Floor of log: a novel intelligent algorithm for 3D lung segmentation in computer tomography images
- PDF / 3,548,369 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 57 Downloads / 141 Views
SPECIAL ISSUE PAPER
Floor of log: a novel intelligent algorithm for 3D lung segmentation in computer tomography images Solon Alves Peixoto1 · Aldísio G. Medeiros1 · Mohammad Mehedi Hassan2 · M. Ali Akber Dewan3 · Victor Hugo C. de Albuquerque4 · Pedro P. Rebouças Filho1 Received: 8 July 2020 / Accepted: 20 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract This work presents a high-performance approach for 3D lung segmentation tasks in computer tomography images using a new intelligent machine learning algorithm called Floor of Log(FoL). The Support Vector Machine was used to learn the better parameter of the FoL algorithm using the parenchyma and its border as labels. Sensitivity, Matthews Correlation Coefficient (MCC), Hausdorff Distance (HD), Dice, Accuracy (ACC), and Jaccard were used to evaluate the proposed algorithm. The FoL was compared with recent 3D region growing, 3D Adaptive Crisp Active Contour, 3D OsiriX toolbox, and Level-set algorithm based on the coherent propagation method algorithms. The FoL algorithm achieves good results with approximately 19 s in the most significant result in an exam with 430 slices and presents similarity indexes achieving HD 3.5, DICE 83.63, and Jaccard 99.73 and qualitative indexes achieving Sensitivity 83.87, MCC 83.08, and ACC 99.62. The proposed approach of this work showed a simple and powerful algorithm to segment lung in computer tomography images of the chest region by combining similar textures, highlighting the lung structure. The FoL was presented as a new supervised clustering algorithm which can be trained to achieve better results and attached to other approaches as Convolutional Deep Neural Networks applications. Keywords Lung Segmentation · Image Processing · Clustering · Floor of Log · Deep learning
1 Introduction In recent years, we have witnessed a significant growth of multimedia healthcare data in the form of text, computer tomography images, audio, video and so forth [16, 17, 44]. They are used in various healthcare applications such as 3D lung segmentation task in pulmonary pathologies [15, 33, 48]. The growing applications related to the detection of * Mohammad Mehedi Hassan [email protected] Solon Alves Peixoto [email protected] Aldísio G. Medeiros [email protected] M. Ali Akber Dewan [email protected] Victor Hugo C. de Albuquerque [email protected] Pedro P. Rebouças Filho [email protected]
pulmonary pathologies have called attention worldwide. The patients with asthma overtake 300 million where some sudden symptoms are responsible for a big part of this value. Some factors involve some additional risk for the apparition of pulmonary diseases, including pollution, lifestyle related to sedentarism, smoking, which significantly affects the ratio of the number of lung pathologies per year [2].
1
Laboratório de Processamento Digital de Imagens, Sinais e Computação Aplicada, Instituto Federal de Federal de Educação, Ciência e Tecnologia do Ceará (IFCE), Cear
Data Loading...
