Deep Learning-Based Lung Medical Image Recognition

Abstract

Pulmonary nodules serve as critical indicators for early lung cancer diagnosis, making their detection and classification essential. The prevalent use of transfer learning in recognition algorithms often encounters a significant disparity between source and target datasets, which hampers effective feature extraction from pulmonary nodules and degrades performance. An enhanced neural network model leveraging convolutional neural networks is introduced to address this issue. This model integrates a pre-trained GoogLeNet Inception V3 network with a custom-designed feature fusion layer, improving the network’s ability to extract features. To ascertain the optimal configuration, the models were evaluated based on accuracy in various combinations. The experiments conducted on the LUNA16 pulmonary nodule dataset revealed that the refined network model achieved an accuracy of 88.78% and a sensitivity of 87.18%. This represents an increase of 2.7 and 2.22 percentage points in accuracy and sensitivity, respectively, compared to the GoogLeNet Inception V3 algorithm. Further tests across different dataset proportions also yielded superior outcomes, demonstrating enhanced generalization capabilities. These findings can offer objective benchmarks for clinical diagnosis.