Automatic classification of kidney CT images with relief based novel hybrid deep model
One of the most crucial organs in the human body is the kidney. Usually, the patient does not realize the serious problems that arise in the kidneys in the early stages of the disease. Many kidney diseases can be detected and diagnosed by specialists with the help of routine computer tomography (CT)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-11-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1717.pdf |
| _version_ | 1797427675619393536 |
|---|---|
| author | Harun Bingol Muhammed Yildirim Kadir Yildirim Bilal Alatas |
| author_facet | Harun Bingol Muhammed Yildirim Kadir Yildirim Bilal Alatas |
| author_sort | Harun Bingol |
| collection | DOAJ |
| description | One of the most crucial organs in the human body is the kidney. Usually, the patient does not realize the serious problems that arise in the kidneys in the early stages of the disease. Many kidney diseases can be detected and diagnosed by specialists with the help of routine computer tomography (CT) images. Early detection of kidney diseases is extremely important for the success of the treatment of the disease and for the prevention of other serious diseases. In this study, CT images of kidneys containing stones, tumors, and cysts were classified using the proposed hybrid model. Results were also obtained using pre-trained models that had been acknowledged in the literature to evaluate the effectiveness of the suggested model. The proposed model consists of 29 layers. While classifying kidney CT images, feature maps were obtained from the convolution 6 and convolution 7 layers of the proposed model, and these feature maps were combined after optimizing with the Relief method. The wide neural network classifier then classifies the optimized feature map. While the highest accuracy value obtained in eight different pre-trained models was 87.75%, this accuracy value was 99.37% in the proposed model. In addition, different performance evaluation metrics were used to measure the performance of the model. These values show that the proposed model has reached high-performance values. Therefore, the proposed approach seems promising in order to automatically and effectively classify kidney CT images. |
| first_indexed | 2024-03-09T08:48:27Z |
| format | Article |
| id | doaj.art-e59d5b65a38645c591ca9142874021cf |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-03-09T08:48:27Z |
| publishDate | 2023-11-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-e59d5b65a38645c591ca9142874021cf2023-12-02T15:05:15ZengPeerJ Inc.PeerJ Computer Science2376-59922023-11-019e171710.7717/peerj-cs.1717Automatic classification of kidney CT images with relief based novel hybrid deep modelHarun Bingol0Muhammed Yildirim1Kadir Yildirim2Bilal Alatas3Software Engineering, Malatya Turgut Ozal University, Malatya, TurkeyComputer Engineering, Malatya Turgut Ozal University, Malatya, TurkeyElazig Fethi Sekin City HTRC, Elazig, TurkeySoftware Engineering, Firat (Euphrates) University, Elazig, TurkeyOne of the most crucial organs in the human body is the kidney. Usually, the patient does not realize the serious problems that arise in the kidneys in the early stages of the disease. Many kidney diseases can be detected and diagnosed by specialists with the help of routine computer tomography (CT) images. Early detection of kidney diseases is extremely important for the success of the treatment of the disease and for the prevention of other serious diseases. In this study, CT images of kidneys containing stones, tumors, and cysts were classified using the proposed hybrid model. Results were also obtained using pre-trained models that had been acknowledged in the literature to evaluate the effectiveness of the suggested model. The proposed model consists of 29 layers. While classifying kidney CT images, feature maps were obtained from the convolution 6 and convolution 7 layers of the proposed model, and these feature maps were combined after optimizing with the Relief method. The wide neural network classifier then classifies the optimized feature map. While the highest accuracy value obtained in eight different pre-trained models was 87.75%, this accuracy value was 99.37% in the proposed model. In addition, different performance evaluation metrics were used to measure the performance of the model. These values show that the proposed model has reached high-performance values. Therefore, the proposed approach seems promising in order to automatically and effectively classify kidney CT images.https://peerj.com/articles/cs-1717.pdfArtificial intelligenceConvolutional neural networkReliefKidney diseasesClassification |
| spellingShingle | Harun Bingol Muhammed Yildirim Kadir Yildirim Bilal Alatas Automatic classification of kidney CT images with relief based novel hybrid deep model PeerJ Computer Science Artificial intelligence Convolutional neural network Relief Kidney diseases Classification |
| title | Automatic classification of kidney CT images with relief based novel hybrid deep model |
| title_full | Automatic classification of kidney CT images with relief based novel hybrid deep model |
| title_fullStr | Automatic classification of kidney CT images with relief based novel hybrid deep model |
| title_full_unstemmed | Automatic classification of kidney CT images with relief based novel hybrid deep model |
| title_short | Automatic classification of kidney CT images with relief based novel hybrid deep model |
| title_sort | automatic classification of kidney ct images with relief based novel hybrid deep model |
| topic | Artificial intelligence Convolutional neural network Relief Kidney diseases Classification |
| url | https://peerj.com/articles/cs-1717.pdf |
| work_keys_str_mv | AT harunbingol automaticclassificationofkidneyctimageswithreliefbasednovelhybriddeepmodel AT muhammedyildirim automaticclassificationofkidneyctimageswithreliefbasednovelhybriddeepmodel AT kadiryildirim automaticclassificationofkidneyctimageswithreliefbasednovelhybriddeepmodel AT bilalalatas automaticclassificationofkidneyctimageswithreliefbasednovelhybriddeepmodel |