Have a personal or library account? Click to login
Research on Early Prediction of Lung Cancer Based on Deep Learning Cover

Research on Early Prediction of Lung Cancer Based on Deep Learning

By: Zhijun Qu and  Zhongsheng Wang  
Open Access
|Jun 2025

Figures & Tables

Figure 1.

The basic architecture of a convolutional neural network
The basic architecture of a convolutional neural network

Figure 2.

Convolution Process Diagram
Convolution Process Diagram

Figure 3.

Pooling Process Diagram
Pooling Process Diagram

Figure 4.

VGG16 Network Architecture Diagram
VGG16 Network Architecture Diagram

Figure 5.

Residual Connection Structure Diagram
Residual Connection Structure Diagram

Figure 6.

Transformer Architecture Diagram
Transformer Architecture Diagram

Figure 7.

Self-Attention Mechanism Computation Diagram
Self-Attention Mechanism Computation Diagram

Figure 8.

ViT Architecture Diagram
ViT Architecture Diagram

Figure 9.

DeiT Architecture Diagram.
DeiT Architecture Diagram.

Figure 10.

Randomly selected training sample images
Randomly selected training sample images

Figure 11.

Accuracy and Loss Curves of theVgg16
Accuracy and Loss Curves of theVgg16

Figure 12.

Accuracy and Loss Curves of the ResNet50
Accuracy and Loss Curves of the ResNet50

Figure 13.

Accuracy and Loss Curves of the DeiT
Accuracy and Loss Curves of the DeiT

Figure 14.

Confusion Matrix
Confusion Matrix

Figure 15.

Random Test Plot
Random Test Plot

EXPERIMENTAL DATASET TABLE

Training SetValidation SetTest Set
lung_aca3500750750
lung_scc3500750750
lung_n3500750750

Prediction Metrics for Different Models

ModelAcc(%)Average Precision(%)Average Recall(%)Average F1-Score(%)
Vgg1698.4998.4998.4998.49
Resnet5097.5197.5197.5197.51
DeiT99.9699.9699.9699.96
Language: English
Page range: 30 - 42
Published on: Jun 16, 2025
Published by: Xi’an Technological University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2025 Zhijun Qu, Zhongsheng Wang, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.