Deep learning for Dixon MRI-based attenuation correction in PET/MRI of head and neck cancer patients.

Autor: Olin AB; Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark. anders.olin@regionh.dk., Hansen AE; Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark.; Faculty of Health and Medical Science, University of Copenhagen, Copenhagen, Denmark.; Department of Radiology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark., Rasmussen JH; Department of Otorhinolaryngology, Head and Neck Surgery and Audiology, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark., Jakoby B; Siemens Healthcare GmbH, Erlangen, Germany.; University of Surrey, Guildford, Surrey, UK., Berthelsen AK; Department of Oncology, Section of Radiotherapy, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark., Ladefoged CN; Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark., Kjær A; Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark., Fischer BM; Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark.; King's College London and Guy's and St Thomas' PET Centre, School of Biomedical Engineering and Imaging Sciences, King's College London, King's Health Partners, London, UK., Andersen FL; Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark.
Jazyk: angličtina
Zdroj: EJNMMI physics [EJNMMI Phys] 2022 Mar 16; Vol. 9 (1), pp. 20. Date of Electronic Publication: 2022 Mar 16.
DOI: 10.1186/s40658-022-00449-z
Abstrakt: Background: Quantitative whole-body PET/MRI relies on accurate patient-specific MRI-based attenuation correction (AC) of PET, which is a non-trivial challenge, especially for the anatomically complex head and neck region. We used a deep learning model developed for dose planning in radiation oncology to derive MRI-based attenuation maps of head and neck cancer patients and evaluated its performance on PET AC.
Methods: Eleven head and neck cancer patients, referred for radiotherapy, underwent CT followed by PET/MRI with acquisition of Dixon MRI. Both scans were performed in radiotherapy position. PET AC was performed with three different patient-specific attenuation maps derived from: (1) Dixon MRI using a deep learning network (PET Deep ). (2) Dixon MRI using the vendor-provided atlas-based method (PET Atlas ). (3) CT, serving as reference (PET CT ). We analyzed the effect of the MRI-based AC methods on PET quantification by assessing the average voxelwise error within the entire body, and the error as a function of distance to bone/air. The error in mean uptake within anatomical regions of interest and the tumor was also assessed.
Results: The average (± standard deviation) PET voxel error was 0.0 ± 11.4% for PET Deep and -1.3 ± 21.8% for PET Atlas . The error in mean PET uptake in bone/air was much lower for PET Deep (-4%/12%) than for PET Atlas (-15%/84%) and PET Deep also demonstrated a more rapidly decreasing error with distance to bone/air affecting only the immediate surroundings (less than 1 cm). The regions with the largest error in mean uptake were those containing bone (mandible) and air (larynx) for both methods, and the error in tumor mean uptake was -0.6 ± 2.0% for PET Deep and -3.5 ± 4.6% for PET Atlas .
Conclusion: The deep learning network for deriving MRI-based attenuation maps of head and neck cancer patients demonstrated accurate AC and exceeded the performance of the vendor-provided atlas-based method both overall, on a lesion-level, and in vicinity of challenging regions such as bone and air.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje