Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

About this Publication
Title
Wavelet decomposition facilitates training on small datasets for medical image classification by deep learning.
Pubmed ID
33502624 (View this publication on the PubMed website)
Digital Object Identifier
Publication
Histochem Cell Biol. 2021 Jan 27
Authors
Masquelin AH, Cheney N, Kinsey CM, Bates JHT
Affiliations
  • University of Vermont, Burlington, VT, USA.
  • Department of Computer Science, University of Vermont, Burlington, VT, USA.
  • Pulmonary and Critical Care, Department of Medicine, University of Vermont, Burlington, VT, USA.
  • University of Vermont, Burlington, VT, USA. jason.h.bates@med.uvm.edu.
Abstract

The adoption of low-dose computed tomography (LDCT) as the standard of care for lung cancer screening results in decreased mortality rates in high-risk population while increasing false-positive rate. Convolutional neural networks provide an ideal opportunity to improve malignant nodule detection; however, due to the lack of large adjudicated medical datasets these networks suffer from poor generalizability and overfitting. Using computed tomography images of the thorax from the National Lung Screening Trial (NLST), we compared discrete wavelet transforms (DWTs) against convolutional layers found in a CNN in order to evaluate their ability to classify suspicious lung nodules as either malignant or benign. We explored the use of the DWT as an alternative to the convolutional operations within CNNs in order to decrease the number of parameters to be estimated during training and reduce the risk of overfitting. We found that multi-level DWT performed better than convolutional layers when multiple kernel resolutions were utilized, yielding areas under the receiver-operating curve (AUC) of 94% and 92%, respectively. Furthermore, we found that multi-level DWT reduced the number of network parameters requiring evaluation when compared to a CNN and had a substantially faster convergence rate. We conclude that utilizing multi-level DWT composition in place of early convolutional layers within a DNN may improve for image classification in data-limited domains.

Related CDAS Studies
Related CDAS Projects