How Does Image Quality Affect Computer-Aided Diagnosis of Colorectal Polyps?

Thom Scheeve*, Nikoo Dehghani, Quirine E.W. van der Zander, Ayla Thijssen, Ramon Michel Schreuder, Ad A.M. Masclee, Erik J. Schoon, Fons van der Sommen, Peter H.N. de With

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

78 Downloads (Pure)

Abstract

Colorectal cancer (CRC) is one of the leading causes of cancer-related deaths with rising incidence. Since the survival rate of CRC is correlated with the cancer stage at diagnosis, timely detection and adequate treatment strategies are of utmost importance. Technical innovations such as machine learning (ML) and its application in endoscopy show promising results, but the trust of medical doctors in ML is lacking and the 'black box' nature complicates the understanding of such systems in clinical practice. In contrast to CT and MRI, image quality is a limiting factor in especially endoscopic imaging, as it is very operator dependent. However, the influence of image quality on convolutional (deep) neural networks (CNNs) is insufficiently studied in relation to clinical practice and the usage of medical image data for computer-aided detection and diagnosis (CADx) systems. This paper explores the influence of degraded image quality on the performance of CNNs applied to colorectal polyp (CRP) characterization. Five commonly used CNN architectures, from simple to more complex, are employed with a custom classification head for common CRP characterization. To degrade the quality of images, distortions such as noise, blur, and contrast changes are imposed on the data and their influence on the performance degradation is studied for the mentioned CNN architectures. A large prospectively collected in vivo data set, gathered from four Dutch, both academic and community, hospitals is employed. Results for CRP characterization show that promising CNN-based methods are rather susceptible to noise and blur distortions but reasonably resilient to changes in contrast. This implies that image quality needs monitoring and control prior to directly using image data in CNN models, in order to gain trustworthy use of deep learning (DL) models in a clinical setting. We propose that incorporating an image quality indicator in CADx systems will lead to better acceptance of such systems, and is necessary for the safe implementation of DL applications in clinical practice.
Original languageEnglish
Title of host publicationMedical Imaging 2023
Subtitle of host publicationComputer-Aided Diagnosis
EditorsKhan M. Iftekharuddin, Weijie Chen
PublisherSPIE
Volume12465
Edition1
ISBN (Print)9781510660359
DOIs
Publication statusPublished - 1 Jan 2023
EventMedical Imaging 2023: Computer-Aided Diagnosis - San Diego, United States
Duration: 19 Feb 202323 Feb 2023

Publication series

SeriesProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Number124650S
Volume12465
ISSN1605-7422

Conference

ConferenceMedical Imaging 2023: Computer-Aided Diagnosis
Country/TerritoryUnited States
CitySan Diego
Period19/02/2323/02/23

Keywords

  • colorectal cancer
  • Deep learning
  • endoscopic imaging
  • gastroenterology
  • image classification
  • image quality
  • reproducibility

Fingerprint

Dive into the research topics of 'How Does Image Quality Affect Computer-Aided Diagnosis of Colorectal Polyps?'. Together they form a unique fingerprint.

Cite this