Personalized Diagnostic Tool for Thyroid Cancer Classification using Multi-view Ultrasound

TL;DR

This paper introduces a personalized ultrasound-based diagnostic tool for thyroid cancer that effectively integrates multi-view data and adapts to individual patient differences, improving classification accuracy.

Contribution

It presents a novel multi-view classification framework with personalized weighting and a self-supervised contrastive loss, enhancing diagnostic performance over existing methods.

Findings

Outperforms competing methods in accuracy.

Effectively utilizes multi-view ultrasound data.

Improves robustness across patient groups.

Abstract

Over the past decades, the incidence of thyroid cancer has been increasing globally. Accurate and early diagnosis allows timely treatment and helps to avoid over-diagnosis. Clinically, a nodule is commonly evaluated from both transverse and longitudinal views using thyroid ultrasound. However, the appearance of the thyroid gland and lesions can vary dramatically across individuals. Identifying key diagnostic information from both views requires specialized expertise. Furthermore, finding an optimal way to integrate multi-view information also relies on the experience of clinicians and adds further difficulty to accurate diagnosis. To address these, we propose a personalized diagnostic tool that can customize its decision-making process for different patients. It consists of a multi-view classification module for feature extraction and a personalized weighting allocation network that generates optimal weighting for different views. It is also equipped with a self-supervised view-aware contrastive loss to further improve the model robustness towards different patient groups. Experimental results show that the proposed framework can better utilize multi-view information and outperform the competing methods.