A soft computing automatic based in deep learning with use of fine-tuning for pulmonary segmentation in computed tomography images

The segmentation of medical images is a significant challenge for computer vision and medical techniques. In the lungs, the difficulty is mainly due to the presence of lung diseases, different dimensions of the lung, and different types and configurations of medical imaging devices. Computed tomogra...

Full description

Saved in:
Bibliographic Details
Published in:Applied soft computing 2021-11, Vol.112, p.107810, Article 107810
Main Authors: Xu, Yongzhao, Souza, Luís F.F., Silva, Iágson C.L., Marques, Adriell G., Silva, Francisco H.S., Nunes, Virgínia X., Han, Tao, Jia, Chuanyu, de Albuquerque, Victor Hugo C., Filho, Pedro P. Rebouças
Format: Article
Language:English
Subjects:
CAD
Fine-tuning
Generalization of models
Lung segmentation
Mask R-CNN
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The segmentation of medical images is a significant challenge for computer vision and medical techniques. In the lungs, the difficulty is mainly due to the presence of lung diseases, different dimensions of the lung, and different types and configurations of medical imaging devices. Computed tomography (CT) is a tool to aid clinical diagnosis; several systems based on computer-aided diagnostics (CAD) are developed or enhanced from CT images combined with computational methods. This study proposes an innovative approach based on the generalization of models for pulmonary segmentation in CT images, using the Convolutional Neural Network Based on Mask Regions (Mask R-CNN) combined with image processing techniques, K-means clustering, region growing and Parzen window through fine-tuning. Our models achieved satisfactory results with 97% Accuracy and 98% Dice, 99% Sensitivity, and 97% Positive Predictive Value (PPV) in our best MPK model. The method was able to generalize its learning to solve different pulmonary segmentation problems in different lung CT databases. A second set of data was used, obtaining even better results. The results obtained for this second data set were: 98% Accuracy, 99% Dice, 100% Sensitivity, and 98% PPV, demonstrating the effectiveness of our method. •Innovative approach for pulmonary segmentation from CT images.•Optimized Mask R-CNN for segmentation of pulmonary medical images.•Novel model has outperformed the other models.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2021.107810