Using transfer learning for a deep learning model observer

W. Murphy; P. Elangovan; M. Halling-Brown; E. Lewis; K. C. Young; D. R. Dance; K. Wells

doi:10.1117/12.2511750

4 March 2019 Using transfer learning for a deep learning model observer

W. Murphy, P. Elangovan, M. Halling-Brown, E. Lewis, K. C. Young, D. R. Dance, K. Wells

Proceedings Volume 10952, Medical Imaging 2019: Image Perception, Observer Performance, and Technology Assessment; 109520E (2019) https://doi.org/10.1117/12.2511750
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

Recent developments in technology assessment and optimization methodology have seen an expansion in the use of Virtual Clinical Trials (VCT) as an alternative to conventional clinical trials. However, the ultimate value gained from VCTs relies on the speed and quality of results generated from the VCT pipeline. In many cases the end-point human observer represents a bottle-neck due to resource and time limitations. This motivates the development of a machine-based observer for key task-based assessment studies. Previous work using Deep Learning for detection and observer studies has shown significant promise, but requires large amounts of data for training. We therefore have built a model observer based on the VGG19 neural network architecture combined with transfer learning to successfully train a TLMO (Transfer Learning Model Observer) that can detect both screen-detected malignancies and simulated lesions in images of 303 x 303 pixels. Our results demonstrate a strong response for the detection of simulated lesions, 4mm in diameter, using the OPTIMAM VCT Toolbox, achieving a sensitivity of 0.78 and a specificity of 0.92. The model has also been tested using well-defined and ill-defined screen-detected masses where it achieved a sensitivity of 0.85 and a specificity of 0.83.

Conference Presentation

Citation Download Citation

W. Murphy, P. Elangovan, M. Halling-Brown, E. Lewis, K. C. Young, D. R. Dance, and K. Wells "Using transfer learning for a deep learning model observer", Proc. SPIE 10952, Medical Imaging 2019: Image Perception, Observer Performance, and Technology Assessment, 109520E (4 March 2019); https://doi.org/10.1117/12.2511750

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available