Reza Piri1,2, Lars Edenbrandt3,4, Måns Larsson5, Olof Enqvist5,6, Sofie Skovrup7, Kasper Karmark Iversen8,9, Babak Saboury10,11,12, Abass Alavi10, Oke Gerke7,13, Poul Flemming Høilund-Carlsen7,13. 1. Department of Nuclear Medicine, Odense University Hospital, 5000, Odense C, Denmark. reza.piri2@rsyd.dk. 2. Department of Clinical Research, University of Southern Denmark, Odense, Denmark. reza.piri2@rsyd.dk. 3. Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden. 4. Department of Clinical Physiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden. 5. Eigenvision AB, Malmö, Sweden. 6. Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden. 7. Department of Nuclear Medicine, Odense University Hospital, 5000, Odense C, Denmark. 8. Department of Cardiology, Herlev and Gentofte Hospital, Copenhagen, Denmark. 9. Department of Emergency Medicine, Herlev and Gentofte Hospital, Copenhagen, Denmark. 10. Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, PA, USA. 11. Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MD, USA. 12. Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health (NIH), Bethesda, MD, USA. 13. Department of Clinical Research, University of Southern Denmark, Odense, Denmark.
Abstract
BACKGROUND: Artificial intelligence (AI) is known to provide effective means to accelerate and facilitate clinical and research processes. So in this study it was aimed to compare a AI-based method for cardiac segmentation in positron emission tomography/computed tomography (PET/CT) scans with manual segmentation to assess global cardiac atherosclerosis burden. METHODS: A trained convolutional neural network (CNN) was used for cardiac segmentation in 18F-sodium fluoride PET/CT scans of 29 healthy volunteers and 20 angina pectoris patients and compared with manual segmentation. Parameters for segmented volume (Vol) and mean, maximal, and total standardized uptake values (SUVmean, SUVmax, SUVtotal) were analyzed by Bland-Altman Limits of Agreement. Repeatability with AI-based assessment of the same scans is 100%. Repeatability (same conditions, same operator) and reproducibility (same conditions, two different operators) of manual segmentation was examined by re-segmentation in 25 randomly selected scans. RESULTS: Mean (± SD) values with manual vs. CNN-based segmentation were Vol 617.65 ± 154.99 mL vs 625.26 ± 153.55 mL (P = .21), SUVmean 0.69 ± 0.15 vs 0.69 ± 0.15 (P = .26), SUVmax 2.68 ± 0.86 vs 2.77 ± 1.05 (P = .34), and SUVtotal 425.51 ± 138.93 vs 427.91 ± 132.68 (P = .62). Limits of agreement were - 89.42 to 74.2, - 0.02 to 0.02, - 1.52 to 1.32, and - 68.02 to 63.21, respectively. Manual segmentation lasted typically 30 minutes vs about one minute with the CNN-based approach. The maximal deviation at manual re-segmentation was for the four parameters 0% to 0.5% with the same and 0% to 1% with different operators. CONCLUSION: The CNN-based method was faster and provided values for Vol, SUVmean, SUVmax, and SUVtotal comparable to the manually obtained ones. This AI-based segmentation approach appears to offer a more reproducible and much faster substitute for slow and cumbersome manual segmentation of the heart.
BACKGROUND: Artificial intelligence (AI) is known to provide effective means to accelerate and facilitate clinical and research processes. So in this study it was aimed to compare a AI-based method for cardiac segmentation in positron emission tomography/computed tomography (PET/CT) scans with manual segmentation to assess global cardiac atherosclerosis burden. METHODS: A trained convolutional neural network (CNN) was used for cardiac segmentation in 18F-sodium fluoride PET/CT scans of 29 healthy volunteers and 20 angina pectoris patients and compared with manual segmentation. Parameters for segmented volume (Vol) and mean, maximal, and total standardized uptake values (SUVmean, SUVmax, SUVtotal) were analyzed by Bland-Altman Limits of Agreement. Repeatability with AI-based assessment of the same scans is 100%. Repeatability (same conditions, same operator) and reproducibility (same conditions, two different operators) of manual segmentation was examined by re-segmentation in 25 randomly selected scans. RESULTS: Mean (± SD) values with manual vs. CNN-based segmentation were Vol 617.65 ± 154.99 mL vs 625.26 ± 153.55 mL (P = .21), SUVmean 0.69 ± 0.15 vs 0.69 ± 0.15 (P = .26), SUVmax 2.68 ± 0.86 vs 2.77 ± 1.05 (P = .34), and SUVtotal 425.51 ± 138.93 vs 427.91 ± 132.68 (P = .62). Limits of agreement were - 89.42 to 74.2, - 0.02 to 0.02, - 1.52 to 1.32, and - 68.02 to 63.21, respectively. Manual segmentation lasted typically 30 minutes vs about one minute with the CNN-based approach. The maximal deviation at manual re-segmentation was for the four parameters 0% to 0.5% with the same and 0% to 1% with different operators. CONCLUSION: The CNN-based method was faster and provided values for Vol, SUVmean, SUVmax, and SUVtotal comparable to the manually obtained ones. This AI-based segmentation approach appears to offer a more reproducible and much faster substitute for slow and cumbersome manual segmentation of the heart.
Authors: Sarah Lindgren Belal; May Sadik; Reza Kaboteh; Olof Enqvist; Johannes Ulén; Mads H Poulsen; Jane Simonsen; Poul F Høilund-Carlsen; Lars Edenbrandt; Elin Trägårdh Journal: Eur J Radiol Date: 2019-02-01 Impact factor: 3.528
Authors: David Haro Alonso; Miles N Wernick; Yongyi Yang; Guido Germano; Daniel S Berman; Piotr Slomka Journal: J Nucl Cardiol Date: 2018-03-14 Impact factor: 5.952
Authors: Ernest V Garcia; J Larry Klein; Valeria Moncayo; C David Cooke; Christian Del'Aune; Russell Folks; Liudmila Verdes Moreiras; Fabio Esteves Journal: J Nucl Cardiol Date: 2018-09-12 Impact factor: 5.952
Authors: Chengyi Zheng; Benjamin C Sun; Yi-Lin Wu; Maros Ferencik; Ming-Sum Lee; Rita F Redberg; Aniket A Kawatkar; Visanee V Musigdilok; Adam L Sharp Journal: J Nucl Cardiol Date: 2020-11-05 Impact factor: 3.872