Reducing scan time of paediatric 99mTc-DMSA SPECT via deep learning

C Lin; Y-C Chang; H-Y Chiu; C-H Cheng; H-M Huang

doi:10.1016/j.crad.2020.11.114

Reducing scan time of paediatric ^99mTc-DMSA SPECT via deep learning

Clin Radiol. 2021 Apr;76(4):315.e13-315.e20. doi: 10.1016/j.crad.2020.11.114. Epub 2020 Dec 16.

Authors

C Lin¹, Y-C Chang², H-Y Chiu¹, C-H Cheng³, H-M Huang⁴

Affiliations

¹ Department of Nuclear Medicine, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Gueishan Dist., Taoyuan, 33305, Taiwan.
² Department of Nuclear Medicine, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Gueishan Dist., Taoyuan, 33305, Taiwan; Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, No. 259, Wenhua 1st Rd., Guishan Dist., Taoyuan, 33302, Taiwan.
³ Department of Paediatrics, Chang Gung University, No. 259, Wenhua 1st Rd, Guishan Dist., Taoyuan, 33302, Taiwan; Department of Paediatrics, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Gueishan Dist., Taoyuan, 33305, Taiwan.
⁴ Institute of Medical Device and Imaging, College of Medicine, National Taiwan University, No.1, Sec. 1, Jen Ai Rd, Zhongzheng Dist., Taipei City, 100, Taiwan. Electronic address: b9003205@gmail.com.

PMID: 33339592
DOI: 10.1016/j.crad.2020.11.114

Abstract

Aim: To investigate the feasibility of reducing the scan time of paediatric technetium 99m (^99mTc) dimercaptosuccinic acid (DMSA) single-photon-emission computed tomographic (SPECT) using a deep learning (DL) method.

Material and methods: A total of 112 paediatric ^99mTc-DMSA renal SPECT scans were analysed retrospectively. Of the 112 examinations, 88 (84 for training and four for validation) were used to train a DL-based model that could generate full-acquisition-time reconstructed SPECT images from half-time acquisition. The remaining 24 examinations were used to evaluate the performance of the trained model.

Results: DL-based SPECT images obtained from half-time acquisition have image quality similar to the standard clinical SPECT images obtained from full-acquisition-time acquisition. Moreover, the accuracy, sensitivity and specificity of the DL-based SPECT images for detection of affected kidneys were 91.7%, 83.3%, and 100%, respectively.

Conclusion: These preliminary results suggest that DL has the potential to reduce the scan time of paediatric ^99mTc-DMSA SPECT imaging while maintaining diagnostic accuracy.

MeSH terms

Adolescent
Child
Child, Preschool
Deep Learning*
Feasibility Studies
Female
Humans
Infant
Kidney / diagnostic imaging*
Kidney Diseases / diagnostic imaging*
Male
Retrospective Studies
Sensitivity and Specificity
Technetium Tc 99m Dimercaptosuccinic Acid*
Time Factors
Tomography, Emission-Computed, Single-Photon / methods*

Substances

Technetium Tc 99m Dimercaptosuccinic Acid