EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Arsitektur Hibrida CNN–LSTM Berbasis Retinex untuk Deteksi Lesi Periapikal pada Radiograf CBCT–Panoramik

Safar Dwi Kurniawan, Tri Haryo Nugroho, David Bani Adam

Applied Information Technology and Computer Science (AICOMS) · 30.12.2025 · 4 (2) · 86-95

DOI: 10.58466/vc18dh25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Information Technology and Computer Science (AICOMS), online erschienen am 30.12.2025. Verfasst von Safar Dwi Kurniawan und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Periapical lesion detection plays a crucial role in endodontic diagnosis; however, manual interpretation of Cone-Beam Computed Tomography (CBCT) and panoramic radiographs remains time-consuming, highly dependent on the clinician's expertise, and susceptible to diagnostic variability. This study proposes a hybrid deep learning framework that integrates a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture, combined with Retinex-based image enhancement, for the automatic detection and classification of periapical lesions. Retinex enhancement is employed as a preprocessing step to normalize illumination and improve lesion contrast. The hybrid CNN-LSTM model captures both spatial and contextual dependencies through sequential patch-based processing of panoramic and CBCT images. Using a dataset of 1,500 annotated images collected from clinical radiographic datasets and publicly available sources, the proposed model achieved an accuracy of 97.8%, precision of 96.4%, recall of 95.9%, and an F1-score of 0.96, significantly outperforming conventional CNN and U-Net models. These findings demonstrate that the integration of image enhancement and hybrid deep learning improves sensitivity to small lesions while reducing false-negative detections, offering a clinically viable AI-assisted approach for endodontic diagnosis.

Zitieren

APA

Kurniawan, S. D., Nugroho, T. H., & Adam, D. B. (2025). Arsitektur Hibrida CNN–LSTM Berbasis Retinex untuk Deteksi Lesi Periapikal pada Radiograf CBCT–Panoramik. Applied Information Technology and Computer Science (AICOMS), 4(2), 86-95. https://doi.org/10.58466/vc18dh25

Vancouver

Kurniawan SD, Nugroho TH, Adam DB. Arsitektur Hibrida CNN–LSTM Berbasis Retinex untuk Deteksi Lesi Periapikal pada Radiograf CBCT–Panoramik. Applied Information Technology and Computer Science (AICOMS). 2025;4(2):86-95. doi:10.58466/vc18dh25

BibTeX
@article{Kurniawan2025,
  author = {Kurniawan, Safar Dwi and Nugroho, Tri Haryo and Adam, David Bani},
  title = {Arsitektur Hibrida CNN–LSTM Berbasis Retinex untuk Deteksi Lesi Periapikal pada Radiograf CBCT–Panoramik},
  journal = {Applied Information Technology and Computer Science (AICOMS)},
  year = {2025},
  volume = {4},
  number = {2},
  pages = {86--95},
  doi = {10.58466/vc18dh25}
}
Kostenlos starten →