EUVIMEDEUVIMED entdecken
Crossref

Fast and Accurate U-Net Model for Fetal Ultrasound Image Segmentation

Vahid Ashkani Chenarlogh, Mostafa Ghelich Oghli iD, Ali Shabanzadeh, Nasim Sirjani iD, Ardavan Akhavan, Isaac Shiri, Hossein Arabi, Morteza Sanei Taheri, Mohammad Kazem Tarzamni

Ultrasonic Imaging · 2022-01 · 44 (1) · 25-38

DOI: 10.1177/01617346211069882 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ultrasonic Imaging, online erschienen am 06.01.2022. Verfasst von Vahid Ashkani Chenarlogh und 8 weiteren Autor:innen. Beteiligte Einrichtung: Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Med Fanavaran Plus.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

U-Net based algorithms, due to their complex computations, include limitations when they are used in clinical devices. In this paper, we addressed this problem through a novel U-Net based architecture that called fast and accurate U-Net for medical image segmentation task. The proposed fast and accurate U-Net model contains four tuned 2D-convolutional, 2D-transposed convolutional, and batch normalization layers as its main layers. There are four blocks in the encoder-decoder path. The results of our proposed architecture were evaluated using a prepared dataset for head circumference and abdominal circumference segmentation tasks, and a public dataset (HC18-Grand challenge dataset) for fetal head circumference measurement. The proposed fast network significantly improved the processing time in comparison with U-Net, dilated U-Net, R2U-Net, attention U-Net, and MFP U-Net. It took 0.47 seconds for segmenting a fetal abdominal image. In addition, over the prepared dataset using the proposed accurate model, Dice and Jaccard coefficients were 97.62% and 95.43% for fetal head segmentation, 95.07%, and 91.99% for fetal abdominal segmentation. Moreover, we have obtained the Dice and Jaccard coefficients of 97.45% and 95.00% using the public HC18-Grand challenge dataset. Based on the obtained results, we have concluded that a fine-tuned and a simple well-structured model used in clinical devices can outperform complex models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

U-Netconvolutional neural networkdeep learningmedical image segmentationultrasound

Autor:innen und Institutionen

  • Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran.
  • Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium.
  • Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
  • Department of Radiology, Shohada-e-Tajrish Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
  • Department of Radiology, Imam Reza Hospital, Tabriz University of Medical Sciences, Tabriz, Iran.

ORCID-Profile: Mostafa Ghelich Oghli, Nasim Sirjani

Förderung

  • Med Fanavaran Plus

Zitieren

APA

Ashkani Chenarlogh, V., Ghelich Oghli, M., Shabanzadeh, A., Sirjani, N., Akhavan, A., Shiri, I., Arabi, H., Sanei Taheri, M., & Tarzamni, M. K. (2022). Fast and Accurate U-Net Model for Fetal Ultrasound Image Segmentation. Ultrasonic Imaging, 44(1), 25-38. https://doi.org/10.1177/01617346211069882

Vancouver

Ashkani Chenarlogh V, Ghelich Oghli M, Shabanzadeh A, Sirjani N, Akhavan A, Shiri I, et al. Fast and Accurate U-Net Model for Fetal Ultrasound Image Segmentation. Ultrasonic Imaging. 2022;44(1):25-38. doi:10.1177/01617346211069882

BibTeX
@article{AshkaniChenarlogh2022,
  author = {Ashkani Chenarlogh, Vahid and Ghelich Oghli, Mostafa and Shabanzadeh, Ali and Sirjani, Nasim and Akhavan, Ardavan and Shiri, Isaac and Arabi, Hossein and Sanei Taheri, Morteza and Tarzamni, Mohammad Kazem},
  title = {Fast and Accurate U-Net Model for Fetal Ultrasound Image Segmentation},
  journal = {Ultrasonic Imaging},
  year = {2022},
  volume = {44},
  number = {1},
  pages = {25--38},
  doi = {10.1177/01617346211069882}
}
Kostenlos starten →