1
|
Wang J, Yin J, Nguyen MH, Wang J, Xu W. Editorial: Big scientific data analytics on HPC and cloud. Front Big Data 2024; 7:1353988. [PMID: 38449567 PMCID: PMC10912602 DOI: 10.3389/fdata.2024.1353988] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Accepted: 01/26/2024] [Indexed: 03/08/2024] Open
Affiliation(s)
- Jianwu Wang
- University of Maryland, Baltimore County, Baltimore, MD, United States
| | - Junqi Yin
- Oak Ridge National Laboratory (DOE), Oak Ridge, TN, United States
| | - Mai H. Nguyen
- University of California, San Diego, La Jolla, CA, United States
| | - Jingbo Wang
- Australian National University, Canberra, ACT, Australia
| | - Weijia Xu
- The University of Texas at Austin, Austin, TX, United States
| |
Collapse
|
2
|
Wassermann C, Mueller F, Dey T, Lambertus J, Schug D, Schulz V, Miller J. High throughput software-based gradient tree boosting positioning for PET systems. Biomed Phys Eng Express 2021; 7. [PMID: 34229316 DOI: 10.1088/2057-1976/ac11c0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Accepted: 07/06/2021] [Indexed: 11/12/2022]
Abstract
The supervised machine learning technique Gradient Tree Boosting (GTB) has shown good accuracy for position estimation of gamma interaction in PET crystals for bench-top experiments while its computational requirements can easily be adjusted. Transitioning to preclinical and clinical applications requires near real-time processing in the scale of full PET systems. In this work, a high throughput GTB-based singles positioning C++ implementation is proposed and a series of optimizations are evaluated regarding their effect on the achievable processing throughput. Moreover, the crucial feature and parameter selection for GTB is investigated for the segmented detectors of the Hyperion IIDPET insert with two main models and a range of GTB hyperparameters. The proposed framework achieves singles positioning throughputs of more than 9.5 GB/s for smaller models and of 240 MB/s for more complex models on a recent Intel Skylake server. Detailed throughput analysis reveals the key performance limiting factors, and an empirical throughput model is derived to guide the GTB model selection process and scanner design decisions. The throughput model allows for throughput estimations with a mean absolute error (MAE) of 175.78 MB/s.
Collapse
Affiliation(s)
- Christian Wassermann
- High Performance Computing Group, Computational Science and Engineering Division, IT Center, RWTH Aachen University, 52074 Aachen, Germany
| | - Florian Mueller
- Department of Physics of Molecular Imaging Systems, Institute for Experimental Molecular Imaging, RWTH Aachen University, 52074 Aachen, Germany
| | - Thomas Dey
- Department of Physics of Molecular Imaging Systems, Institute for Experimental Molecular Imaging, RWTH Aachen University, 52074 Aachen, Germany.,Faculty 05 Electrical Engineering and Information Technology, FH Aachen University of Applied Sciences, 52074 Aachen, Germany
| | - Janko Lambertus
- Department of Physics of Molecular Imaging Systems, Institute for Experimental Molecular Imaging, RWTH Aachen University, 52074 Aachen, Germany
| | - David Schug
- Department of Physics of Molecular Imaging Systems, Institute for Experimental Molecular Imaging, RWTH Aachen University, 52074 Aachen, Germany.,Hyperion Hybrid Imaging Systems GmbH, 52074 Aachen, Germany
| | - Volkmar Schulz
- Department of Physics of Molecular Imaging Systems, Institute for Experimental Molecular Imaging, RWTH Aachen University, 52074 Aachen, Germany.,Hyperion Hybrid Imaging Systems GmbH, 52074 Aachen, Germany.,Physics Institute III B, RWTH Aachen University, 52074 Aachen, Germany.,Fraunhofer Institute for Digital Medicine MEVIS, 52074 Aachen, Germany
| | - Julian Miller
- High Performance Computing Group, Computational Science and Engineering Division, IT Center, RWTH Aachen University, 52074 Aachen, Germany
| |
Collapse
|