Investigating the impact of class-dependent label noise in medical image classification

Bidur Khanal; S.M. Kamrul Hasan; Bishesh Khanal; Cristian A. Linte

doi:10.1117/12.2654420

3 April 2023 Investigating the impact of class-dependent label noise in medical image classification

Bidur Khanal, S.M. Kamrul Hasan, Bishesh Khanal, Cristian A. Linte

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 1246437 (2023) https://doi.org/10.1117/12.2654420
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Label noise is inevitable in medical image databases, which can degrade the actual performance of supervised deep learning models and can bias the model's evaluation. Existing literature show that label noise in one class has minimal impact on model’s performance for another class in natural image classification problems where different target classes have relatively distinct shape and share minimal visual cues for knowledge transfer among the classes. However, it is not clear how class-dependent label noise affects the model’s performance when operating on medical images, for which different output classes can be difficult to distinguish even for experts, and there is a high possibility of knowledge transfer across classes during the training period. We hypothesize and investigate that for medical image classification tasks where different classes share very similar shape with differences only in texture, the noisy label for one class might affect the performance across other classes.

Citation Download Citation

Bidur Khanal, S.M. Kamrul Hasan, Bishesh Khanal, and Cristian A. Linte "Investigating the impact of class-dependent label noise in medical image classification", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 1246437 (3 April 2023); https://doi.org/10.1117/12.2654420

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