Fatichah, Chastine
Informatics Department, Institut Teknologi Sepuluh Nopember

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Determination of Location and Severity of Nodules on Lung Cancer CT Image Using YOLO Methods Ramadhani, Hanun Masitha; Fatichah, Chastine
IPTEK The Journal for Technology and Science Vol 34, No 2 (2023)
Publisher : IPTEK, DRPM, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j20882033.v34i2.16821

Abstract

The severity of lung cancer can be used to determine appropriate treatment measures and reduce the risk of death. The severity identification is monitored based on the size and location of the nodule. However, previous studies still focused on determining the location of nodules without identifying their severity. In this study, the severity of lung cancer is detected based on the size of its nodules. This research contributes to the annotation of severity to the Lung Image Database Consortium image collection (LIDC-IDRI) dataset and the development of automatic severity detection using You Only Look Once (YOLO) methods. The data is given a severity level based on the nodule size calculated based on the number of pixels in the nodule length. Automatic detection is done using YOLO methods, which consist of several versions, namely YOLOv5, YOLOv7, and YOLOv8. YOLO methods can properly detect the location and severity of cancer nodules with the IoU evaluation results obtained using YOLOv5, YOLOv7, and YOLOv8, which are 0.86, 0.6, and 0.87, respectively. From the experiment, it can be concluded that determining the location and severity of cancer based on nodule size using YOLO methods is proven effective and can be done in real-time.