Comparison of deep learning and human observer performance for detection and characterization of simulated lesions

Ruben De Man; Grace J. Gang; Xin Li; Ge Wang

doi:10.1117/1.JMI.6.2.025503

21 June 2019 Comparison of deep learning and human observer performance for detection and characterization of simulated lesions

Ruben De Man, Grace J. Gang, Xin Li, Ge Wang

Author Affiliations +

Journal of Medical Imaging, Vol. 6, Issue 2, 025503 (June 2019). https://doi.org/10.1117/1.JMI.6.2.025503

Abstract

Detection and characterization of abnormalities in clinical imaging are of utmost importance for patient diagnosis and treatment. We present a comparison of convolutional neural network (CNN) and human observer performance on a simulated lesion detection and characterization task. We apply both conventional performance metrics, including accuracy and nonconventional metrics such as lift charts to perform qualitative and quantitative comparisons of each type of observer. It is determined that the CNN generally outperforms the human observers, particularly at high noise levels. However, high noise correlation reduces the relative performance of the CNN, and human observer performance is comparable to CNN under these conditions. These findings extend into the field of diagnostic radiology, where the adoption of deep learning is starting to become widespread. Consideration of the applications for which deep learning is most effective is of critical importance to this development.

Citation Download Citation

Ruben De Man, Grace J. Gang, Xin Li, and Ge Wang "Comparison of deep learning and human observer performance for detection and characterization of simulated lesions," Journal of Medical Imaging 6(2), 025503 (21 June 2019). https://doi.org/10.1117/1.JMI.6.2.025503

Received: 3 January 2019; Accepted: 30 May 2019; Published: 21 June 2019

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