Klasifikasi penyakit Kanker Serviks berdasarkan Citra Pap Smear menggunakan Convolutional Neural Network (CNN) model Xception

Maesaroh, Ima Siti (2023) Klasifikasi penyakit Kanker Serviks berdasarkan Citra Pap Smear menggunakan Convolutional Neural Network (CNN) model Xception. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (92kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak.pdf Download (144kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi.pdf Download (140kB) | Preview
Preview	Text (BAB I) 4_bab1.pdf Download (141kB) | Preview
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (4MB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (5MB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (3MB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (128kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9_daftarpustaka.pdf Restricted to Registered users only Download (187kB) | Request a copy

Abstract

Cervical cancer is a disease that damages the female reproductive organs and is the cause of a high increase in mortality rates in women. This increase in the number of deaths is caused by delays in cancer screening, so it is important to prevent the high mortality rate of cervical cancer patients by taking early prevention. The pap smear test can detect and diagnose cervical cancer early, but manual pap smear test results still have weaknesses in observation and the length of the laboratory process. The purpose of this research is to be able to implement the Convolutional Neural Network (CNN) method of transfer learning exception model for cervical cancer classification based on pap smear images in 2 classes and 4 classes on data sourced from RepoMedUNM, namely 400 cervical cell images consisting of normal cells, koilocyt, L-Sil and H-Sil. The stages in this study include resizing and augmenting data, sharing data, searching for hyperparameter tuning, building a CNN model with the xception architecture, training and testing and evaluating the model. Based on the research that has been done, the results show that the Convolutional Neural Network (CNN) method of transfer learning xception model is able to classify cervical cancer based on pap smear images in 2 classes and 4 classes. The evaluation obtained an accuracy of 100% in the 2 class classification and 95% in the 4 class classification.

Actions (login required)

View Item