TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER
Skin cancer is a severe problem that is frequently disregarded. In circumstances of manual examination by a clinician, the human eye is occasionally unable to detect disorders precisely from imaging data. Deep learning techniques are increasingly being used nowadays to solve various problems in our...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Zibeline International
2022-11-01
|
| Series: | Acta Informatica Malaysia |
| Subjects: | |
| Online Access: | https://actainformaticamalaysia.com/archives/AIM/1aim2023/1aim2023-01-07.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850265711540174848 |
|---|---|
| author | Peshraw Ahmed Abdalla Abdalbasit Mohammed Qadir Omed Jamal Rashid Sarkhel H. Taher Karim Bashdar Abdalrahman Mohammed Karzan Jaza Ghafoor |
| author_facet | Peshraw Ahmed Abdalla Abdalbasit Mohammed Qadir Omed Jamal Rashid Sarkhel H. Taher Karim Bashdar Abdalrahman Mohammed Karzan Jaza Ghafoor |
| author_sort | Peshraw Ahmed Abdalla |
| collection | DOAJ |
| description | Skin cancer is a severe problem that is frequently disregarded. In circumstances of manual examination by a clinician, the human eye is occasionally unable to detect disorders precisely from imaging data. Deep learning techniques are increasingly being used nowadays to solve various problems in our daily lives. Therefore, deep neural network techniques are used to create an automated and computerized mechanism for detecting skin illnesses. To identify and diagnose skin illnesses over a range of criteria several neural network algorithms are evaluated and tested in the suggested model to see how well they perform. The networks are constructed to provide better outcomes using the CNN (Convolution neural network) and the Keras Sequential API architectures. The paper also compares the outcomes of the models using several metrics, such as accuracy, precision, f1 score, and recall. The transfer learning model involves seven models like DenseNet201, InseptionResnetV2, MobileNetV2, InceptionV3, ResNet50, DenseNet169, and VGG16. Among the employed models, the DenseNet169 model achieved the highest score of 87.58% in terms of accuracy; also, in terms of sensitivity and F1 score, DenseNet201 achieved the highest scores of 95.28% and 89.09%, respectively. On the other hand, VGG16 gained a score of 89.67% in terms of specificity, and DenseNet169 achieved the highest score of 90.64% in terms of precision. |
| format | Article |
| id | doaj-art-2809bda4231347bdb2618bd6ec940538 |
| institution | OA Journals |
| issn | 2521-0874 2521-0505 |
| language | English |
| publishDate | 2022-11-01 |
| publisher | Zibeline International |
| record_format | Article |
| series | Acta Informatica Malaysia |
| spelling | doaj-art-2809bda4231347bdb2618bd6ec9405382025-08-20T01:54:20ZengZibeline InternationalActa Informatica Malaysia2521-08742521-05052022-11-0171010710.26480/aim.01.2023.01.07TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCERPeshraw Ahmed Abdalla0Abdalbasit Mohammed Qadir1Omed Jamal Rashid2Sarkhel H. Taher Karim3Bashdar Abdalrahman Mohammed4Karzan Jaza Ghafoor5Computer Science Department, College of Science, University of Halabja, Halabja 46018, Kurdistan Region, Iraq Computer Science Department, College of Science and Technology, University of Human Development, Sulaimaniyah 46001, Kurdistan Region, IraqComputer Science Department, College of Science, University of Halabja, Halabja 46018, Kurdistan Region, IraqComputer Science Department, College of Science, University of Halabja, Halabja 46018, Kurdistan Region, IraqComputer Science Department, College of Science, University of Halabja, Halabja 46018, Kurdistan Region, IraqComputer Science Department, College of Science, University of Halabja, Halabja 46018, Kurdistan Region, IraqSkin cancer is a severe problem that is frequently disregarded. In circumstances of manual examination by a clinician, the human eye is occasionally unable to detect disorders precisely from imaging data. Deep learning techniques are increasingly being used nowadays to solve various problems in our daily lives. Therefore, deep neural network techniques are used to create an automated and computerized mechanism for detecting skin illnesses. To identify and diagnose skin illnesses over a range of criteria several neural network algorithms are evaluated and tested in the suggested model to see how well they perform. The networks are constructed to provide better outcomes using the CNN (Convolution neural network) and the Keras Sequential API architectures. The paper also compares the outcomes of the models using several metrics, such as accuracy, precision, f1 score, and recall. The transfer learning model involves seven models like DenseNet201, InseptionResnetV2, MobileNetV2, InceptionV3, ResNet50, DenseNet169, and VGG16. Among the employed models, the DenseNet169 model achieved the highest score of 87.58% in terms of accuracy; also, in terms of sensitivity and F1 score, DenseNet201 achieved the highest scores of 95.28% and 89.09%, respectively. On the other hand, VGG16 gained a score of 89.67% in terms of specificity, and DenseNet169 achieved the highest score of 90.64% in terms of precision.https://actainformaticamalaysia.com/archives/AIM/1aim2023/1aim2023-01-07.pdfcnnconvolution neural networkcancer detectioncancer diagnosisdeep learningmachine learningneural networksskin cancertransfer learning |
| spellingShingle | Peshraw Ahmed Abdalla Abdalbasit Mohammed Qadir Omed Jamal Rashid Sarkhel H. Taher Karim Bashdar Abdalrahman Mohammed Karzan Jaza Ghafoor TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER Acta Informatica Malaysia cnn convolution neural network cancer detection cancer diagnosis deep learning machine learning neural networks skin cancer transfer learning |
| title | TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER |
| title_full | TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER |
| title_fullStr | TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER |
| title_full_unstemmed | TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER |
| title_short | TRANSFER LEARNING MODELS COMPARISON FOR DETECTING AND DIAGNOSING SKIN CANCER |
| title_sort | transfer learning models comparison for detecting and diagnosing skin cancer |
| topic | cnn convolution neural network cancer detection cancer diagnosis deep learning machine learning neural networks skin cancer transfer learning |
| url | https://actainformaticamalaysia.com/archives/AIM/1aim2023/1aim2023-01-07.pdf |
| work_keys_str_mv | AT peshrawahmedabdalla transferlearningmodelscomparisonfordetectinganddiagnosingskincancer AT abdalbasitmohammedqadir transferlearningmodelscomparisonfordetectinganddiagnosingskincancer AT omedjamalrashid transferlearningmodelscomparisonfordetectinganddiagnosingskincancer AT sarkhelhtaherkarim transferlearningmodelscomparisonfordetectinganddiagnosingskincancer AT bashdarabdalrahmanmohammed transferlearningmodelscomparisonfordetectinganddiagnosingskincancer AT karzanjazaghafoor transferlearningmodelscomparisonfordetectinganddiagnosingskincancer |