AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification
Lung cancer is a leading cause of mortality worldwide, and early detection is crucial in improving treatment outcomes and reducing death rates. However, diagnosing medical images, such as Computed Tomography scans (CT scans), is complex and requires a high level of expertise. This study focuses on d...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/12/1/18 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342730569777152 |
|---|---|
| author | Rapeepat Klangbunrueang Pongsathon Pookduang Wirapong Chansanam Tassanee Lunrasri |
| author_facet | Rapeepat Klangbunrueang Pongsathon Pookduang Wirapong Chansanam Tassanee Lunrasri |
| author_sort | Rapeepat Klangbunrueang |
| collection | DOAJ |
| description | Lung cancer is a leading cause of mortality worldwide, and early detection is crucial in improving treatment outcomes and reducing death rates. However, diagnosing medical images, such as Computed Tomography scans (CT scans), is complex and requires a high level of expertise. This study focuses on developing and evaluating the performance of Convolutional Neural Network (CNN) models, specifically the Visual Geometry Group 16 (VGG16) architecture, to classify lung cancer CT scan images into three categories: Normal, Benign, and Malignant. The dataset used consists of 1097 CT images from 110 patients, categorized according to these severity levels. The research methodology began with data collection and preparation, followed by training and testing the VGG16 model and comparing its performance with other CNN architectures, including Residual Network with 50 layers (ResNet50), Inception Version 3 (InceptionV3), and Mobile Neural Network Version 2 (MobileNetV2). The experimental results indicate that VGG16 achieved the highest classification performance, with a Test Accuracy of 98.18%, surpassing the other models. This accuracy highlights VGG16’s strong potential as a supportive diagnostic tool in medical imaging. However, a limitation of this study is the dataset size, which may reduce model accuracy when applied to new data. Future studies should consider increasing the dataset size, using Data Augmentation techniques, fine-tuning model parameters, and employing advanced models such as 3D CNN or Vision Transformers. Additionally, incorporating Gradient-weighted Class Activation Mapping (Grad-CAM) to interpret model decisions would enhance transparency and reliability. This study confirms the potential of CNNs, particularly VGG16, for classifying lung cancer CT images and provides a foundation for further development in medical applications. |
| format | Article |
| id | doaj-art-04e7db9c4d274f7fbb6ed71c407c6c09 |
| institution | Kabale University |
| issn | 2227-9709 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj-art-04e7db9c4d274f7fbb6ed71c407c6c092025-08-20T03:43:16ZengMDPI AGInformatics2227-97092025-02-011211810.3390/informatics12010018AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image ClassificationRapeepat Klangbunrueang0Pongsathon Pookduang1Wirapong Chansanam2Tassanee Lunrasri3Department of Information Science, Faculty of Humanities and Social Sciences, Khon Kaen University, Khon Kaen 40002, ThailandDepartment of Information Science, Faculty of Humanities and Social Sciences, Khon Kaen University, Khon Kaen 40002, ThailandDepartment of Information Science, Faculty of Humanities and Social Sciences, Khon Kaen University, Khon Kaen 40002, ThailandDepartment of Information Systems, Faculty of Business Administration and Information Technology, Rajamangala University of Technology Isan, Khon Kaen Campus, Khon Kaen 40000, ThailandLung cancer is a leading cause of mortality worldwide, and early detection is crucial in improving treatment outcomes and reducing death rates. However, diagnosing medical images, such as Computed Tomography scans (CT scans), is complex and requires a high level of expertise. This study focuses on developing and evaluating the performance of Convolutional Neural Network (CNN) models, specifically the Visual Geometry Group 16 (VGG16) architecture, to classify lung cancer CT scan images into three categories: Normal, Benign, and Malignant. The dataset used consists of 1097 CT images from 110 patients, categorized according to these severity levels. The research methodology began with data collection and preparation, followed by training and testing the VGG16 model and comparing its performance with other CNN architectures, including Residual Network with 50 layers (ResNet50), Inception Version 3 (InceptionV3), and Mobile Neural Network Version 2 (MobileNetV2). The experimental results indicate that VGG16 achieved the highest classification performance, with a Test Accuracy of 98.18%, surpassing the other models. This accuracy highlights VGG16’s strong potential as a supportive diagnostic tool in medical imaging. However, a limitation of this study is the dataset size, which may reduce model accuracy when applied to new data. Future studies should consider increasing the dataset size, using Data Augmentation techniques, fine-tuning model parameters, and employing advanced models such as 3D CNN or Vision Transformers. Additionally, incorporating Gradient-weighted Class Activation Mapping (Grad-CAM) to interpret model decisions would enhance transparency and reliability. This study confirms the potential of CNNs, particularly VGG16, for classifying lung cancer CT images and provides a foundation for further development in medical applications.https://www.mdpi.com/2227-9709/12/1/18lung cancer image classificationCT scansconvolutional neural network (CNN)VGG16 architectureAI-assisted diagnosisdeep learning |
| spellingShingle | Rapeepat Klangbunrueang Pongsathon Pookduang Wirapong Chansanam Tassanee Lunrasri AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification Informatics lung cancer image classification CT scans convolutional neural network (CNN) VGG16 architecture AI-assisted diagnosis deep learning |
| title | AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification |
| title_full | AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification |
| title_fullStr | AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification |
| title_full_unstemmed | AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification |
| title_short | AI-Powered Lung Cancer Detection: Assessing VGG16 and CNN Architectures for CT Scan Image Classification |
| title_sort | ai powered lung cancer detection assessing vgg16 and cnn architectures for ct scan image classification |
| topic | lung cancer image classification CT scans convolutional neural network (CNN) VGG16 architecture AI-assisted diagnosis deep learning |
| url | https://www.mdpi.com/2227-9709/12/1/18 |
| work_keys_str_mv | AT rapeepatklangbunrueang aipoweredlungcancerdetectionassessingvgg16andcnnarchitecturesforctscanimageclassification AT pongsathonpookduang aipoweredlungcancerdetectionassessingvgg16andcnnarchitecturesforctscanimageclassification AT wirapongchansanam aipoweredlungcancerdetectionassessingvgg16andcnnarchitecturesforctscanimageclassification AT tassaneelunrasri aipoweredlungcancerdetectionassessingvgg16andcnnarchitecturesforctscanimageclassification |