Feature Separation in Diffuse Lung Disease Image Classification by Using Evolutionary Algorithm-Based NAS

In the field of diagnosing lung diseases, the application of neural networks (NNs) in image classification exhibits significant potential. However, NNs are considered “black boxes, ” making it difficult to discern their decision-making processes, thereby leading to skepticism and concern regarding NNs. This compromises model reliability and hampers intelligent medicine's development. To tackle this issue, we introduce the Evolutionary Neural Architecture Search (EvoNAS). In image classification tasks, EvoNAS initially utilizes an Evolutionary Algorithm to explore various Convolutional Neural Networks, ultimately yielding an optimized network that excels at separating between redundant texture features and the most discriminative ones. Retaining the most discriminative features improves classification accuracy, particularly in distinguishing similar features. This approach illuminates the intrinsic mechanics of classification, thereby enhancing the accuracy of the results. Subsequently, we incorporate a Differential Evolution algorithm based on distribution estimation, significantly enhancing search efficiency. Employing visualization techniques, we demonstrate the effectiveness of EvoNAS, endowing the model with interpretability. Finally, we conduct experiments on the diffuse lung disease texture dataset using EvoNAS. Compared to the original network, the classification accuracy increases by 0. 56%. Moreover, our EvoNAS approach demonstrates significant advantages over existing methods in the same dataset.

Authors

• Qing Zhang
• Dan Shao
• Lin Lin UCloud Technology Co. Ltd.
• Guoliang Gong
• Rui Xu Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350116, China
• Shoji Kido
• HongWei Cui

Keywords

• Pulmonary diseases
• Accuracy
• Lung
• Image classification
• Visualization
• Bioinformatics
• Medical diagnostic imaging
• Diseases
• Convolutional neural networks
• Interstitial Lung Disease
• Neural Architecture Search
• Neural Network
• Convolutional Neural Network
• Classification Accuracy
• Classification Task
• Approximate Distribution
• Optimal Network
• Visualization Techniques
• Original Network
• Redundant Features
• Improve Classification Accuracy
• Image Classification Tasks
• Diffuse Disease
• Computed Tomography
• Medical Imaging
• Training Dataset
• Convolutional Layers
• Validation Dataset
• Convolution Kernel
• Number Of Kernels
• Medical Image Classification
• Irrelevant Features
• Incorrect Classification
• Fitness Function
• Multi-scale Feature Fusion
• Osaka University Hospital
• Image Block
• Selected Feature Set
• Diffuse lung disease image classification
• evolutionary algorithm
• feature separation
• neural archi- tecture search
• Humans
• Neural Networks, Computer
• Algorithms
• Lung Diseases
• Image Interpretation, Computer-Assisted
• Tomography, X-Ray Computed