EUVIMEDEUVIMED entdecken
Crossref

Lung cancer segmentation Using the Att-U-Net Model on PET-CT Images

A Ayadi, I Hammami, O Mdimagh

Radiography · 2026-05 · 32 (4) · 103403

DOI: 10.1016/j.radi.2026.103403 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiography, 2026-05. Verfasst von A Ayadi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Tunisian Center for Nuclear Sciences and Technology, Technopark Sidi Thabet, Tunisia; Research Laboratory on Energy and Matter for Nuclear Science De…. Hauptthemen laut MEDLINE: Lung Neoplasms, Positron Emission Tomography Computed Tomography, Image Processing, Computer-Assisted. Die Arbeit nennt 26 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION Lung cancer is the leading cause of cancer-related deaths worldwide, emphasizing the need for early and accurate diagnosis. Precise segmentation of lung regions and tumors in imaging is critical for effective diagnosis and treatment. This study investigates the Attention U-Net (Att-U-Net) model for segmenting lung tissues and tumors in positron emission tomography-computed tomography (PET-CT) images. METHODS The Att-U-Net model was trained and evaluated for lung tissue and tumor segmentation using the publicly available Lung-PET-CT-Dx dataset from the Cancer Imaging Archive. Performance was measured using Dice Similarity Coefficient (DSC) and Intersection over Union (IoU), with Binary Cross-Entropy and Dice loss functions. RESULTS The Att-U-Net achieved a DSC of 0.81 and an IoU of 0.69 for tumor segmentation, indicating strong alignment between predicted and actual tumor regions. CONCLUSION The model shows high potential for accurately segmenting lung tumors and tissues on PET-CT images, supporting improved diagnosis and treatment planning. IMPLICATIONS FOR PRACTICE Incorporating Att-U-Net into clinical workflows could enhance segmentation accuracy, assist clinicians in decision-making, reduce manual effort, and promote more personalized treatment strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsPositron Emission Tomography Computed TomographyImage Processing, Computer-AssistedHumans

Stichwörter der Autor:innen

Deep learningPET-CT imagesTumor segmentationU-net modellung cancer

Autor:innen und Institutionen

  • Tunisian Center for Nuclear Sciences and Technology, Technopark Sidi Thabet, Tunisia; Research Laboratory on Energy and Matter for Nuclear Science Development (LR16CNSTN02), Ministry of Higher Education and Research, Tu…
  • Research Laboratory on Energy and Matter for Nuclear Science Development (LR16CNSTN02), Ministry of Higher Education and Research, Tunisia; UTM, Higher Institute for Medical Technologies of Tunis, Tunisia.
  • UTM, Higher Institute for Medical Technologies of Tunis, Tunisia.

Zitieren

APA

Ayadi, A., Hammami, I., & Mdimagh, O. (2026). Lung cancer segmentation Using the Att-U-Net Model on PET-CT Images. Radiography, 32(4), 103403. https://doi.org/10.1016/j.radi.2026.103403

Vancouver

Ayadi A, Hammami I, Mdimagh O. Lung cancer segmentation Using the Att-U-Net Model on PET-CT Images. Radiography. 2026;32(4):103403. doi:10.1016/j.radi.2026.103403

BibTeX
@article{Ayadi2026,
  author = {Ayadi, A and Hammami, I and Mdimagh, O},
  title = {Lung cancer segmentation Using the Att-U-Net Model on PET-CT Images},
  journal = {Radiography},
  year = {2026},
  volume = {32},
  number = {4},
  pages = {103403},
  doi = {10.1016/j.radi.2026.103403}
}
Kostenlos starten →