Thyroid Ultrasound Texture Classification Using Autoregressive Features in Conjunction With Machine Learning Approaches

Abstract

The thyroid is one of the largest endocrine glands in the human body, which is involved in several body mechanisms like controlling protein synthesis, use of energy sources, and controlling the body's sensitivity to other hormones. Thyroid segmentation and volume reconstruction are hence essential to diagnose thyroid related diseases as most of these diseases involve a change in the shape and size of the thyroid over time. Classification of thyroid texture is the first step toward the segmentation of the thyroid. The classification of texture in thyroid Ultrasound (US) images is not an easy task as it suffers from low image contrast, presence of speckle noise, and non-homogeneous texture distribution inside the thyroid region. Hence, a robust algorithmic approach is required to accurately classify thyroid texture. In this paper, we propose three machine learning based approaches: Support Vector Machine; Artificial Neural Network; and Random Forest Classifier to classify thyroid texture. The computation of features for training these classifiers is based on a novel approach recently proposed by our team, where autoregressive modeling was applied on a signal version of the 2D thyroid US images to compute 30 spectral energy-based features for classifying the thyroid and non-thyroid textures. Our approach differs from the methods proposed in the literature as they use image-based features to characterize thyroid tissues. We obtained an accuracy of around 90% with all the three methods. INDEX TERMSMedical imaging, support vector machine, artificial neural network, random forest classifier, texture classification, thyroid ultrasound. During the course of his B.Sc., he worked as a Research Assistant with Fraunhofer Mevis, Bremen, Germany, and recently he was a Visiting Researcher with General Electric Healthcare, Milwaukee, USA. His research interest includes medical image processing, computer vision, and machine learning.

Parametrical modelling for texture characterization—A novel approach applied to ultrasound thyroid segmentation

“…Two different real US image datasets have been used to evaluate the proposed approach. The first dataset (in the sequel Dataset 1) has been introduced in [24] and involves six healthy human subjects freehand US images acquired using a Logiq E9 US device with a linear probe and equipped with an electromagnetic tracking system. This database has a total of 675 2D US slices with a 760 × 500 pixels with between 53 and 189 US slices per subject.…”

Effective Voting Ensemble of Homogenous Ensembling with Multiple Attribute-Selection Approaches for Improved Identification of Thyroid Disorder

“…A low-cost thyroid diagnostic report is now available to patients using this technique. To identify thyroid texture, researchers in this study [19] offer three machine-learning-based methods known as the SVM, RF, and ANN. The researchers generated 30 spectral energy-based attributes for these classifiers during training via autoregressive modeling on a signal variant of 2D thyroid US pictures.…”

Pixel Classification Based on Local Gray Level Rectangle Window Sampling for Amniotic Fluid Segmentation

“…Random forest (RF) is widely applied to solve some segmentation and classification problems in medical images [8,14 -16]. RF classifier is a type of ensemble learning method used to build a final classifier with a set of collections from individual weak classifiers (M) such as the binary tree [16]. This study trained a random forest classifier to classify each pixel into the classes contained in the amniotic fluid, placenta, uterus, and fetal.…”

“…Furthermore, this study uses Dice's Coefficient (DSC), Error Rate (ER), and Jaccard index to evaluate the segmentation performance. DSC measures the similarity between two objects, which in the case of this study is the overlap computation of overlap area between the ground truth image and segmentation amniotic fluid area of the proposed model [16]. ER presents the ratio of misclassified image pixels over the total amount [18].…”