Supervised learning with low-quality ground truth in early diagnostics of malignant melanoma

Łukasz Szyc; Eduard Dronnik; Sebastian Ahlberg

doi:10.1117/12.2571475

20 August 2020 Supervised learning with low-quality ground truth in early diagnostics of malignant melanoma

Łukasz Szyc, Eduard Dronnik, Sebastian Ahlberg

Proceedings Volume 11469, Emerging Topics in Artificial Intelligence 2020; 114690A (2020) https://doi.org/10.1117/12.2571475
Event: SPIE Nanoscience + Engineering, 2020, Online Only

Abstract

The label noise in AI-aided cancer diagnostics has various origins but often poses a challenge to the data analysis. Misclassified samples in the training set can lead to low accuracy of predictions. In this work, we present strategies of reducing the label noise in the context of dermatofluoroscopy (two-photon fluorescence excitation spectroscopy for early diagnosis of malignant melanoma) and support vector machines (SVMs). The experiments performed on real data set composed of 265 pigmented skin lesions confirm the hypothesis of reduced model accuracy in the presence of label noise. Relabeling and especially removing the supporting vector examples from the training set (100 skin lesions) allow for building models of very high predictive accuracy in diagnosing malignant melanoma as shown on independent data set (165 skin lesions). Furthermore, in the limit of very low data quantity, relabeling of supporting vectors and ensembling are shown to yield models that are more robust to label noise.

Conference Presentation

Citation Download Citation

Łukasz Szyc, Eduard Dronnik, and Sebastian Ahlberg "Supervised learning with low-quality ground truth in early diagnostics of malignant melanoma", Proc. SPIE 11469, Emerging Topics in Artificial Intelligence 2020, 114690A (20 August 2020); https://doi.org/10.1117/12.2571475

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