scholarly journals Texton and sparse representation based texture classification of lung parenchyma in CT images

2016 ◽  
Author(s):  
Jie Yang ◽  
Xinyang Feng ◽  
Elsa D. Angelini ◽  
Andrew F. Laine
Keyword(s):  
Sparse Representation ◽  
Texture Classification ◽  
Lung Parenchyma ◽  
Ct Images

scholarly journals A Texton-Based Approach for the Classification of Lung Parenchyma in CT Images

2010 ◽  
pp. 595-602 ◽  
Author(s):  
Mehrdad J. Gangeh ◽  
Lauge Sørensen ◽  
Saher B. Shaker ◽  
Mohamed S. Kamel ◽  
Marleen de Bruijne ◽  
...  
Keyword(s):  
Lung Parenchyma ◽  
Ct Images

Use of Local Binary Pattern in Texture Classification of Carbonate Rock Micro-CT Images

2017 ◽  
Author(s):  
Khurshed Rahimov ◽  
Ali M. AlSumaiti ◽  
Hasan AlMarzouqi ◽  
Mohamed Soufiane Jouini
Keyword(s):  
Carbonate Rock ◽  
Local Binary Pattern ◽  
Texture Classification ◽  
Ct Images ◽  
Micro Ct

DELINEATION AND CLASSIFICATION OF LIVER CANCER USING LEVEL SET METHOD IN CT IMAGES

2017 ◽  
Vol 29 (06) ◽  
pp. 1750047
Author(s):  
Amita Das ◽  
S. S. Panda ◽  
Sukanta Sabut
Keyword(s):  
Machine Learning ◽  
Level Set ◽  
Texture Classification ◽  
Ct Images ◽  
Experimental Result ◽  
Support Vector ◽  
Svm Classifier ◽  
Correct Prediction ◽  
Liver Cancers

The paper proposes a modified approach of delineation and classification of two different types of liver cancers viz. Hepatocellular Carcinoma (HCC) and Metastatic Carcinoma (MET) from different slices of computed tomography (CT) scans images. A combined framework of reorganization and extraction of region of interest (ROI), texture feature extraction followed by texture classification by different machine learning approaches has been presented. Initially, adaptive thresholding has been applied to segment the liver region from CT images. Level set algorithm has been used for detecting the region of cancer tissues. In the classification stage, the delineated output lesions have been extracted with 38 features to build up the dataset. Two machine learning classifiers, support vector machine (SVM) and random forest (RF), have been used to train the dataset for correct prediction of cancer classes. Ten-fold cross-validation has been used to evaluate the performance of two classifiers. The efficiency of the proposed algorithm is tested in terms of accuracy, where the RF classifier achieved a higher accuracy of 95% compared to SVM classifier of 87%. The experimental result proves the superiority of RF classifier compared to SVM classifier with level-set features.

scholarly journals Sparse representation-based classification of mysticete calls

2018 ◽  
Vol 144 (3) ◽  
pp. 1550-1563 ◽  
Author(s):  
Thomas Guilment ◽  
Francois-Xavier Socheleau ◽  
Dominique Pastor ◽  
Simon Vallez
Keyword(s):  
Sparse Representation

scholarly journals Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Margarita Kirienko ◽  
Martina Sollini ◽  
Giorgia Silvestri ◽  
Serena Mognetti ◽  
Emanuele Voulaz ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Fdg Pet ◽  
Area Under The Curve ◽  
Ct Images ◽  
Tnm System ◽  
Positron Emission ◽  
Pet Ct ◽  
Test Sets ◽  
Fdg Pet Ct

Aim. To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images. Methods. We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model. Results. The algorithm, composed of two networks (a “feature extractor” and a “classifier”), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively. Conclusion. We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.

Sign in / Sign up

Export Citation Format

Share Document