Takuya Toyonaga1, Dan Shao1,2, Luyao Shi3, Jiazhen Zhang1, Enette Mae Revilla1, David Menard4, Joseph Ankrah4, Kenji Hirata5, Ming-Kai Chen1,4, John A Onofrey1,3,6, Yihuan Lu7. 1. Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA. 2. Guangdong Provincial People's Hospital, Guangzhou, Guangdong, China. 3. Department of Biomedical Engineering, Yale University, New Haven, CT, 06520, USA. 4. Yale New Haven Hospital, New Haven, CT, USA. 5. Department of Diagnostic Imaging, School of Medicine, Hokkaido University, Sapporo, Hokkaido, Japan. 6. Department of Urology, Yale University, New Haven, CT, USA. 7. Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA. yihuan.lu@yale.edu.
Abstract
A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT). METHODS: Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics. RESULTS: µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: - 3.6 ± 4.4% vs. - 1.7 ± 4.5% for 18F-FDG (N = 152), - 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and - 7.3 ± 2.9% vs. - 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., - 8.4 ± 14.5% (OSEMMLAA) vs. - 3.0 ± 15.0% for 18F-FDG, - 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and - 15.9 ± 9.1% vs. - 6.4 ± 6.4% for 18F-Fluciclovine. CONCLUSIONS: The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.
A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT). METHODS: Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics. RESULTS: µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: - 3.6 ± 4.4% vs. - 1.7 ± 4.5% for 18F-FDG (N = 152), - 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and - 7.3 ± 2.9% vs. - 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., - 8.4 ± 14.5% (OSEMMLAA) vs. - 3.0 ± 15.0% for 18F-FDG, - 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and - 15.9 ± 9.1% vs. - 6.4 ± 6.4% for 18F-Fluciclovine. CONCLUSIONS: The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.
Authors: Thorsten D Poeppel; Ina Binse; Stephan Petersenn; Harald Lahner; Matthias Schott; Gerald Antoch; Wolfgang Brandau; Andreas Bockisch; Christian Boy Journal: J Nucl Med Date: 2011-11-09 Impact factor: 10.057
Authors: Ahmadreza Rezaei; Michel Defrise; Girish Bal; Christian Michel; Maurizio Conti; Charles Watson; Johan Nuyts Journal: IEEE Trans Med Imaging Date: 2012-08-09 Impact factor: 10.048
Authors: Claes N Ladefoged; Ian Law; Udunna Anazodo; Keith St Lawrence; David Izquierdo-Garcia; Ciprian Catana; Ninon Burgos; M Jorge Cardoso; Sebastien Ourselin; Brian Hutton; Inés Mérida; Nicolas Costes; Alexander Hammers; Didier Benoit; Søren Holm; Meher Juttukonda; Hongyu An; Jorge Cabello; Mathias Lukas; Stephan Nekolla; Sibylle Ziegler; Matthias Fenchel; Bjoern Jakoby; Michael E Casey; Tammie Benzinger; Liselotte Højgaard; Adam E Hansen; Flemming L Andersen Journal: Neuroimage Date: 2016-12-14 Impact factor: 6.556
Authors: Jeremie Calais; Francesco Ceci; Matthias Eiber; Thomas A Hope; Michael S Hofman; Christoph Rischpler; Tore Bach-Gansmo; Cristina Nanni; Bital Savir-Baruch; David Elashoff; Tristan Grogan; Magnus Dahlbom; Roger Slavik; Jeannine Gartmann; Kathleen Nguyen; Vincent Lok; Hossein Jadvar; Amar U Kishan; Matthew B Rettig; Robert E Reiter; Wolfgang P Fendler; Johannes Czernin Journal: Lancet Oncol Date: 2019-07-30 Impact factor: 41.316