Accelerating Real-Time Imaging for Radiotherapy: Leveraging Multi-GPU Training with PyTorch

Simple item page
dc.contributor.authorObe, Ruth
dc.contributor.authorKaufmann, Brandt
dc.contributor.authorBaird, Kaelen
dc.contributor.authorKadel, Sam
dc.contributor.authorSoltani, Yasmin
dc.contributor.authorCham, Mostafa
dc.contributor.authorGobbert, Matthias
dc.contributor.authorBarajas, Carlos A.
dc.contributor.authorJiang, Zhuoran
dc.contributor.authorSharma, Vijay R.
dc.contributor.authorRen, Lei
dc.contributor.authorPeterson, Stephen W.
dc.contributor.authorPolf, Jerimy C.
dc.date.accessioned2023-11-27T19:56:34Z
dc.date.available2023-11-27T19:56:34Z
dc.date.issued2023-10-02
dc.description2023 Symposium for Undergraduate Research in Data Science, Systems, and Security (REU Symposium 2023); Jacksonville, Florida, USA; December 15-17, 2023
dc.description.abstractProton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mitigate unnecessary radiation exposure in healthy tissues. Realtime imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera’s non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera’s image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch’s flexibility, powerful capabilities in handling sequential data, and enhanced GPU usage. This accelerates the model’s computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7% to over 60%. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple GPUs, which significantly reduced the training time with a minor impact on model accuracy.
dc.description.sponsorshipThis work is supported by the NSF-grant “REU Site: Online Interdisciplinary Big Data Analytics in Science and Engineering” from the National Science Foundation (grant no. OAC–2050943). Co-author Ren acknowledges support from the NIH-grant R01–CA279013. Co-author Cham additionally acknowledges support as HPCF RA. The hardware used in the computational studies is part of the UMBC High Performance Computing Facility (HPCF). The facility is supported by the U.S. National Science Foundation through the MRI program (grant nos. CNS–0821258, CNS–1228778, OAC–1726023, and CNS–1920079) and the SCREMS program (grant no. DMS–0821311), with additional substantial support from the University of Maryland, Baltimore County (UMBC). See hpcf.umbc.edu for more information on HPCF and the projects using its resources.
dc.description.urihttps://hpcf-files.umbc.edu/research/papers/BigDataREU2023Team2REUSymposium.pdf
dc.format.extent8 pages
dc.genreconference papers and proceedings
dc.genrepostprints
dc.identifier.urihttp://hdl.handle.net/11603/30856
dc.language.isoen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Information Systems Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Mathematics and Statistics Department
dc.relation.ispartofUMBC Student Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.subjectUMBC High Performance Computing Facility (HPCF)
dc.titleAccelerating Real-Time Imaging for Radiotherapy: Leveraging Multi-GPU Training with PyTorch
dc.typeText
dcterms.creatorhttps://orcid.org/0000-0003-1745-2292

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BigDataREU2023Team2REUSymposium.pdf
Size:
2.67 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Information Systems Department
UMBC Faculty Collection
UMBC Mathematics and Statistics Department
UMBC Student Collection