Title

Resetting the baseline: CT-based COVID-19 diagnosis with deep transfer learning is not as accurate as widely thought

Document Type

Conference Proceeding

Publication Title

2021 Digital Image Computing: Techniques and Applications (DICTA)

Publisher

IEEE

School

School of Science

RAS ID

40649

Funders

Office of National NIPG Grant NIPG-2021–001, Australian Government

Comments

Altaf, F., Islam, S. M. S., & Akhtar, N. (2021, November-December). Resetting the baseline: CT-based COVID-19 diagnosis with deep transfer learning is not as accurate as widely thought [Paper presentation]. 2021 Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, Australia.

https://doi.org/10.1109/DICTA52665.2021.9647158

Abstract

Deep learning is gaining instant popularity in computer aided diagnosis of COVID-19. Due to the high sensitivity of Computed Tomography (CT) to this disease, CT-based COVID-19 detection with visual models is currently at the forefront of medical imaging research. Outcomes published in this direction are frequently claiming highly accurate detection under deep transfer learning. This is leading medical technologists to believe that deep transfer learning is the mainstream solution for the problem. However, our critical analysis of the literature reveals an alarming performance disparity between different published results. Hence, we conduct a systematic thorough investigation to analyze the effectiveness of deep transfer learning for COVID-19 detection with CT images. Exploring 14 state-of-the-art visual models with over 200 model training sessions, we conclusively establish that the published literature is frequently overestimating transfer learning performance for the problem, even in the prestigious scientific sources. The roots of overestimation trace back to inappropriate data curation. We also provide case studies that consider more realistic scenarios, and establish transparent baselines for the problem. We hope that our reproducible investigation will help in curbing hype-driven claims for the critical problem of COVID-19 diagnosis, and pave the way for a more transparent performance evaluation of techniques for CT-based COVID-19 detection.

DOI

10.1109/DICTA52665.2021.9647158

Access Rights

free_to_read

Research Themes

Health

Priority Areas

Prevention, detection and management of cancer and other chronic diseases

Share

 
COinS