Finite element method and hybrid deep learning approaches: high-accuracy lung cancer detection model

• Published in: Multiscale and Multidisciplinary Modeling, Experiments and Design Vol. 7; no. 3; pp. 3017 - 3029
• Main Author: Khalefa, Suhad Jasim
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.07.2024
• Subjects: Characterization and Evaluation of Materials; Engineering; Mathematical Applications in the Physical Sciences; Mechanical Engineering; Numerical and Computational Physics; Original Paper; Simulation; Solid Mechanics; Finite element method; Deep learning; Image segmentation; CNN algorithms; Lung cancer diagnoses
• ISSN: 2520-8160; 2520-8179
• DOI: 10.1007/s41939-024-00385-8

Deep learning has become a crucial instrument for medical research in recent years. Computer science-based mathematics have been extensively used in research to identify and forecast various diseases. This research presents a new model called FEM-DCNN that integrates the Finite Element Method (FEM), Deep Auto Encoder Algorithm (DAE), and Convolutional Neural Network (CNN) techniques. The performance of two deep learning (DL) models was combined rather than just one to enable the execution and prediction of the outcome with greater accuracy. The LIDC-IDRI dataset, which is publicly available, was used in this study; the dataset comprises a CT scan along with annotations that enhance the understanding of the data as well as information pertaining to each CT scan. In this work, an ensemble approach has been developed for solving the issue of lung nodule detection and thus coming up with a robust automated model for lung cancer diagnosis. The objective of DAE is to extract the features of various objects in CT-scan images. The extracted features are then used to build the CNN network. This combination is aimed at precisely determining the boundaries of different objects, allowing for effective image segmentation. The use of FEM helps to decrease computational complexity when integrating DAE and CNN, thereby achieving the objective of this study. The proposed approach in this study outperformed the single CNN algorithms based on the employed performance metrics.