Karunia Agustiani, . (2025) PENERAPAN EXTREME GRADIENT BOOSTING UNTUK KLASIFIKASI CITRA MRI KANKER PROSTAT BERDASARKAN EKSTRAKSI FITUR GLCM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (168kB) |
|
Text
AWAL.pdf Download (724kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (509kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (822kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (857kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB 5.pdf Download (189kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (317kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (18kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (998kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (20MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (897kB) |
Abstract
Prostate cancer is one of the most common cancers in men and one of the leading causes of cancer deaths in the world. In Indonesia, the number of prostate cancer cases continues to increase, so an early detection method through Magnetic Resonance Imaging (MRI) examination is needed. MRI images have an important role in early diagnosis and treatment planning of prostate cancer. Therefore, this study aims to develop a machine learning model that can classify prostate MRI images. The dataset used consists of 671 prostate MRI images classified into two classes, namely positive and negative. The classification model was built using the Gray Level Co-Occurrence Matrix (GLCM) method for extracting texture features in MRI images, and the Extreme Gradient Boosting (XGBoost) algorithm as the classification algorithm. This research was conducted in six model scheme experiments based on a combination of using Optuna hyperparameter tuning and resampling methods, namely Random Under-Sampling (RUS) and Synthetic Minority Over-Sampling Technique (SMOTE) to overcome data imbalance. The results show that the model built with the RUS method provides the best evaluation performance with an accuracy rate on test data of 0.82, precision of 0.82, recall of 0.82, and F1-score of 0.82. In addition, the model was successfully implemented in a GUI interface system that can facilitate the classification process using the built model. This research is expected to contribute in supporting the process of early detection of prostate cancer and demonstrate the potential use of the XGBoost algorithm in medical image classification.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2110511002] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Hamonangan Kinantan Prabu] [Penguji 1: Widya Cholil] [Penguji 2: Muhammad Adrezo] |
| Uncontrolled Keywords: | Prostate Cancer, MRI Image, GLCM, XGBoost |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | KARUNIA AGUSTIANI |
| Date Deposited: | 13 Jul 2025 21:05 |
| Last Modified: | 13 Jul 2025 21:05 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37152 |
Actions (login required)
 |
View Item |