Cargando…

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

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Riaz, Zainab, Khan, Bangul, Abdullah, Saad, Khan, Samiullah, Islam, Md Shohidul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451633/
https://www.ncbi.nlm.nih.gov/pubmed/37627866
http://dx.doi.org/10.3390/bioengineering10080981
_version_ 1785095462679740416
author Riaz, Zainab
Khan, Bangul
Abdullah, Saad
Khan, Samiullah
Islam, Md Shohidul
author_facet Riaz, Zainab
Khan, Bangul
Abdullah, Saad
Khan, Samiullah
Islam, Md Shohidul
author_sort Riaz, Zainab
collection PubMed
description 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.
format Online
Article
Text
id pubmed-10451633
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104516332023-08-26 Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning Riaz, Zainab Khan, Bangul Abdullah, Saad Khan, Samiullah Islam, Md Shohidul Bioengineering (Basel) Article 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. MDPI 2023-08-20 /pmc/articles/PMC10451633/ /pubmed/37627866 http://dx.doi.org/10.3390/bioengineering10080981 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Riaz, Zainab
Khan, Bangul
Abdullah, Saad
Khan, Samiullah
Islam, Md Shohidul
Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning
title Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning
title_full Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning
title_fullStr Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning
title_full_unstemmed Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning
title_short Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning
title_sort lung tumor image segmentation from computer tomography images using mobilenetv2 and transfer learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451633/
https://www.ncbi.nlm.nih.gov/pubmed/37627866
http://dx.doi.org/10.3390/bioengineering10080981
work_keys_str_mv AT riazzainab lungtumorimagesegmentationfromcomputertomographyimagesusingmobilenetv2andtransferlearning
AT khanbangul lungtumorimagesegmentationfromcomputertomographyimagesusingmobilenetv2andtransferlearning
AT abdullahsaad lungtumorimagesegmentationfromcomputertomographyimagesusingmobilenetv2andtransferlearning
AT khansamiullah lungtumorimagesegmentationfromcomputertomographyimagesusingmobilenetv2andtransferlearning
AT islammdshohidul lungtumorimagesegmentationfromcomputertomographyimagesusingmobilenetv2andtransferlearning