EUVIMEDEUVIMED entdecken
Crossref

Double Inertial Shrinking Projection Algorithm for Fixed Point Problems with Deep Learning Integration for Lumbar Spinal Stenosis Detection

PAPINWICH PAIMSANG, WONGTHAWAT LIAWRUNGRUEANG, JAKKAPHONG INPAN, PHISIT KATONGTUNG, KANOKWATT SHIANGJEN, JEN-CHIH YAO, PRASIT CHOLAMJIAK, SUTHEP SUANTAI, WATCHARAPORN CHOLAMJIAK

Carpathian Journal of Mathematics · 12.05.2026 · 42 (3) · 661-678

DOI: 10.37193/cjm.2026.03.12 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Carpathian Journal of Mathematics, online erschienen am 09.05.2026. Verfasst von PAPINWICH PAIMSANG und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper,we introduce a new modified hybrid iterative algorithm that integrates the shrink ing projection method with double inertial extrapolations for solving common fixed point problems of a count able family of quasi-nonexpansive mappings in real Hilbert spaces. By incorporating double inertial terms, our scheme enables more efficient utilization of historical information from the iterates and significantly enhances convergence behavior. Under appropriate conditions, we prove a strong convergence theorem for the proposed method. To demonstrate its practical utility, we applied our algorithm to an automated classification task for lumbar spinal stenosis using axial T2-weighted MRI. The pipeline integrates YOLO segmentation, SSIM-based filtering, data augmentation, VGG19 feature extraction, and classification via a regularized ELM. Our model achieved 96.41% test accuracy and a macro-average AUC of 0.97. Comparative experiments with several stan dard machine learning models, including XGBoost, Random Forest, LightGBM, and SVM, demonstrated that our approach not only yields higher accuracy but also exhibits superior generalization performance, with mini mal overfitting. These findings highlight the advantages of integrating advanced optimization algorithms with deep learning for improving classification performance in challenging medical image analysis tasks

Zitieren

APA

PAIMSANG, P., LIAWRUNGRUEANG, W., INPAN, J., KATONGTUNG, P., SHIANGJEN, K., YAO, J., CHOLAMJIAK, P., SUANTAI, S., & CHOLAMJIAK, W. (2026). Double Inertial Shrinking Projection Algorithm for Fixed Point Problems with Deep Learning Integration for Lumbar Spinal Stenosis Detection. Carpathian Journal of Mathematics, 42(3), 661-678. https://doi.org/10.37193/cjm.2026.03.12

Vancouver

PAIMSANG P, LIAWRUNGRUEANG W, INPAN J, KATONGTUNG P, SHIANGJEN K, YAO J, et al. Double Inertial Shrinking Projection Algorithm for Fixed Point Problems with Deep Learning Integration for Lumbar Spinal Stenosis Detection. Carpathian Journal of Mathematics. 2026;42(3):661-678. doi:10.37193/cjm.2026.03.12

BibTeX
@article{PAIMSANG2026,
  author = {PAIMSANG, PAPINWICH and LIAWRUNGRUEANG, WONGTHAWAT and INPAN, JAKKAPHONG and KATONGTUNG, PHISIT and SHIANGJEN, KANOKWATT and YAO, JEN-CHIH and CHOLAMJIAK, PRASIT and SUANTAI, SUTHEP and CHOLAMJIAK, WATCHARAPORN},
  title = {Double Inertial Shrinking Projection Algorithm for Fixed Point Problems with Deep Learning Integration for Lumbar Spinal Stenosis Detection},
  journal = {Carpathian Journal of Mathematics},
  year = {2026},
  volume = {42},
  number = {3},
  pages = {661--678},
  doi = {10.37193/cjm.2026.03.12}
}
Kostenlos starten →