Junichi Tsuchiya1, Kota Yokoyama2, Ken Yamagiwa2, Ryosuke Watanabe2, Koichiro Kimura2, Mitsuhiro Kishino2, Chung Chan3, Evren Asma3, Ukihide Tateishi2. 1. Department of Diagnostic Radiology and Nuclear Medicine, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8510, Japan. tuwu11@gmail.com. 2. Department of Diagnostic Radiology and Nuclear Medicine, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8510, Japan. 3. Canon Medical Research USA, Inc., 706 N. Deerpath Drive, Vernon Hills, IL, 60061, USA.
Abstract
BACKGROUND: Deep learning (DL)-based image quality improvement is a novel technique based on convolutional neural networks. The aim of this study was to compare the clinical value of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images obtained with the DL method with those obtained using a Gaussian filter. METHODS: Fifty patients with a mean age of 64.4 (range, 19-88) years who underwent 18F-FDG PET/CT between April 2019 and May 2019 were included in the study. PET images were obtained with the DL method in addition to conventional images reconstructed with three-dimensional time of flight-ordered subset expectation maximization and filtered with a Gaussian filter as a baseline for comparison. The reconstructed images were reviewed by two nuclear medicine physicians and scored from 1 (poor) to 5 (excellent) for tumor delineation, overall image quality, and image noise. For the semi-quantitative analysis, standardized uptake values in tumors and healthy tissues were compared between images obtained using the DL method and those obtained with a Gaussian filter. RESULTS: Images acquired using the DL method scored significantly higher for tumor delineation, overall image quality, and image noise compared to baseline (P < 0.001). The Fleiss' kappa value for overall inter-reader agreement was 0.78. The standardized uptake values in tumor obtained by DL were significantly higher than those acquired using a Gaussian filter (P < 0.001). CONCLUSIONS: Deep learning method improves the quality of PET images.
BACKGROUND: Deep learning (DL)-based image quality improvement is a novel technique based on convolutional neural networks. The aim of this study was to compare the clinical value of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images obtained with the DL method with those obtained using a Gaussian filter. METHODS: Fifty patients with a mean age of 64.4 (range, 19-88) years who underwent 18F-FDG PET/CT between April 2019 and May 2019 were included in the study. PET images were obtained with the DL method in addition to conventional images reconstructed with three-dimensional time of flight-ordered subset expectation maximization and filtered with a Gaussian filter as a baseline for comparison. The reconstructed images were reviewed by two nuclear medicine physicians and scored from 1 (poor) to 5 (excellent) for tumor delineation, overall image quality, and image noise. For the semi-quantitative analysis, standardized uptake values in tumors and healthy tissues were compared between images obtained using the DL method and those obtained with a Gaussian filter. RESULTS: Images acquired using the DL method scored significantly higher for tumor delineation, overall image quality, and image noise compared to baseline (P < 0.001). The Fleiss' kappa value for overall inter-reader agreement was 0.78. The standardized uptake values in tumor obtained by DL were significantly higher than those acquired using a Gaussian filter (P < 0.001). CONCLUSIONS: Deep learning method improves the quality of PET images.
Entities:
Keywords:
18F-fluorodeoxyglucose positron emission tomography; Deep learning; Image quality
Authors: Lukas Lenga; Rouben Czwikla; Julian L Wichmann; Doris Leithner; Moritz H Albrecht; Christian Booz; Christophe T Arendt; Ibrahim Yel; Tommaso D'Angelo; Thomas J Vogl; Simon S Martin Journal: Eur J Radiol Date: 2018-07-31 Impact factor: 3.528
Authors: Robert K Heck; Aran M O'Malley; Ethan L Kellum; Timothy B Donovan; Andrew Ellzey; Dexter A Witte Journal: Clin Orthop Relat Res Date: 2007-06 Impact factor: 4.176
Authors: Andreas Hauptmann; Simon Arridge; Felix Lucka; Vivek Muthurangu; Jennifer A Steeden Journal: Magn Reson Med Date: 2018-09-08 Impact factor: 4.668
Authors: Abolfazl Mehranian; Scott D Wollenweber; Matthew D Walker; Kevin M Bradley; Patrick A Fielding; Martin Huellner; Fotis Kotasidis; Kuan-Hao Su; Robert Johnsen; Floris P Jansen; Daniel R McGowan Journal: Eur J Nucl Med Mol Imaging Date: 2022-05-04 Impact factor: 10.057