• Page End: 194
• Publication Date: 2019-02
• Subjects: Deep learning -- CT -- PET -- GAN -- Image synthesis -- Liver lesion; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2018.11.013
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: In this work we present a novel system for generation of virtual PET images using CT scans. We combine a fully convolutional network (FCN) with a conditional generative adversarial network (GAN) to generate simulated PET data from given input CT data. The synthesized PET can be used for false-positive reduction in lesion detection solutions. Clinically, such solutions may enable lesion detection and drug treatment evaluation in a CT-only environment, thus reducing the need for the more expensive and radioactive PET/CT scan. Our dataset includes 60 PET/CT scans from Sheba Medical center. We used 23 scans for training and 37 for testing. Different schemes to achieve the synthesized output were qualitatively compared. Quantitative evaluation was conducted using an existing lesion detection software, combining the synthesized PET as a false positive reduction layer for the detection of malignant lesions in the liver. Current results look promising showing a 28% reduction in the average false positive per case from 2.9 to 2.1. The suggested solution is comprehensive and can be expanded to additional body organs, and different modalities. Highlights: An automated method to synthesize PET images from CT images is proposed. A combination of cGAN and FCN is shown to achieve the best performance. Custom loss function is shown to improve performance in clinically important regions. Results are provided showing improvement in existing lesion detection frameworks when using the virtual-PET images .