Low-count whole-body PET with deep learning in a multicenter and externally validated study

Abstract More widespread use of positron emission tomography (PET) imaging is limited by its high cost and radiation dose. Reductions in PET scan time or radiotracer dosage typically degrade diagnostic image quality (DIQ). Deep-learning-based reconstruction may improve DIQ, but such methods have not...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Akshay S. Chaudhari, Erik Mittra, Guido A. Davidzon, Praveen Gulaka, Harsh Gandhi, Adam Brown, Tao Zhang, Shyam Srinivas, Enhao Gong, Greg Zaharchuk, Hossein Jadvar
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/e86ee2526a4f48489a765c32f2d6fa8a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e86ee2526a4f48489a765c32f2d6fa8a
record_format	dspace
spelling	oai:doaj.org-article:e86ee2526a4f48489a765c32f2d6fa8a2021-12-02T15:09:04ZLow-count whole-body PET with deep learning in a multicenter and externally validated study10.1038/s41746-021-00497-22398-6352https://doaj.org/article/e86ee2526a4f48489a765c32f2d6fa8a2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00497-2https://doaj.org/toc/2398-6352Abstract More widespread use of positron emission tomography (PET) imaging is limited by its high cost and radiation dose. Reductions in PET scan time or radiotracer dosage typically degrade diagnostic image quality (DIQ). Deep-learning-based reconstruction may improve DIQ, but such methods have not been clinically evaluated in a realistic multicenter, multivendor environment. In this study, we evaluated the performance and generalizability of a deep-learning-based image-quality enhancement algorithm applied to fourfold reduced-count whole-body PET in a realistic clinical oncologic imaging environment with multiple blinded readers, institutions, and scanner types. We demonstrate that the low-count-enhanced scans were noninferior to the standard scans in DIQ (p < 0.05) and overall diagnostic confidence (p < 0.001) independent of the underlying PET scanner used. Lesion detection for the low-count-enhanced scans had a high patient-level sensitivity of 0.94 (0.83–0.99) and specificity of 0.98 (0.95–0.99). Interscan kappa agreement of 0.85 was comparable to intrareader (0.88) and pairwise inter-reader agreements (maximum of 0.72). SUV quantification was comparable in the reference regions and lesions (lowest p-value=0.59) and had high correlation (lowest CCC = 0.94). Thus, we demonstrated that deep learning can be used to restore diagnostic image quality and maintain SUV accuracy for fourfold reduced-count PET scans, with interscan variations in lesion depiction, lower than intra- and interreader variations. This method generalized to an external validation set of clinical patients from multiple institutions and scanner types. Overall, this method may enable either dose or exam-duration reduction, increasing safety and lowering the cost of PET imaging.Akshay S. ChaudhariErik MittraGuido A. DavidzonPraveen GulakaHarsh GandhiAdam BrownTao ZhangShyam SrinivasEnhao GongGreg ZaharchukHossein JadvarNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Akshay S. Chaudhari Erik Mittra Guido A. Davidzon Praveen Gulaka Harsh Gandhi Adam Brown Tao Zhang Shyam Srinivas Enhao Gong Greg Zaharchuk Hossein Jadvar Low-count whole-body PET with deep learning in a multicenter and externally validated study
description	Abstract More widespread use of positron emission tomography (PET) imaging is limited by its high cost and radiation dose. Reductions in PET scan time or radiotracer dosage typically degrade diagnostic image quality (DIQ). Deep-learning-based reconstruction may improve DIQ, but such methods have not been clinically evaluated in a realistic multicenter, multivendor environment. In this study, we evaluated the performance and generalizability of a deep-learning-based image-quality enhancement algorithm applied to fourfold reduced-count whole-body PET in a realistic clinical oncologic imaging environment with multiple blinded readers, institutions, and scanner types. We demonstrate that the low-count-enhanced scans were noninferior to the standard scans in DIQ (p < 0.05) and overall diagnostic confidence (p < 0.001) independent of the underlying PET scanner used. Lesion detection for the low-count-enhanced scans had a high patient-level sensitivity of 0.94 (0.83–0.99) and specificity of 0.98 (0.95–0.99). Interscan kappa agreement of 0.85 was comparable to intrareader (0.88) and pairwise inter-reader agreements (maximum of 0.72). SUV quantification was comparable in the reference regions and lesions (lowest p-value=0.59) and had high correlation (lowest CCC = 0.94). Thus, we demonstrated that deep learning can be used to restore diagnostic image quality and maintain SUV accuracy for fourfold reduced-count PET scans, with interscan variations in lesion depiction, lower than intra- and interreader variations. This method generalized to an external validation set of clinical patients from multiple institutions and scanner types. Overall, this method may enable either dose or exam-duration reduction, increasing safety and lowering the cost of PET imaging.
format	article
author	Akshay S. Chaudhari Erik Mittra Guido A. Davidzon Praveen Gulaka Harsh Gandhi Adam Brown Tao Zhang Shyam Srinivas Enhao Gong Greg Zaharchuk Hossein Jadvar
author_facet	Akshay S. Chaudhari Erik Mittra Guido A. Davidzon Praveen Gulaka Harsh Gandhi Adam Brown Tao Zhang Shyam Srinivas Enhao Gong Greg Zaharchuk Hossein Jadvar
author_sort	Akshay S. Chaudhari
title	Low-count whole-body PET with deep learning in a multicenter and externally validated study
title_short	Low-count whole-body PET with deep learning in a multicenter and externally validated study
title_full	Low-count whole-body PET with deep learning in a multicenter and externally validated study
title_fullStr	Low-count whole-body PET with deep learning in a multicenter and externally validated study
title_full_unstemmed	Low-count whole-body PET with deep learning in a multicenter and externally validated study
title_sort	low-count whole-body pet with deep learning in a multicenter and externally validated study
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e86ee2526a4f48489a765c32f2d6fa8a
work_keys_str_mv	AT akshayschaudhari lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT erikmittra lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT guidoadavidzon lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT praveengulaka lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT harshgandhi lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT adambrown lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT taozhang lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT shyamsrinivas lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT enhaogong lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT gregzaharchuk lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy AT hosseinjadvar lowcountwholebodypetwithdeeplearninginamulticenterandexternallyvalidatedstudy
_version_	1718387971970826240

Low-count whole-body PET with deep learning in a multicenter and externally validated study

Ejemplares similares