Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis

TL;DR

This paper introduces an Adaptive Curriculum Learning framework to improve thyroid nodule classification by discarding inconsistent labels, enhancing accuracy and reliability in ultrasound image diagnosis.

Contribution

The paper proposes a novel ACL framework that adaptively identifies and discards inconsistent labels, and introduces the TNCD dataset for thyroid nodule classification research.

Findings

ACL outperforms baseline models on TNCD dataset.

Discarding inconsistent labels improves classification accuracy.

The less-is-more principle enhances model performance.

Abstract

Thyroid nodule classification aims at determining whether the nodule is benign or malignant based on a given ultrasound image. However, the label obtained by the cytological biopsy which is the golden standard in clinical medicine is not always consistent with the ultrasound imaging TI-RADS criteria. The information difference between the two causes the existing deep learning-based classification methods to be indecisive. To solve the Inconsistent Label problem, we propose an Adaptive Curriculum Learning (ACL) framework, which adaptively discovers and discards the samples with inconsistent labels. Specifically, ACL takes both hard sample and model certainty into account, and could accurately determine the threshold to distinguish the samples with Inconsistent Label. Moreover, we contribute TNCD: a Thyroid Nodule Classification Dataset to facilitate future related research on the thyroid nodules. Extensive experimental results on TNCD based on three different backbone networks not only demonstrate the superiority of our method but also prove that the less-is-more principle which strategically discards the samples with Inconsistent Label could yield performance gains. Source code and data are available at https://github.com/chenghui-666/ACL/.