Claim Missing Document
Check
Articles

Found 22 Documents
Search

Skin Cancer Segmentation On Dermoscopy Images Using Fuzzy C-Means Algorithm Aldi, Febri; Sumijan
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i2.3797

Abstract

Millions of people around the world suffer from skin cancer, a common and sometimes fatal disease. Dermoscopy has become an effective diagnostic technique for skin cancer. Precise segmentation is essential for skin cancer diagnosis. Segmentation allows more precise analysis of dermoscopic images by defining the boundaries of the lesion and separating it from surrounding healthy tissue. Dermoscopy images served as a source of research data, and Fuzzy C-Means (FCM) segmentation techniques were used. FCM is a promising method and has received a lot of attention lately. FCM is able to distinguish the various components within the lesion and effectively separate the lesion from the surrounding area. As a result, the distribution of membership degree values of each pixel in the image for each cluster represents the segmentation results obtained through FCM. The FCM technique for segmenting dermoscopic images is expected to significantly improve the precision and effectiveness of skin cancer diagnosis.
Architecture-Dependent Effects of CLAHE Enhancement Across YOLOv5, YOLOv8, YOLOv10, and YOLOv11 for Bone Fracture Detection Febri Aldi; Irohito Nozomi; Ronaldo Syahputra
Journal of Computer Networks, Architecture and High Performance Computing Vol. 8 No. 3 (2026): Research Paper July 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v8i3.8572

Abstract

Bone fracture detection in X-ray images remains challenging because fracture lines often appear as low-contrast, subtle, and visually similar patterns across fracture types. Although YOLO-based detectors have been widely used for medical object detection, the effect of contrast enhancement is commonly evaluated on a single architecture, making it unclear whether preprocessing benefits are consistent across different YOLO generations. This study investigates the architecture-dependent effect of Contrast Limited Adaptive Histogram Equalization (CLAHE) on YOLOv5, YOLOv8, YOLOv10, and YOLOv11 for bone fracture detection. A total of 1,539 annotated X-ray images were prepared in YOLO bounding-box format and evaluated under two scenarios: original images and CLAHE-enhanced images. Model performance was assessed using precision, recall, mAP50, and mAP50-95, followed by paired architecture-level comparison using paired t-test, Wilcoxon signed-rank test, and bootstrap confidence intervals. The results show that CLAHE does not uniformly improve all detection metrics. YOLOv8 without CLAHE achieved the strongest mAP50 and recall, whereas YOLOv11 with CLAHE produced the highest mAP50-95, indicating better localization precision under stricter IoU thresholds. The statistical comparison suggests a positive but exploratory improvement in mAP50-95 after CLAHE, while other metrics showed no significant architecture-level difference. These findings demonstrate that image enhancement effectiveness is architecture-dependent and should be selected according to the feature extraction and localization characteristics of the detector rather than applied as a universal preprocessing step.