Trainable model for segmenting and identifying Nasopharyngeal carcinoma
Nasopharyngeal carcinoma (NPC) is a multifaceted cancer tumor that makes its diagnosis challenging. NPC has a consistently diffusive enlargement that makes its resection exceptionally challenging. The pathological identification of NPC and comparing typical and anomalous tissues require a set of adv...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2018
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/5142/1/AJ%202018%20%28845%29%20Trainable%20model%20for%20segmenting%20and%20identifying%20Nasopharyngeal%20carcinoma.pdf |
| _version_ | 1796869149665787904 |
|---|---|
| author | Mohammed, Mazin Abed Abd Ghani, Mohd Khanapi Arunkumar, N. A. Mostafa, Salama Abdullah, Mohamad Khir Burhanuddina, M.A. |
| author_facet | Mohammed, Mazin Abed Abd Ghani, Mohd Khanapi Arunkumar, N. A. Mostafa, Salama Abdullah, Mohamad Khir Burhanuddina, M.A. |
| author_sort | Mohammed, Mazin Abed |
| collection | UTHM |
| description | Nasopharyngeal carcinoma (NPC) is a multifaceted cancer tumor that makes its diagnosis challenging. NPC has a consistently diffusive enlargement that makes its resection exceptionally challenging. The pathological identification of NPC and comparing typical and anomalous tissues require a set of advanced strategies for the extraction of features. The use of medical images to diagnoses NPC tumor depends on tumor shape, region, and intensity. This paper proposes a novel approach for diagnosing NPC from endoscopic images. The approach includes a trainable segmentation for identifying NPC tissues, genetic algorithm for selecting the best features, and support vector machine for classifying NPC. The proposed approach is validated by comparing the number of classified NPC cases against the manual approach of ENT specialists. The approach shows a high precision of 95.15%, sensitivity of 94.80%, and specificity of 95.20%. Additionally, the optimized feature selection provides straightforward and efficient classification results. |
| first_indexed | 2024-03-05T21:50:31Z |
| format | Article |
| id | uthm.eprints-5142 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T21:50:31Z |
| publishDate | 2018 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | uthm.eprints-51422022-01-06T02:33:00Z http://eprints.uthm.edu.my/5142/ Trainable model for segmenting and identifying Nasopharyngeal carcinoma Mohammed, Mazin Abed Abd Ghani, Mohd Khanapi Arunkumar, N. A. Mostafa, Salama Abdullah, Mohamad Khir Burhanuddina, M.A. RC Internal medicine T Technology (General) T58.6-58.62 Management information systems Nasopharyngeal carcinoma (NPC) is a multifaceted cancer tumor that makes its diagnosis challenging. NPC has a consistently diffusive enlargement that makes its resection exceptionally challenging. The pathological identification of NPC and comparing typical and anomalous tissues require a set of advanced strategies for the extraction of features. The use of medical images to diagnoses NPC tumor depends on tumor shape, region, and intensity. This paper proposes a novel approach for diagnosing NPC from endoscopic images. The approach includes a trainable segmentation for identifying NPC tissues, genetic algorithm for selecting the best features, and support vector machine for classifying NPC. The proposed approach is validated by comparing the number of classified NPC cases against the manual approach of ENT specialists. The approach shows a high precision of 95.15%, sensitivity of 94.80%, and specificity of 95.20%. Additionally, the optimized feature selection provides straightforward and efficient classification results. Elsevier 2018 Article PeerReviewed text en http://eprints.uthm.edu.my/5142/1/AJ%202018%20%28845%29%20Trainable%20model%20for%20segmenting%20and%20identifying%20Nasopharyngeal%20carcinoma.pdf Mohammed, Mazin Abed and Abd Ghani, Mohd Khanapi and Arunkumar, N. and A. Mostafa, Salama and Abdullah, Mohamad Khir and Burhanuddina, M.A. (2018) Trainable model for segmenting and identifying Nasopharyngeal carcinoma. Computers and Electrical Engineering, 71 (4). pp. 372-387. ISSN 0045-7906 |
| spellingShingle | RC Internal medicine T Technology (General) T58.6-58.62 Management information systems Mohammed, Mazin Abed Abd Ghani, Mohd Khanapi Arunkumar, N. A. Mostafa, Salama Abdullah, Mohamad Khir Burhanuddina, M.A. Trainable model for segmenting and identifying Nasopharyngeal carcinoma |
| title | Trainable model for segmenting and identifying Nasopharyngeal carcinoma |
| title_full | Trainable model for segmenting and identifying Nasopharyngeal carcinoma |
| title_fullStr | Trainable model for segmenting and identifying Nasopharyngeal carcinoma |
| title_full_unstemmed | Trainable model for segmenting and identifying Nasopharyngeal carcinoma |
| title_short | Trainable model for segmenting and identifying Nasopharyngeal carcinoma |
| title_sort | trainable model for segmenting and identifying nasopharyngeal carcinoma |
| topic | RC Internal medicine T Technology (General) T58.6-58.62 Management information systems |
| url | http://eprints.uthm.edu.my/5142/1/AJ%202018%20%28845%29%20Trainable%20model%20for%20segmenting%20and%20identifying%20Nasopharyngeal%20carcinoma.pdf |
| work_keys_str_mv | AT mohammedmazinabed trainablemodelforsegmentingandidentifyingnasopharyngealcarcinoma AT abdghanimohdkhanapi trainablemodelforsegmentingandidentifyingnasopharyngealcarcinoma AT arunkumarn trainablemodelforsegmentingandidentifyingnasopharyngealcarcinoma AT amostafasalama trainablemodelforsegmentingandidentifyingnasopharyngealcarcinoma AT abdullahmohamadkhir trainablemodelforsegmentingandidentifyingnasopharyngealcarcinoma AT burhanuddinama trainablemodelforsegmentingandidentifyingnasopharyngealcarcinoma |