Abstract

Background

Investigate the potential benefits of sequential deployment of two deep learning (DL) algorithms namely DL-Enhancement (DLE) and DL-based time-of-flight (ToF) (DLT). DLE aims to enhance the rapidly reconstructed ordered-subset-expectation-maximisation algorithm (OSEM) images towards block-sequential-regularised-expectation-maximisation (BSREM) images, whereas DLT aims to improve the quality of BSREM images reconstructed without ToF. As the algorithms differ in their purpose, sequential application may allow benefits from each to be combined. 20 FDG PET-CT scans were performed on a Discovery 710 (D710) and 20 on Discovery MI (DMI; both GE HealthCare). PET data was reconstructed using five combinations of algorithms:1. ToF-BSREM, 2. ToF-OSEM + DLE, 3. OSEM + DLE + DLT, 4. ToF-OSEM + DLE + DLT, 5. ToF-BSREM + DLT. To assess image noise, 30 mm-diameter spherical VOIs were drawn in both lung and liver to measure standard deviation of voxels within the volume. In a blind clinical reading, two experienced readers rated the images on a five-point Likert scale based on lesion detectability, diagnostic confidence, and image quality.

Results

Applying DLE + DLT reduced noise whilst improving lesion detectability, diagnostic confidence, and image reconstruction time. ToF-OSEM + DLE + DLT reconstructions demonstrated an increase in lesion SUVmax of 28 ± 14% (average ± standard deviation) and 11 ± 5% for data acquired on the D710 and DMI, respectively. The same reconstruction scored highest in clinical readings for both lesion detectability and diagnostic confidence for D710.

Conclusions

The combination of DLE and DLT increased diagnostic confidence and lesion detectability compared to ToF-BSREM images. As DLE + DLT used input OSEM images, and because DL inferencing was fast, there was a significant decrease in overall reconstruction time. This could have applications to total body PET.

Details

Title
Sequential deep learning image enhancement models improve diagnostic confidence, lesion detectability, and image reconstruction time in PET
Author
Dedja, Meghi 1 ; Mehranian, Abolfazl 2 ; Bradley, Kevin M. 3 ; Walker, Matthew D. 1 ; Fielding, Patrick A. 3 ; Wollenweber, Scott D. 4 ; Johnsen, Robert 4 ; McGowan, Daniel R. 5   VIAFID ORCID Logo 

1  Oxford University Hospitals, Oxford, UK (GRID:grid.410556.3) (ISNI:0000 0001 0440 1440) 
2  GE HealthCare, Oxford, UK (GRID:grid.420685.d) (ISNI:0000 0001 1940 6527) 
3  Cardiff University, Cardiff, UK (GRID:grid.5600.3) (ISNI:0000 0001 0807 5670) 
4  GE HealthCare, Waukesha, USA (GRID:grid.418143.b) (ISNI:0000 0001 0943 0267) 
5  Oxford University Hospitals, Oxford, UK (GRID:grid.410556.3) (ISNI:0000 0001 0440 1440); University of Oxford, Oxford, UK (GRID:grid.4991.5) (ISNI:0000 0004 1936 8948) 
Pages
28
Publication year
2024
Publication date
Dec 2024
Publisher
Springer Nature B.V.
e-ISSN
21977364
Source type
Scholarly Journal
Language of publication
English
DOI
https://doi.org/10.1186/s40658-024-00632-4
ProQuest document ID
2957625169
Copyright
© The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.