Architecture-Dependent Effects of CLAHE Enhancement Across YOLOv5, YOLOv8, YOLOv10, and YOLOv11 for Bone Fracture Detection

Febri Aldi; Irohito Nozomi; Ronaldo Syahputra

doi:10.47709/cnahpc.v8i3.8572

Authors

Febri Aldi Universitas Putra Indonesia YPTK Padang
Irohito Nozomi Universitas Putra Indonesia YPTK Padang
Ronaldo Syahputra Universitas Putra Indonesia YPTK Padang

DOI:

https://doi.org/10.47709/cnahpc.v8i3.8572

Keywords:

Bone fracture detection, CLAHE, YOLO, X-Ray image, object detection

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.

Downloads

Download data is not yet available.

References

Ahmed, A., Imran, A. S., Manaf, A., Kastrati, Z., & Daudpota, S. M. (2024). Enhancing wrist abnormality detection with YOLO: Analysis of state-of-the-art single-stage detection models. Biomedical Signal Processing and Control, 93, 106144. https://doi.org/10.1016/J.BSPC.2024.106144

Aldi, F., Nozomi, I., Hafizh, M., & Novita, T. (2025). Comparative Analysis of YOLOv11 with Previous YOLO in the Detection of Human Bone Fractures. Journal of Computer Networks, Architecture and High Performance Computing, 7(3), 777–790. https://doi.org/10.47709/CNAHPC.V7I3.6051

Aldi, F., Yuhandri, & Tajuddin, M. (2024). Enhanced U-Net Architecture for Glottis Segmentation with VGG-16. JOIV?: International Journal on Informatics Visualization, 8(4), 2173–2180. https://doi.org/10.62527/JOIV.8.4.3088

Belali, M. H., Khan, F. R., Rajin, N. M., Sarkar, H., & Uddin, K. M. M. (2025). Bone Osteoporosis Fractures Detection with Deep Learning: An X-ray Image Analysis Approach. Biomedical Materials & Devices 2025 4:1, 4(1), 533–551. https://doi.org/10.1007/S44174-025-00285-6

Cai, Z., Zhou, K., & Liao, Z. (2025). A Systematic Review of YOLO-Based Object Detection in Medical Imaging: Advances, Challenges, and Future Directions. Computers, Materials & Continua, 85(2), 2255–2303. https://doi.org/10.32604/CMC.2025.067994

Chien, C. T., Ju, R. Y., Chou, K. Y., & Chiang, J. S. (2024). YOLOv9 for fracture detection in pediatric wrist trauma X-ray images. Electronics Letters, 60(11), e13248. https://doi.org/10.1049/ELL2.13248;REQUESTEDJOURNAL:JOURNAL:1350911X;WEBSITE:WEBSITE:IETRESEARCH;WGROUP:STRING:PUBLICATION

Dritsas, E., & Trigka, M. (2025). Machine Learning in Intelligent Networks: Architectures, Techniques, and Use Cases. IEEE Access, 13, 102724–102745. https://doi.org/10.1109/ACCESS.2025.3577968

Hidayat, J. J., Anshor, A. H., Anwar, M. S., & Syaibani Anwar, M. (2026). Pemodelan Deteksi dan Klasifikasi Fraktur Tulang pada Radiografi X-Ray Menggunakan YOLOv8 dan Preprocessing CLAHE. JURNAL FASILKOM, 16(1), 31–45. https://doi.org/10.37859/JF.V16I1.11241

Joshi, S. (2022). Why Bounding Box Annotation is Crucial: The Ultimate Guide. https://www.hitechbpo.com/blog/bounding-box-annotation-guide.php?utm_source=chatgpt.com

Ju, R.-Y., & Cai, W. (2023). Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-47460-7

Ju, R. Y., & Cai, W. (2023). Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Scientific Reports, 13(1), 20077. https://doi.org/10.1038/S41598-023-47460-7

Ju, R. Y., Chien, C. T., & Chiang, J. S. (2024). YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection. Communications in Computer and Information Science, 2290 CCIS, 403–416. https://doi.org/10.1007/978-981-96-6972-1_28

Ju, R. Y., Chien, C. T., Lin, C. M., & Chiang, J. S. (2024). Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detection. Proceedings of the International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS, 2024. https://doi.org/10.1109/ISPACS62486.2024.10869064

Koonsanit, K., Thongvigitmanee, S., Pongnapang, N., & Thajchayapong, P. (2017). Image enhancement on digital X-ray images using N-CLAHE. BMEiCON 2017 - 10th Biomedical Engineering International Conference, 2017-January, 1–4. https://doi.org/10.1109/BMEICON.2017.8229130

Meena, T., & Roy, S. (2022). Bone Fracture Detection Using Deep Supervised Learning from Radiological Images: A Paradigm Shift. Diagnostics 2022, Vol. 12, Page 2420, 12(10), 2420. https://doi.org/10.3390/DIAGNOSTICS12102420

Olveres, J., González, G., Torres, F., Moreno-Tagle, J. C., Carbajal-Degante, E., Valencia-Rodríguez, A., Méndez-Sánchez, N., & Escalante- Ramírez, B. (2021). What is new in computer vision and artificial intelligence in medical image analysis applications. Quantitative Imaging in Medicine and Surgery, 11(8), 3830–3853. https://doi.org/10.21037/QIMS-20-1151

Oryan, A., Monazzah, S., & Bigham-Sadegh, A. (2015). Bone Injury and Fracture Healing Biology. Biomedical and Environmental Sciences, 28(1), 57–71. https://doi.org/10.3967/BES2015.006

Priyanka, M., Reddy, C. L., Aymon, U., & Jipeng, T. (2025). FractureNet: A Fusion Approach for Automated Hand Fracture Detection and Classification. Procedia Computer Science, 258, 1131–1146. https://doi.org/10.1016/J.PROCS.2025.04.348

Rutledge, M., Yap, M., & Chai, K. (2023). Plain film mandibular fracture detection using machine learning – Model development. Advances in Oral and Maxillofacial Surgery, 11, 100436. https://doi.org/10.1016/J.ADOMS.2023.100436

Shaban, W., El-Behaidy, W., & badawy, W. (2024). YOLOv8-Based Fracture Detection System. https://doi.org/10.21203/RS.3.RS-5455810/V1

Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data 2019 6:1, 6(1), 60-. https://doi.org/10.1186/S40537-019-0197-0

Su, Z., Adam, A., Nasrudin, M. F., Ayob, M., & Punganan, G. (2023). Skeletal Fracture Detection with Deep Learning: A Comprehensive Review. Diagnostics 2023, Vol. 13, Page 3245, 13(20), 3245. https://doi.org/10.3390/DIAGNOSTICS13203245

Wu, P., He, X., Dai, W., Zhou, J., Shang, Y., Fan, Y., & Hu, T. (2025). A Review on Research and Application of AI-Based Image Analysis in the Field of Computer Vision. IEEE Access, 13, 76684–76702. https://doi.org/10.1109/ACCESS.2025.3565300

Zhang, W., & Ji, S. (2025). Rehabilitation Driven Optimized YOLOv11 Model for Medical X-Ray Fracture Detection. Sensors 2025, Vol. 25, Page 5793, 25(18), 5793. https://doi.org/10.3390/S25185793