Concatenated Modified LeNet Approach for Classifying Pneumonia Images
Pneumonia remains a critical health concern worldwide, necessitating efficient diagnostic tools to enhance patient care. This research proposes a concatenated modified LeNet classifier to classify pneumonia images accurately. The model leverages deep learning techniques to improve the diagnosis of P...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/14/3/328 |
| _version_ | 1797240361657040896 |
|---|---|
| author | Dhayanithi Jaganathan Sathiyabhama Balsubramaniam Vidhushavarshini Sureshkumar Seshathiri Dhanasekaran |
| author_facet | Dhayanithi Jaganathan Sathiyabhama Balsubramaniam Vidhushavarshini Sureshkumar Seshathiri Dhanasekaran |
| author_sort | Dhayanithi Jaganathan |
| collection | DOAJ |
| description | Pneumonia remains a critical health concern worldwide, necessitating efficient diagnostic tools to enhance patient care. This research proposes a concatenated modified LeNet classifier to classify pneumonia images accurately. The model leverages deep learning techniques to improve the diagnosis of Pneumonia, leading to more effective and timely treatment. Our modified LeNet architecture incorporates a revised Rectified Linear Unit (ReLU) activation function. This enhancement aims to boost the discriminative capacity of the features learned by the model. Furthermore, we integrate batch normalization to stabilize the training process and enhance performance within smaller, less complex, CNN architectures like LeNet. Batch normalization addresses internal covariate shift, a phenomenon where the distribution of activations within a network alter during training. These modifications help to prevent overfitting and decrease computational time. A comprehensive dataset is used to evaluate the model’s performance, and the model is benchmarked against relevant deep-learning models. The results demonstrate a high recognition rate, with an accuracy of 96% in pneumonia image recognition. This research suggests that the Concatenated Modified LeNet classifier has the potential to be a highly useful tool for medical professionals in the diagnosis of pneumonia. By offering accurate and efficient image classification, our model could contribute to improved treatment decisions and patient outcomes. |
| first_indexed | 2024-04-24T18:06:13Z |
| format | Article |
| id | doaj.art-ab466edcc1e44352b23d108922d75aa6 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-04-24T18:06:13Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-ab466edcc1e44352b23d108922d75aa62024-03-27T13:50:17ZengMDPI AGJournal of Personalized Medicine2075-44262024-03-0114332810.3390/jpm14030328Concatenated Modified LeNet Approach for Classifying Pneumonia ImagesDhayanithi Jaganathan0Sathiyabhama Balsubramaniam1Vidhushavarshini Sureshkumar2Seshathiri Dhanasekaran3Department of Computer Science and Engineering, Sona College of Technology, Salem 636005, IndiaDepartment of Computer Science and Engineering, Sona College of Technology, Salem 636005, IndiaDepartment of Computer Science and Engineering, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Vadapalani Campus, Chennai 600026, IndiaDepartment of Computer Science, UiT The Arctic University of Norway, 9037 Tromsø, NorwayPneumonia remains a critical health concern worldwide, necessitating efficient diagnostic tools to enhance patient care. This research proposes a concatenated modified LeNet classifier to classify pneumonia images accurately. The model leverages deep learning techniques to improve the diagnosis of Pneumonia, leading to more effective and timely treatment. Our modified LeNet architecture incorporates a revised Rectified Linear Unit (ReLU) activation function. This enhancement aims to boost the discriminative capacity of the features learned by the model. Furthermore, we integrate batch normalization to stabilize the training process and enhance performance within smaller, less complex, CNN architectures like LeNet. Batch normalization addresses internal covariate shift, a phenomenon where the distribution of activations within a network alter during training. These modifications help to prevent overfitting and decrease computational time. A comprehensive dataset is used to evaluate the model’s performance, and the model is benchmarked against relevant deep-learning models. The results demonstrate a high recognition rate, with an accuracy of 96% in pneumonia image recognition. This research suggests that the Concatenated Modified LeNet classifier has the potential to be a highly useful tool for medical professionals in the diagnosis of pneumonia. By offering accurate and efficient image classification, our model could contribute to improved treatment decisions and patient outcomes.https://www.mdpi.com/2075-4426/14/3/328pneumoniaconvolution neural networkmodified LeNetclassificationReLU |
| spellingShingle | Dhayanithi Jaganathan Sathiyabhama Balsubramaniam Vidhushavarshini Sureshkumar Seshathiri Dhanasekaran Concatenated Modified LeNet Approach for Classifying Pneumonia Images Journal of Personalized Medicine pneumonia convolution neural network modified LeNet classification ReLU |
| title | Concatenated Modified LeNet Approach for Classifying Pneumonia Images |
| title_full | Concatenated Modified LeNet Approach for Classifying Pneumonia Images |
| title_fullStr | Concatenated Modified LeNet Approach for Classifying Pneumonia Images |
| title_full_unstemmed | Concatenated Modified LeNet Approach for Classifying Pneumonia Images |
| title_short | Concatenated Modified LeNet Approach for Classifying Pneumonia Images |
| title_sort | concatenated modified lenet approach for classifying pneumonia images |
| topic | pneumonia convolution neural network modified LeNet classification ReLU |
| url | https://www.mdpi.com/2075-4426/14/3/328 |
| work_keys_str_mv | AT dhayanithijaganathan concatenatedmodifiedlenetapproachforclassifyingpneumoniaimages AT sathiyabhamabalsubramaniam concatenatedmodifiedlenetapproachforclassifyingpneumoniaimages AT vidhushavarshinisureshkumar concatenatedmodifiedlenetapproachforclassifyingpneumoniaimages AT seshathiridhanasekaran concatenatedmodifiedlenetapproachforclassifyingpneumoniaimages |