Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning
Accurate lung cancer detection is vital for timely diagnosis and treatment. This study evaluates the performance of six convolutional neural network (CNN) architectures, ResNet-50, VGG-16, ResNet-101, VGG-19, DenseNet-201, and EfficientNet-B4, using the LIDC-IDRI dataset. Models were assessed both i...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Journal of Electrical and Computer Engineering |
| Online Access: | http://dx.doi.org/10.1155/2024/3790617 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557409953906688 |
|---|---|
| author | Mohd Munazzer Ansari Shailendra Kumar Umair Tariq Md Belal Bin Heyat Faijan Akhtar Mohd Ammar Bin Hayat Eram Sayeed Saba Parveen Dustin Pomary |
| author_facet | Mohd Munazzer Ansari Shailendra Kumar Umair Tariq Md Belal Bin Heyat Faijan Akhtar Mohd Ammar Bin Hayat Eram Sayeed Saba Parveen Dustin Pomary |
| author_sort | Mohd Munazzer Ansari |
| collection | DOAJ |
| description | Accurate lung cancer detection is vital for timely diagnosis and treatment. This study evaluates the performance of six convolutional neural network (CNN) architectures, ResNet-50, VGG-16, ResNet-101, VGG-19, DenseNet-201, and EfficientNet-B4, using the LIDC-IDRI dataset. Models were assessed both in their base forms and with transfer learning. The dataset consisted of 460 × 460 × 3 pixel images categorized into squamous cell carcinoma (SCC), normal benign, large cell carcinoma (LCC), and adenocarcinoma (ADC). Performance metrics were computed, including accuracy (99.47% for the custom CNN), precision (99.50%), recall (98.37%), AUC (99.98%), and F1-score (98.98%) during training. However, overfitting was observed in the validation phases. Transfer learning models showed better generalization, with DenseNet-201 achieving a top validation accuracy of 96.88% and EfficientNet-B4 of 96.53%. Hyperparameter tuning improved the models’ generalization capabilities, maintaining high accuracy while reducing overfitting. This study highlights the effectiveness of transfer learning, particularly DenseNet-201, in enhancing automated lung cancer detection systems. Future work will focus on expanding datasets and exploring additional augmentation techniques to further refine model performance in clinical settings. |
| format | Article |
| id | doaj-art-df8cd686b154422b8f7ab51f5e428a41 |
| institution | Kabale University |
| issn | 2090-0155 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering |
| spelling | doaj-art-df8cd686b154422b8f7ab51f5e428a412025-02-03T05:15:30ZengWileyJournal of Electrical and Computer Engineering2090-01552024-01-01202410.1155/2024/3790617Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer LearningMohd Munazzer Ansari0Shailendra Kumar1Umair Tariq2Md Belal Bin Heyat3Faijan Akhtar4Mohd Ammar Bin Hayat5Eram Sayeed6Saba Parveen7Dustin Pomary8Department of Electronic and Communication EngineeringDepartment of Electronic and Communication EngineeringSchool of Electronic EngineeringCenBRAIN Neurotech Center of ExcellenceCenBRAIN Neurotech Center of ExcellenceCollege of Intelligent Systems Science and EngineeringKisan Inter CollegeCollege of Electronics and Information EngineeringElectrical and Electronics Engineering DepartmentAccurate lung cancer detection is vital for timely diagnosis and treatment. This study evaluates the performance of six convolutional neural network (CNN) architectures, ResNet-50, VGG-16, ResNet-101, VGG-19, DenseNet-201, and EfficientNet-B4, using the LIDC-IDRI dataset. Models were assessed both in their base forms and with transfer learning. The dataset consisted of 460 × 460 × 3 pixel images categorized into squamous cell carcinoma (SCC), normal benign, large cell carcinoma (LCC), and adenocarcinoma (ADC). Performance metrics were computed, including accuracy (99.47% for the custom CNN), precision (99.50%), recall (98.37%), AUC (99.98%), and F1-score (98.98%) during training. However, overfitting was observed in the validation phases. Transfer learning models showed better generalization, with DenseNet-201 achieving a top validation accuracy of 96.88% and EfficientNet-B4 of 96.53%. Hyperparameter tuning improved the models’ generalization capabilities, maintaining high accuracy while reducing overfitting. This study highlights the effectiveness of transfer learning, particularly DenseNet-201, in enhancing automated lung cancer detection systems. Future work will focus on expanding datasets and exploring additional augmentation techniques to further refine model performance in clinical settings.http://dx.doi.org/10.1155/2024/3790617 |
| spellingShingle | Mohd Munazzer Ansari Shailendra Kumar Umair Tariq Md Belal Bin Heyat Faijan Akhtar Mohd Ammar Bin Hayat Eram Sayeed Saba Parveen Dustin Pomary Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning Journal of Electrical and Computer Engineering |
| title | Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning |
| title_full | Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning |
| title_fullStr | Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning |
| title_full_unstemmed | Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning |
| title_short | Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning |
| title_sort | evaluating cnn architectures and hyperparameter tuning for enhanced lung cancer detection using transfer learning |
| url | http://dx.doi.org/10.1155/2024/3790617 |
| work_keys_str_mv | AT mohdmunazzeransari evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT shailendrakumar evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT umairtariq evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT mdbelalbinheyat evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT faijanakhtar evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT mohdammarbinhayat evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT eramsayeed evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT sabaparveen evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning AT dustinpomary evaluatingcnnarchitecturesandhyperparametertuningforenhancedlungcancerdetectionusingtransferlearning |