MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

JACK KROHMER JUNIOR INVESTIGATOR COMPETITION WINNER: Deep Learning-Based Self Attenuation Correction for Whole-Body PET Imaging

X Dong1, Y Lei1 , T Wang1 , K Higgins1,2 , T Liu1,2 , W Curran1,2 , H Mao2,3 , J Nye3* , X Yang1,2 , (1) Department of Radiation Oncology, Emory University, Atlanta, GA (2)Winship Cancer Institute, Emory University, Atlanta, GA (3)Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA

Presentations

(Sunday, 7/14/2019) 4:00 PM - 6:00 PM

Room: 304ABC

Purpose: Deriving accurate attenuation correction maps remains difficult due to image truncation, inter-scan motion, and erroneous transformation of structural voxel-intensities to PET mu-map. This work presents a deep learning-based attenuation correction (DL-AC) method to derive the non-linear mapping between attenuation corrected PET (AC PET) and non-attenuation corrected PET (NAC PET) images for whole-body PET imaging.

Methods: We propose to integrate residual block minimization into a 3D cycle-consistent generative adversarial networks (cycle GAN) framework to synthesize DL-AC PET from NAC PET. The method learns a transformation that minimizes the difference between DL-AC PET, generated from NAC PET, and AC PET images. It also learns an inverse transformation such that cycle NAC PET image generated from the DL-AC PET is close to the real NAC PET image. We conducted a retrospective study on 25 sets of whole-body PET/CT and evaluated the reliability of proposed method on 10 patients, each with three sequential scans.

Results: In comparing the DL-AC PET with AC PET, the average mean error (ME) and normalized mean square error (NMSE) of the whole-body were -0.01% ±2.91% and 1.21%±1.73%, respectively. In selected regions of normal physiologic uptake (brain, lung, heart, left and right kidney and liver), the average ME were 1.23%±5.16%, -3.79%±7.89%, 2.15%±4.61%, 1.37%±7.01%, 1.08%±6.25% and 0.89%±6.00%, respectively. ME of lesions was 1.41%±4.35%. The average intensity changes measured on sequential PET images with AC and DL-AC on both normal tissues and lesions differ less than 3%. There was no significant difference of the intensity changes between AC and DL-AC PET (p>0.7).

Conclusion: We proposed a novel deep-learning-based approach to correct whole-body PET attenuation and scatter from NAC PET. The method demonstrates excellent quantification accuracy and reliability and is applicable to PET data collected on a hybrid platform (PET/CT or PET/MRI).

Keywords

Not Applicable / None Entered.

Taxonomy

Not Applicable / None Entered.

Contact Email