Classifying chronic obstructive pulmonary disease status using computed tomography imaging and convolutional neural networks: comparison of model input image types and training data severity.

Sara Rezvanjou¹, Amir Moslemi², Samuel Peterson³, Wan-Cheng Tan⁴, James C Hogg⁴, Jean Bourbeau⁵, Joseph M Reinhardt⁶, Miranda Kirby^1,4

¹Toronto Metropolitan University, Department of Physics, Toronto, Ontario, Canada.

²Sunnybrook Research Institute, Toronto, Ontario, Canada.

³VIDA Diagnostics, Coralville, Iowa, United States.

⁴University of British Columbia, Centre for Heart Lung Innovation, Vancouver, British Columbia, Canada.

⁵Montreal Chest Institute of the Royal Victoria Hospital, Montreal, Quebec, Canada.

⁶University of Iowa, Roy J. Carver Department of Biomedical Engineering, Iowa City, United States.

PubMed PMC DOI PDF

Abstract

PURPOSE: Convolutional neural network (CNN)-based models using computed tomography images can classify chronic obstructive pulmonary disease (COPD) with high performance, but various input image types have been investigated, and it is unclear what image types are optimal. We propose a 2D airway-optimized topological multiplanar reformat (tMPR) input image and compare its performance with establish…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.