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 Payudara Dengan Metode CNN dan Transfer Learning

      Thumbnail
      View/Open
      Cover (524.9Kb)
      Fullteks (1.162Mb)
      Date
      2023
      Author
      Albertino, Muhamad
      Haryanto, Toto
      Mushthofa
      Metadata
      Show full item record
      Abstract
      Kanker payudara adalah kanker dengan jumlah kasus terbanyak pertama di dunia dan di Indonesia. Kanker payudara memiliki kontribusi sebesar 11,7% (2.261.419) dari total kasus baru kanker di dunia serta 16,6% (65,858) di Indonesia yang tercatat di tahun 2020. Pemeriksaan kanker umumnya menggunakan teknik biopsi dengan melakukan pengambilan sampel jaringan yang dicurigai terdapat sel kanker. Penelitian ini bertujuan untuk membuat model convolutional neural network dengan metode transfer learning dalam memprediksi status kanker payudara pada citra histopatologi. Data yang digunakan dalam penelitian ini bersumber dari dataset BreakHis yang terdiri atas 7,909 citra histopatologi jaringan tumor payudara dan terbagi menjadi dua kelompok utama, yaitu tumor jinak dan tumor ganas. Tahapan dalam penelitian ini meliputi praproses data, pembagian data, pelatihan model, dan evaluasi. Hasil dari penelitian ini adalah model CNN yang dapat membantu proses klasifikasi kanker payudara pada citra histopatologi. Penelitian ini menghasilkan dua model CNN berbeda dengan akurasi terbaik sebesar 96%.
       
      Breast cancer is the cancer with the highest number of incidences, both in Indonesia and in the world. Breast cancer contributes up to 11,7% (2,261,419) of the total new cases of cancer in the world and 16,6% (65,858) in Indonesia (recorded in 2020). Cancer examination generally uses a biopsy technique by taking tissue samples suspected of having cancer cells. This study aims to create a convolutional neural network model with transfer learning method in predicting breast cancer status on histopathological images. The data used in this study were sourced from the BreakHis dataset which consisted of 7,909 histopathological images of breast tumor tissue and was divided into two main groups, namely benign tumors and malignant tumors. The stages in this research include data preprocessing, data sharing, model training, and evaluation. The result of this research is a convolutional neural network model that can help classify breast cancer in histopathological images. Two different CNN models were created with the best accuracy of 96%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/116046
      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