EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards Automated Quality Assurance: Integrating Deep Learning and Classical ML into the Digital Radiography Pipeline

Hsuan-Yu Chen iD, Cheng-Fu Chou iD, Sheng-Hung Liao, Meng-Hsun Wu, Kuan-Yi Chen, Ta-Wei Yang iD, Jungwei Wilfred Fan, Chih-Hao Chang iD

Diagnostics · 06.07.2026 · 16 (13) · 2111

DOI: 10.3390/diagnostics16132111 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 06.07.2026. Verfasst von Hsuan-Yu Chen und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedic Surgery, College of Medicine, National Taiwan University, No.7, Chung-Shan South Road, Zhong-Zheng District, Taipei 100, Tai…. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Taiwan University Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: To develop and evaluate a deep learning-based quality control system for Lumbar Spinal Digital Radiographs (LSDR), designed to automate and improve their evaluation and reduce reliance on manual reviews.

Methods

This retrospective study utilized a deep learning workflow comprising image segmentation, feature extraction, and a classification model. The dataset, including anteroposterior (AP) and lateral (LAT) X-ray images, was expanded through data augmentation techniques. Four U-Net-based models were assessed: standard U-Net, Swin-UNet, Attention U-Net, and Attention U-Net with the weight map, with the latter selected for its superior performance. Extracted features, such as brightness, contrast, and anatomical positioning, were used in an XGBoost classifier, which was evaluated using mean intersection over union (mIoU), accuracy, sensitivity, specificity, and AUC.

Results

The Attention U-Net with weighted attention outperformed the other models, achieving high mIoU scores in both AP and LAT views. The XGBoost classifier achieved the best performance in classifying images as “qualified” or “unqualified,” with an AUC of approximately 0.9, high accuracy, and balanced sensitivity and specificity. This approach effectively addressed class imbalances and improved model accuracy compared to traditional machine learning models such as MLP and SVM.

Conclusions

The developed automated quality control system demonstrated potential for enhancing image quality, enhancing diagnostic reliability, and optimizing clinical workflow efficiency.

Schlagwörter

Stichwörter der Autor:innen

automateddeep learninglumbar spine X-raypatient safetyquality control

Autor:innen und Institutionen

  • Department of Orthopedic Surgery, College of Medicine, National Taiwan University, No.7, Chung-Shan South Road, Zhong-Zheng District, Taipei 100, Taiwan.
  • Department of Orthopedic Surgery, Mayo Clinic, Rochester 55905, MN, USA.
  • Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei 106, Taiwan.
  • Department of Computer Science and Information Engineering, National Taiwan University, Taipei 106, Taiwan.
  • Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester 55905, MN, USA.

ORCID-Profile: Hsuan-Yu Chen, Cheng-Fu Chou, Ta-Wei Yang, Chih-Hao Chang

Förderung

  • National Taiwan University Hospital

Zitieren

APA

Chen, H. Y., Chou, C. F., Liao, S. H., Wu, M. H., Chen, K. Y., Yang, T. W., Fan, J. W., & Chang, C. H. (2026). Towards Automated Quality Assurance: Integrating Deep Learning and Classical ML into the Digital Radiography Pipeline. Diagnostics, 16(13), 2111. https://doi.org/10.3390/diagnostics16132111

Vancouver

Chen HY, Chou CF, Liao SH, Wu MH, Chen KY, Yang TW, et al. Towards Automated Quality Assurance: Integrating Deep Learning and Classical ML into the Digital Radiography Pipeline. Diagnostics. 2026;16(13):2111. doi:10.3390/diagnostics16132111

BibTeX
@article{Chen2026,
  author = {Chen, Hsuan-Yu and Chou, Cheng-Fu and Liao, Sheng-Hung and Wu, Meng-Hsun and Chen, Kuan-Yi and Yang, Ta-Wei and Fan, Jungwei Wilfred and Chang, Chih-Hao},
  title = {Towards Automated Quality Assurance: Integrating Deep Learning and Classical ML into the Digital Radiography Pipeline},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {13},
  pages = {2111},
  doi = {10.3390/diagnostics16132111}
}
Kostenlos starten →