View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Computer Science
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Klasifikasi Citra Histopatologi Kanker Serviks Menggunakan Metode Transfer Learning

      Thumbnail
      View/Open
      Cover (2.129Mb)
      Fullteks (9.158Mb)
      Lampiran (567.5Kb)
      Date
      2021
      Author
      Hafiz, Fahreza Ikhsan
      Agmalaro, Muhammad Asyhar
      Sitanggang, Imas Sukaesih
      Metadata
      Show full item record
      Abstract
      Kanker mulut rahim (serviks) adalah kanker dengan jumlah kasus terbanyak kelima pada wanita di seluruh dunia dan merupakan masalah kesehatan perempuan di Indonesia dengan angka kejadian dan kematiannya yang tinggi. Tes skrining pap smear manual yang berfungsi sebagai pencegahan dan deteksi awal kanker serviks masih rawan akan terjadinya kesalahan observasi. Penelitian ini bertujuan untuk membuat model convolutional neural network dengan metode transfer learning untuk identifikasi kanker serviks pada citra pap smear. Data yang digunakan pada penelitian ini adalah dataset open source SIPaKMeD yang mengandung 4049 citra sel serviks normal, abnormal, dan jinak. Penelitian ini dilakukan melalui beberapa tahapan yaitu praproses data, pembagian data, hyperparameter tuning, pembuatan model prediksi, dan evaluasi model. Penelitian ini menghasilkan tiga model CNN berbeda dengan akurasi terbaik sebesar 99,04%.
       
      Cervical cancer is a cancer with the fifth highest number of cases in women worldwide and is a health problem in Indonesia with high incidence and death rate. Manual pap smear screening tests that function as prevention and early detection of cervical cancer are still prone to observation errors. This study aims to create a convolutional neural network with transfer learning method to identify cervical cancer on pap smear images. The data used in this study are the open source dataset SIPaKMeD that contains 4049 normal, abnormal, and benign cervical cell images. The study was carried out through several stages which are data preprocessing, data splitting, hyperparameter tuning, prediction model making, and model evaluation. Three different CNN models were made, having the best accuracy of 99.04%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/107156
      Collections
      • UT - Computer Science [2482]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository