EMM-LC Fusion: Enhanced Multimodal Fusion for Lung Cancer Classification

Barret, James and Viana, Thiago ORCID: 0000-0001-9380-4611 (2022) EMM-LC Fusion: Enhanced Multimodal Fusion for Lung Cancer Classification. AI, 3 (3). doi:10.3390/ai3030038

Preview

Text (© 2022 by the authors) ai-03-00038.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (2MB) | Preview

Abstract

Lung cancer (LC) is the most common cause of cancer-related deaths in the UK due to delayed diagnosis. The existing literature establishes a variety of factors which contribute to this, including the misjudgement of anatomical structure by doctors and radiologists. This study set out to develop a solution which utilises multiple modalities in order to detect the presence of LC. A review of the existing literature established failings within methods to exploit rich intermediate feature representations, such that it can capture complex multimodal associations between heterogenous data sources. The methodological approach involved the development of a novel machine learning (ML) model to facilitate quantitative analysis. The proposed solution, named EMM-LC Fusion, extracts intermediate features from a pre-trained modified AlignedXception model and concatenates these with linearly inflated features of Clinical Data Elements (CDE). The implementation was evaluated and compared against existing literature using F1 score, average precision (AP), and area under curve (AUC) as metrics. The findings presented in this study show a statistically significant improvement (p < 0.05) upon the previous fusion method, with an increase in F-Score from 0.402 to 0.508. The significance of this establishes that the extraction of intermediate features produces a fertile environment for the detection of intermodal relationships for the task of LC classification. This research also provides an architecture to facilitate the future implementation of alternative biomarkers for lung cancer, one of the acknowledged limitations of this study.

Item Type:	Article
Article Type:	Article
Uncontrolled Keywords:	deep learning; lung cancer; machine learning; multimodal fusion
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Schools and Research Institutes > School of Business, Computing and Social Sciences
Research Priority Areas:	Applied Business & Technology
Depositing User:	Thiago Viana
Date Deposited:	15 Aug 2022 11:16
Last Modified:	04 Sep 2024 12:30
URI:	https://eprints.glos.ac.uk/id/eprint/11448

University Staff: Request a correction | Repository Editors: Update this record