EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

COLONOSCOPIC POLYP SEGMENTATION USING SEGFORMER-B0 WITH A DICE-BCE HYBRID LOSS

Ahmad Yani, San Sudirman, M. Zulpahmi, Emi Suryadi, Bahtiar Imran

Jurnal Kecerdasan Buatan dan Teknologi Informasi · 10.05.2026 · 5 (2) · 235-242

DOI: 10.69916/jkbti.v5i2.476 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal Kecerdasan Buatan dan Teknologi Informasi, online erschienen am 10.05.2026. Verfasst von Ahmad Yani und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Colorectal cancer is one of the leading causes of cancer-related deaths worldwide, with most cases originating from early lesions such as colon polyps. Early detection through colonoscopy is essential to reduce mortality rates; however, accurate polyp identification remains challenging due to variations in shape, size, texture, and illumination conditions. This study aims to implement and evaluate the SegFormer-B0 architecture combined with a Dice-BCE hybrid loss function for polyp segmentation in colonoscopy images. The study utilized the public Kvasir-SEG dataset consisting of 1,000 colonoscopy images with pixel-level annotations. The dataset was divided into 80% training data and 20% validation data. Image preprocessing included resizing to 256×256 pixels and normalization using ImageNet statistics. The model was trained for 25 epochs using the AdamW optimizer with a learning rate of 1×10⁻⁴. Performance evaluation was conducted using Dice Coefficient, Intersection over Union (IoU), Sensitivity, and Specificity metrics. The experimental results demonstrated that the proposed model achieved a Dice Coefficient of 89.92%, Mean IoU of 81.90%, Sensitivity of 89.12%, and Specificity of 98.51%. The training process also showed stable convergence, supported by a training loss of 7.53% and validation loss of 23.30%. The findings indicate that the integration of SegFormer-B0 with the Dice-BCE hybrid loss effectively improves segmentation accuracy and stability while addressing class imbalance issues in colonoscopy images. Therefore, the proposed approach has strong potential to support computer-aided diagnosis systems for colorectal cancer screening.

Zitieren

APA

Yani, A., Sudirman, S., Zulpahmi, M., Suryadi, E., & Imran, B. (2026). COLONOSCOPIC POLYP SEGMENTATION USING SEGFORMER-B0 WITH A DICE-BCE HYBRID LOSS. Jurnal Kecerdasan Buatan dan Teknologi Informasi, 5(2), 235-242. https://doi.org/10.69916/jkbti.v5i2.476

Vancouver

Yani A, Sudirman S, Zulpahmi M, Suryadi E, Imran B. COLONOSCOPIC POLYP SEGMENTATION USING SEGFORMER-B0 WITH A DICE-BCE HYBRID LOSS. Jurnal Kecerdasan Buatan dan Teknologi Informasi. 2026;5(2):235-242. doi:10.69916/jkbti.v5i2.476

BibTeX
@article{Yani2026,
  author = {Yani, Ahmad and Sudirman, San and Zulpahmi, M. and Suryadi, Emi and Imran, Bahtiar},
  title = {COLONOSCOPIC POLYP SEGMENTATION USING SEGFORMER-B0 WITH A DICE-BCE HYBRID LOSS},
  journal = {Jurnal Kecerdasan Buatan dan Teknologi Informasi},
  year = {2026},
  volume = {5},
  number = {2},
  pages = {235--242},
  doi = {10.69916/jkbti.v5i2.476}
}
Kostenlos starten →