Adaptive Fusion of Radiomics and Deep Features for Lung Adenocarcinoma Subtype Recognition

TL;DR

This paper introduces a multi-head attentional feature fusion model that combines radiomics and deep features to accurately classify lung adenocarcinoma subtypes, aiding in clinical decision-making.

Contribution

It presents a novel adaptive fusion approach for integrating radiomics and deep features to distinguish lung adenocarcinoma subtypes, including invasive and pre-invasive forms.

Findings

Effective differentiation of LUAD subtypes demonstrated on multi-center data.

Improved accuracy over existing methods in classifying invasive versus pre-invasive LUAD.

Adaptive fusion model learns attention-based discriminative features.

Abstract

The most common type of lung cancer, lung adenocarcinoma (LUAD), has been increasingly detected since the advent of low-dose computed tomography screening technology. In clinical practice, pre-invasive LUAD (Pre-IAs) should only require regular follow-up care, while invasive LUAD (IAs) should receive immediate treatment with appropriate lung cancer resection, based on the cancer subtype. However, prior research on diagnosing LUAD has mainly focused on classifying Pre-IAs/IAs, as techniques for distinguishing different subtypes of IAs have been lacking. In this study, we proposed a multi-head attentional feature fusion (MHA-FF) model for not only distinguishing IAs from Pre-IAs, but also for distinguishing the different subtypes of IAs. To predict the subtype of each nodule accurately, we leveraged both radiomics and deep features extracted from computed tomography images. Furthermore, those features were aggregated through an adaptive fusion module that can learn attention-based discriminative features. The utility of our proposed method is demonstrated here by means of real-world data collected from a multi-center cohort.