TY - JOUR
T1 - Ct-less direct correction of attenuation and scatter in the image space using deep learning for whole-body fdg pet
T2 - Potential benefits and pitfalls
AU - Yang, Jaewon
AU - Sohn, Jae Ho
AU - Behr, Spencer C.
AU - Gullberg, Grant T.
AU - Seo, Youngho
N1 - Funding Information:
Disclosures of Conflicts of Interest: J.Y. Activities related to the present article: study supported in part by National Institutes of Health grants R01HL135490 and R01EB026331. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. J.H.S. Activities related to the present article: received Biomedical Imaging for Clinician Scientists T32 grant (NIBIB 2T32EB001631) from National Institute of Biomedical Imaging and Bioengineering. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. S.C.B. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: paid member of AAA advisory board for trial design, small business innovation research grant from CTT. Other relationships: disclosed no relevant relationships. G.T.G. Activities related to the present article: institution received National Institutes of Health grant (1R01HL135490-01: Dynamic Cardiac SPECT; principal investigators, Y.S. and G.T.G.). Activities not related to the present article: paid consultant for Spectrum Dynamics (for consulting on development of reconstruction algorithms for processing the acquisition of SPECT dynamic cardiac data), employed by TF Instruments for work on development of x-ray bi-prism interferometry system, principal investigator for SolvingDynamics for work funded by NSF proposal (1842671: SBIR Phase I: Improving Accuracy and Reducing Scan Time of Dynamic Brain PET”). Other relationships: disclosed no relevant relationships. Y.S. Activities related to the present article: institution received National Institutes of Health grants (R01HL135490 and R01EB026331). Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships.
Publisher Copyright:
© RSNA, 2020.
PY - 2021/3
Y1 - 2021/3
N2 - Purpose: To demonstrate the feasibility of CT-less attenuation and scatter correction (ASC) in the image space using deep learning for whole-body PET, with a focus on the potential benefits and pitfalls. Materials and Methods: In this retrospective study, 110 whole-body fluorodeoxyglucose (FDG) PET/CT studies acquired in 107 patients (mean age ± standard deviation, 58 years ± 18; age range, 11–92 years; 72 females) from February 2016 through January 2018 were randomly collected. A total of 37.3% (41 of 110) of the studies showed metastases, with diverse FDG PET findings throughout the whole body. A U-Net–based network was developed for directly transforming noncorrected PET (PETNC ) into attenuation-and scatter-corrected PET (PETASC ). Deep learning–corrected PET (PETDL ) images were quantitatively evaluated by using the standardized uptake value (SUV) of the normalized root mean square error, the peak signal-to-noise ratio, and the structural similarity index, in addition to a joint histogram for statistical analysis. Qualitative reviews by radiologists revealed the potential benefits and pitfalls of this correction method. Results: The normalized root mean square error (0.21 ± 0.05 [mean SUV ± standard deviation]), mean peak signal-to-noise ratio (36.3 ± 3.0), mean structural similarity index (0.98 ± 0.01), and voxelwise correlation (97.62%) of PETDL demonstrated quantitatively high similarity with PETASC . Radiologist reviews revealed the overall quality of PETDL . The potential benefits of PETDL include a radiation dose reduction on follow-up scans and artifact removal in the regions with attenuation correction– and scatter correction–based artifacts. The pitfalls involve potential false-negative results due to blurring or missing lesions or false-positive results due to pseudo–low-uptake patterns. Conclusion: Deep learning–based direct ASC at whole-body PET is feasible and potentially can be used to overcome the current limitations of CT-based approaches, benefiting patients who are sensitive to radiation from CT.
AB - Purpose: To demonstrate the feasibility of CT-less attenuation and scatter correction (ASC) in the image space using deep learning for whole-body PET, with a focus on the potential benefits and pitfalls. Materials and Methods: In this retrospective study, 110 whole-body fluorodeoxyglucose (FDG) PET/CT studies acquired in 107 patients (mean age ± standard deviation, 58 years ± 18; age range, 11–92 years; 72 females) from February 2016 through January 2018 were randomly collected. A total of 37.3% (41 of 110) of the studies showed metastases, with diverse FDG PET findings throughout the whole body. A U-Net–based network was developed for directly transforming noncorrected PET (PETNC ) into attenuation-and scatter-corrected PET (PETASC ). Deep learning–corrected PET (PETDL ) images were quantitatively evaluated by using the standardized uptake value (SUV) of the normalized root mean square error, the peak signal-to-noise ratio, and the structural similarity index, in addition to a joint histogram for statistical analysis. Qualitative reviews by radiologists revealed the potential benefits and pitfalls of this correction method. Results: The normalized root mean square error (0.21 ± 0.05 [mean SUV ± standard deviation]), mean peak signal-to-noise ratio (36.3 ± 3.0), mean structural similarity index (0.98 ± 0.01), and voxelwise correlation (97.62%) of PETDL demonstrated quantitatively high similarity with PETASC . Radiologist reviews revealed the overall quality of PETDL . The potential benefits of PETDL include a radiation dose reduction on follow-up scans and artifact removal in the regions with attenuation correction– and scatter correction–based artifacts. The pitfalls involve potential false-negative results due to blurring or missing lesions or false-positive results due to pseudo–low-uptake patterns. Conclusion: Deep learning–based direct ASC at whole-body PET is feasible and potentially can be used to overcome the current limitations of CT-based approaches, benefiting patients who are sensitive to radiation from CT.
UR - http://www.scopus.com/inward/record.url?scp=85110971438&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110971438&partnerID=8YFLogxK
U2 - 10.1148/ryai.2020200137
DO - 10.1148/ryai.2020200137
M3 - Article
C2 - 33937860
AN - SCOPUS:85110971438
VL - 3
JO - Radiology: Artificial Intelligence
JF - Radiology: Artificial Intelligence
SN - 2638-6100
IS - 2
M1 - e200137
ER -