EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning

Zainab Riaz iD, Bangul Khan iD, Saad Abdullah iD, Samiullah Khan, Md Shohidul Islam

Bioengineering · 20.08.2023 · 10 (8) · 981

DOI: 10.3390/bioengineering10080981 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 20.08.2023. Verfasst von Zainab Riaz und 4 weiteren Autor:innen. Beteiligte Einrichtung: Hong Kong Center for Cerebro-Cardiovascular Health Engineering (COCHE), Hong Kong SAR, China. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Lung cancer is one of the most fatal cancers worldwide, and malignant tumors are characterized by the growth of abnormal cells in the tissues of lungs. Usually, symptoms of lung cancer do not appear until it is already at an advanced stage. The proper segmentation of cancerous lesions in CT images is the primary method of detection towards achieving a completely automated diagnostic system.

Method

In this work, we developed an improved hybrid neural network via the fusion of two architectures, MobileNetV2 and UNET, for the semantic segmentation of malignant lung tumors from CT images. The transfer learning technique was employed and the pre-trained MobileNetV2 was utilized as an encoder of a conventional UNET model for feature extraction. The proposed network is an efficient segmentation approach that performs lightweight filtering to reduce computation and pointwise convolution for building more features. Skip connections were established with the Relu activation function for improving model convergence to connect the encoder layers of MobileNetv2 to decoder layers in UNET that allow the concatenation of feature maps with different resolutions from the encoder to decoder. Furthermore, the model was trained and fine-tuned on the training dataset acquired from the Medical Segmentation Decathlon (MSD) 2018 Challenge.

Results

The proposed network was tested and evaluated on 25% of the dataset obtained from the MSD, and it achieved a dice score of 0.8793, recall of 0.8602 and precision of 0.93. It is pertinent to mention that our technique outperforms the current available networks, which have several phases of training and testing.

Schlagwörter

Stichwörter der Autor:innen

CTMobileNetV2UNETdeep learninglung cancermedical imagingpulmonary nodule

Autor:innen und Institutionen

  • Hong Kong Center for Cerebro-Cardiovascular Health Engineering (COCHE), Hong Kong SAR, China.
  • Department of Biomedical Engineering, City University Hongkong, Hong Kong SAR, China.
  • Division of Intelligent Future Technologies, School of Innovation, Design and Engineering, Mälardalen University, P.O. Box 883, 721 23 Västerås, Sweden.
  • Center for Eye & Vision Research, 17W Science Park, Hong Kong SAR, China.

ORCID-Profile: Zainab Riaz, Bangul Khan, Saad Abdullah

Zitieren

APA

Riaz, Z., Khan, B., Abdullah, S., Khan, S., & Islam, M. S. (2023). Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning. Bioengineering, 10(8), 981. https://doi.org/10.3390/bioengineering10080981

Vancouver

Riaz Z, Khan B, Abdullah S, Khan S, Islam MS. Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning. Bioengineering. 2023;10(8):981. doi:10.3390/bioengineering10080981

BibTeX
@article{Riaz2023,
  author = {Riaz, Zainab and Khan, Bangul and Abdullah, Saad and Khan, Samiullah and Islam, Md Shohidul},
  title = {Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning},
  journal = {Bioengineering},
  year = {2023},
  volume = {10},
  number = {8},
  pages = {981},
  doi = {10.3390/bioengineering10080981}
}
Kostenlos starten →