AVERILL, MOCH DAFFA YUDIS (2026) APPLYING THE MASK REGION-BASED CONVOLUTIONAL NEURAL NETWORK METHOD IN A PNEUMONIA DISEASE DETECTION SYSTEM. Tugas Akhir thesis, University of Technology Yogyakarta.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
52204111377_Moch Daffa Yudis Averill_ABSTRAK.pdf Download (137kB) |
Abstract
ABSTRACT Manual identification of pneumonia on medical imaging is often time-consuming and heavily relies on radiologists’ expertise. Without the development of artificial intelligence-based applications, the risk of misdiagnosis and delayed treatment increases, potentially leading to serious complications for patients. Therefore, this study proposes implementing Mask R-CNN to improve the accuracy of pneumonia detection in lung X-ray images. The study utilized a dataset of 2,239 X-ray images, with an 80:20 split between training and testing data. Training was conducted using ResNet50 and ResNet101 backbone architectures, with 10 epochs, a learning rate of 0.00001, and 50 steps per epoch. The methodology involved data preprocessing followed by the application of the Mask R-CNN model to identify affected areas in the medical images. Performance was evaluated using precision, recall, and F1-score metrics. Preliminary results indicate that the proposed method achieves promising performance, with a precision of 41.34%, recall of 81.20%, and an F1-score of 54.78%. Keywords: Pneumonia, Mask R-CNN, Medical Image Detection, Deep Learning, Image Segmentation.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T201 Patents. Trademarks |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 07 May 2026 07:18 |
| Last Modified: | 07 May 2026 07:18 |
| URI: | http://eprints.uty.ac.id/id/eprint/19840 |
Actions (login required)
 |
View Item |
