Deep curriculum learning in task space for multi-class based mammography diagnosis

Jun Luo; Dooman Arefan; Margarita Zuley M.D.; Jules Sumkin; Shandong Wu

doi:10.1117/12.2612617

4 April 2022 Deep curriculum learning in task space for multi-class based mammography diagnosis

Jun Luo, Dooman Arefan, Margarita Zuley M.D., Jules Sumkin, Shandong Wu

Proceedings Volume 12033, Medical Imaging 2022: Computer-Aided Diagnosis; 120330C (2022) https://doi.org/10.1117/12.2612617
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

Mammography is used as a standard screening procedure for the potential patients of breast cancer. Over the past decade, it has been shown that deep learning techniques have succeeded in reaching near-human performance in a number of tasks, and its application in mammography is one of the topics that medical researchers most concentrate on. In this work, we propose an end-to-end Curriculum Learning (CL) strategy in task space for classifying the three categories of Full-Field Digital Mammography (FFDM), namely Malignant, Negative, and False recall. Specifically, our method treats this three-class classification as a “harder” task in terms of CL, and creates an “easier” sub-task of classifying False recall against the combined group of Negative and Malignant. We introduce a loss scheduler to dynamically weight the contribution of the losses from the two tasks throughout the entire training process. We conduct experiments on an FFDM dataset of 1,709 images using 5-fold cross validation. The results show that our curriculum learning strategy can boost the performance for classifying the three categories of FFDM compared to the baseline strategies for model training.

Conference Presentation

Citation Download Citation

Jun Luo, Dooman Arefan, Margarita Zuley M.D., Jules Sumkin, and Shandong Wu "Deep curriculum learning in task space for multi-class based mammography diagnosis", Proc. SPIE 12033, Medical Imaging 2022: Computer-Aided Diagnosis, 120330C (4 April 2022); https://doi.org/10.1117/12.2612617

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