Sequential deep learning image enhancement models improve diagnostic confidence, lesion detectability, and image reconstruction time in PET

被引：2

作者：

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. ^{[1
,5
]}

机构：

[1] Oxford Univ Hosp, Oxford, England

[2] GE Healthcare, Oxford, England

[3] Cardiff Univ, Cardiff, Wales

[4] GE Healthcare, Waukesha, WI USA

[5] Univ Oxford, Oxford, England

来源：

EJNMMI PHYSICS | 2024年 / 11卷 / 01期

基金：

“创新英国”项目;

关键词：

Positron-emission tomography; Deep learning; Image reconstruction; OF-FLIGHT; PHANTOM; OSEM;

D O I：

10.1186/s40658-024-00632-4

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

BackgroundInvestigate 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.ResultsApplying 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.ConclusionsThe 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.

引用

页数：12

共 21 条

[1] Quantitative comparison of OSEM and penalized likelihood image reconstruction using relative difference penalties for clinical PET [J].