KLASIFIKASI LESI PRA-KANKER SERVIKS MELALUI CITRA MEDIS IVA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK DAN CLASS ACTIVATION MAPPING

ARUM, AKHIAR WISTA and Nurmaini, Siti and Rini, Dian Palupi (2022) KLASIFIKASI LESI PRA-KANKER SERVIKS MELALUI CITRA MEDIS IVA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK DAN CLASS ACTIVATION MAPPING. Master thesis, Sriwijaya University.

[thumbnail of RAMA_55101_09012682024006_TURNITIN.pdf] Text
RAMA_55101_09012682024006_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (28MB) | Request a copy
[thumbnail of RAMA_55101_09012682024006.pdf] Text
RAMA_55101_09012682024006.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (5MB) | Request a copy
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_01_Font_Ref.pdf]
Preview
Text
RAMA_55101_09012682024006_0002085908_0023027804_01_Font_Ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Preview
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_02.pdf] Text
RAMA_55101_09012682024006_0002085908_0023027804_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_03.pdf] Text
RAMA_55101_09012682024006_0002085908_0023027804_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_04.pdf] Text
RAMA_55101_09012682024006_0002085908_0023027804_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_05.pdf] Text
RAMA_55101_09012682024006_0002085908_0023027804_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (190kB) | Request a copy
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_06_Ref.pdf] Text
RAMA_55101_09012682024006_0002085908_0023027804_06_Ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (427kB) | Request a copy
[thumbnail of RAMA_55101_09012682024006_0002085908_0023027804_07_Lamp.pdf] Text
RAMA_55101_09012682024006_0002085908_0023027804_07_Lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (821kB) | Request a copy

Abstract

The high-level infection of Human Papilloma Virus (HPV) causes cervical cancer to become the second most common disease that affects women, especially in low-middle income countries (LMICs), including Indonesia. Early screening for pre-cancerous lesions is one way to reduce the spread of cervical cancer. Visual inspection with acetic acid (VIA) is one initial screening methods recommended by the World Health Organization (WHO) to be applied in LMICs. However, healthcare professional is needed to read the VIA test diagnosis. This is because the anatomy of cervical pre-cancerous lesions is so complex. The lack healthcare professional is a problem in implementing the VIA test, especially in Indonesia. Therefore, artificial intelligence technology that is able to predict cervical pre-cancerous lesions automatically and accurately needs to be developed. This study developed a classification model for cervical pre-cancerous lesions on VIA medical images using the Convolutional Neural Network (CNN) method. The three CNN architectures used include the VGG16, VGG19 and ResNet50 architectures. Because the amount of data used is still limited, two test cases were carried out, the first without data augmentation and the second with data augmentation. The results obtained show that the performance of model classification ResNet50 pre-train with data augmentation outperformed other classification models with a performance value 91.28% accuracy, 98.75% precision, 86.81% sensitivity, 92.402% f1-score and 98.27% specificity. In addition, to increase the confidence of the CNN model results, which have been considered a black box, the interpretation of the CNN model results in heatmap visualization to show the area generated by CNN is shown. The interpretation methods used are Class Activation Mapping (CAM) and Gradient-Weight Class Activation Mapping (Grad-CAM). The visualization results obtained show that the model can be used by healthcare professionals as an alternative to the automatic initial screening of the VIA test. Keywords: Classification, Localization, CNN, CAM, Grad-CAM, Visual inspection with acetic acid.

Item Type: Thesis (Master)
Uncontrolled Keywords: Klasifikasi, Lokalisasi, CNN, CAM, Grad-CAM, Inspeksi Visual dengan Asam Asetat.
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
R Medicine > RG Gynecology and obstetrics > RG211-483 Abnormalities and diseases of the female genital organs
Divisions: 09-Faculty of Computer Science > 55101-Informatics (S2)
Depositing User: Akhiar Wista Arum
Date Deposited: 02 Aug 2022 04:03
Last Modified: 02 Aug 2022 04:03
URI: http://repository.unsri.ac.id/id/eprint/74742

Actions (login required)

View Item View Item