EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

Effects of Image Degradation on Deep Neural Network Classification of Scaphoid Fracture Radiographs: Comparison Study of Different Noise Types

Chihung Lin iD, Alfred P Yoon iD, Chien-Wei Wang iD, Tung Chao iD, Kevin C Chung iD, Chang-Fu Kuo iD

JMIR Medical Informatics · 22.01.2026 · 14 · e65596-e65596

DOI: 10.2196/65596 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift JMIR Medical Informatics, online erschienen am 22.01.2026. Verfasst von Chihung Lin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Taoyuan, Taiwan. Hauptthemen laut MEDLINE: Scaphoid Bone, Deep Learning, Fractures, Bone, Neural Networks, Computer. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Deep learning models have shown strong potential for automated fracture detection in medical images. However, their robustness under varying image quality remains uncertain, particularly for small and subtle fractures, such as scaphoid fractures. Understanding how different types of image perturbations affect model performance is crucial for ensuring reliable deployment in clinical practice.

Objective

This study aimed to evaluate the robustness of a deep learning model trained to detect scaphoid fractures in radiographs when exposed to various image perturbations. We sought to identify which perturbations most strongly impact performance and to explore strategies to mitigate performance degradation.

Methods

Radiographic datasets were systematically modified by applying Gaussian noise, blurring, JPEG compression, contrast-limited adaptive histogram equalization, resizing, and geometric offsets. Model accuracy was evaluated across different perturbation types and levels. Image quality was quantified using peak signal-to-noise ratio and structural similarity index measure to assess correlations between degradation and model performance.

Results

Model accuracy declined with increasing perturbation severity, but the extent varied across perturbation types. Gaussian blur caused the most substantial performance drop, whereas contrast-limited adaptive histogram equalization increased the false-negative rate. The model demonstrated higher resilience to color perturbations than to grayscale degradations. A strong linear correlation was found between peak signal-to-noise ratio–structural similarity index measure and accuracy, suggesting that better image quality led to improved detection. Geometric offsets and pixel value rescaling had minimal influence, whereas resolution was the dominant factor affecting performance.

Conclusions

The findings indicate that image quality, especially resolution and blurring, substantially influences the robustness of deep learning–based fracture detection models. Ensuring adequate image resolution and quality control can enhance diagnostic reliability. These results provide valuable insights for designing more accurate and resilient medical imaging models under real-world variability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Scaphoid BoneDeep LearningFractures, BoneNeural Networks, ComputerWrist FracturesRadiographyImage Processing, Computer-AssistedHumansSignal-To-Noise Ratio

Stichwörter der Autor:innen

CLAHEPSNRSSIMcontrast-limited adaptive histogram equalizationimage qualityneural network.peak signal-to-noise ratioscaphoid fracturesstructural similarity index measure

Autor:innen und Institutionen

  • Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Taoyuan, Taiwan.
  • Department of Artificial Intelligence, Chang Gung University, Taoyuan, Taiwan.
  • Division of Plastic and Reconstructive Surgery, Section of Hand and Microvascular Surgery, University of California Davis Medical Center, Sacramento, CA, United States.
  • Comprehensive Hand Center, Michigan Medicine, Ann Arbor, MI, United States.
  • Division of Rheumatology, Allergy and Immunology, Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, No.5, Fuxing Street, Guishan District, Taoyuan City 333, Taoyuan, 333, Taiwan, 886 3328-120…
  • College of Medicine, Chang Gung University, Taoyuan, Taiwan.

ORCID-Profile: Chihung Lin, Alfred P Yoon, Chien-Wei Wang, Tung Chao, Kevin C Chung, Chang-Fu Kuo

Zitieren

APA

Lin, C., Yoon, A. P., Wang, C. W., Chao, T., Chung, K. C., & Kuo, C. F. (2026). Effects of Image Degradation on Deep Neural Network Classification of Scaphoid Fracture Radiographs: Comparison Study of Different Noise Types. JMIR Medical Informatics, 14, e65596-e65596. https://doi.org/10.2196/65596

Vancouver

Lin C, Yoon AP, Wang CW, Chao T, Chung KC, Kuo CF. Effects of Image Degradation on Deep Neural Network Classification of Scaphoid Fracture Radiographs: Comparison Study of Different Noise Types. JMIR Medical Informatics. 2026;14:e65596-e65596. doi:10.2196/65596

BibTeX
@article{Lin2026,
  author = {Lin, Chihung and Yoon, Alfred P and Wang, Chien-Wei and Chao, Tung and Chung, Kevin C and Kuo, Chang-Fu},
  title = {Effects of Image Degradation on Deep Neural Network Classification of Scaphoid Fracture Radiographs: Comparison Study of Different Noise Types},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e65596--e65596},
  doi = {10.2196/65596}
}
Kostenlos starten →