PocketNet: A Smaller Neural Network For Medical Image Analysis

Simple item page
dc.contributor.advisorRiviere, Beatrice
dc.contributor.advisorFuentes, David
dc.creatorCelaya, Adrian
dc.date.accessioned2023-06-13T15:50:14Z
dc.date.available2023-06-13T15:50:14Z
dc.date.created2023-05
dc.date.issued2023-04-24
dc.date.submittedMay 2023
dc.date.updated2023-06-13T15:50:14Z
dc.description.abstractMedical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by throttling the growth of the number of channels in convolutional neural networks. We demonstrate that, for a range of segmentation and classification tasks, PocketNet architectures produce results comparable to that of conventional neural networks while reducing the number of parameters by multiple orders of magnitude, using up to 90% less GPU memory, and speeding up training times by up to 40%, thereby allowing such models to be trained and deployed in resource-constrained settings.
dc.format.mimetypeapplication/pdf
dc.identifier.citationCelaya, Adrian. "PocketNet: A Smaller Neural Network For Medical Image Analysis." (2023) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/114903">https://hdl.handle.net/1911/114903</a>.
dc.identifier.urihttps://hdl.handle.net/1911/114903
dc.language.isoeng
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.
dc.subjectNeural network
dc.subjectsegmentation
dc.subjectpattern recognition and classification
dc.titlePocketNet: A Smaller Neural Network For Medical Image Analysis
dc.typeThesis
dc.type.materialText
thesis.degree.departmentComputational and Applied Mathematics
thesis.degree.disciplineEngineering
thesis.degree.grantorRice University
thesis.degree.levelMasters
thesis.degree.nameMaster of Arts
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
CELAYA-DOCUMENT-2023.pdf
Size:
14.05 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Electronic Theses and Dissertations