The Sriwijaya University Library

  • Home
  • Information
  • News
  • Help
  • Login
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of KLASIFIKASI PRA-KANKER SERVIKS BERBASIS FITUR HIBRIDA DENGAN CITRA KOLPOSKOPI MENGGUNAKAN MULTI LAYER PERCEPTRON DAN DEEP NEURAL NETWORK
Bookmark Share

Skripsi

KLASIFIKASI PRA-KANKER SERVIKS BERBASIS FITUR HIBRIDA DENGAN CITRA KOLPOSKOPI MENGGUNAKAN MULTI LAYER PERCEPTRON DAN DEEP NEURAL NETWORK

Suhandono, Nugroho - Personal Name;

Cervical cancer remains one of the leading causes of cancer-related mortality among women worldwide, particularly in resource-limited settings where access to routine screening and expert medical evaluation is restricted. Early detection of Cervical Intraepithelial Neoplasia (CIN) through colposcopy image analysis is critical to prevent the progression of pre-cancerous lesions into invasive cervical cancer. This study proposes a hybrid feature-based classification approach for cervical pre-cancer using two model schemes. The first scheme combines conventional texture feature extraction methods, namely Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP), with deep features extracted from MobileNetV2, subsequently classified using a Multilayer Perceptron (MLP). The second scheme integrates Gray Level Run Length Matrix (GLRLM) texture features, Color Moments, and deep features from EfficientNetB3 and MobileNetV3, classified using a Deep Neural Network (DNN). The dataset consists of 200 colposcopy images obtained from the International Agency for Research on Cancer (IARC), categorized into four classes: Normal, CIN1, CIN2, and CIN3. Image augmentation was applied to address data scarcity, and model evaluation was conducted using stratified 5-fold cross-validation with accuracy, precision, recall, F1-score, and Cohen's Kappa as performance metrics. Experimental results demonstrate that the MLP-based hybrid feature model achieved a mean accuracy of 86.75% ± 2.62% and a mean Cohen's Kappa of 0.7963, while the DNN-based hybrid feature model achieved a mean accuracy of 82.67% ± 3.65% and a mean Cohen's Kappa of 0.7466. Both models consistently exhibited strong performance on the Normal and CIN3 classes, whereas CIN2 classification remained the most challenging due to overlapping visual and textural characteristics with adjacent lesion grades. This study demonstrates that the hybrid feature fusion approach holds significant potential as a computer-aided decision support system for objective and automated early screening of cervical pre-cancerous lesions. Keywords: Cervical pre-cancer, CIN, colposcopy image, hybrid features, MLP, DNN, GLCM, LBP, GLRLM, Color Moments, MobileNetV2, MobileNetV3, EfficientNetB3


Availability
#
Central Library (Reference) T2016492026
T201649
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T2016492026
Publisher
Palembang : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026
Collation
116 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
006.307
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Prodi Magister Ilmu Komputer
Deep Neural Network
Specific Detail Info
-
Statement of Responsibility
MI
Other version/related

No other version available

File Attachment
  • KLASIFIKASI PRA-KANKER SERVIKS BERBASIS FITUR HIBRIDA DENGAN CITRA KOLPOSKOPI MENGGUNAKAN MULTI LAYER PERCEPTRON DAN DEEP NEURAL NETWORK
Comments

You must be logged in to post a comment

The Sriwijaya University Library
  • Information
  • Services
  • Librarian
  • Member Area

About Us

As a complete Library Management System, SLiMS (Senayan Library Management System) has many features that will help libraries and librarians to do their job easily and quickly. Follow this link to show some features provided by SLiMS.

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2026 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?