Early Diagnosis System For Lung Nodules Based On The Integration Of A Higher-Order Mgrf Appearance Feature Model And 3d-Cnn

Document Type

Book Chapter

Source of Publication

Lung Cancer And Imaging

Publication Date



In this chapter, a new system for lung nodule diagnosis, using features extracted from one computed tomography (CT) scan, is presented. To get an accurate diagnosis of the detected lung nodules, the proposed framework integrates the following two groups of features: (i) appearance features that are modeled using higher-order Markov–Gibbs random field (MGRF)-model that has the ability to describe the spatial inhomogeneities inside the lung nodule; and (ii) local features that are extracted using 3D convolutional neural networks (3D-CNN) because of its ability to exploit the spatial correlation of input data in an efficient way. The novelty of this chapter is to accurately model the appearance of the detected lung nodules using a new developed 7th-order MGRF model that has the ability to model the existing spatial inhomogeneities for both small and large detected lung nodules, in addition to the integration with the extracted local features from 3D-CNN. Finally, a deep autoencoder (AE) classifier is fed by the above two feature groups to distinguish between the malignant and benign nodules.


978-0-7503-2540-0; 978-0-7503-2538-7


IOP Publishing


Medicine and Health Sciences


Image-analysis Approach, Blood-vessels, Accurate Identification, Automatic-analysis, Pulmonary Nodules, Texture Analysis, Classification, Framework, Segmentation, MRI

Indexed in Scopus


Open Access