Utilization of ultrasound imaging with various resolutions as modalities for thyroid nodules examination is growing rapidly. This is consistent with an increase in incidence of thyroid malignancy. Thyroid ultrasound examination is considered superior to other medical imaging modalities for its non-invasive, practical, inexpensive and painless. In the examination process, a radiologist expects areas of thyroid nodules that can be localized precisely from the surrounding normal tissue. Thus boundary of the nodules can be seen as to be regular or irregular. Boundary is one of the important features of malignancy that doctors use to make a diagnosis. Most malignant nodules have unclear and irregular boundaries. Imprecise segmentation result will lead to misdiagnosis based on boundary characteristics. Active contour segmentation technique is applied for detecting boundary of thyroid nodules and separating them with normal tissue iteratively. However, the characteristics of the ultrasound image that brings speckle noises make the segmentation process more complicated. It also resulted in interpretation errors and inaccuracies diagnosis made by a doctor. The intricacy of irregular nodule area can not easily be solved by changing the value of iteration on active contour. Therefore, speckle noise reduction method is needed to overcome this problem so that nodule area segmented properly. In this paper speckle noise reduction is done with bilateral filter. Comparison of image segmentation results of thyroid nodules with and without bilateral filter is attached at the end of this article. The combination of bilateral filter and active contour showed better results with the edge of the nodules firmly and clear.

Ultrasound image is commonly used to examine the malignancy characteristics of thyroid nodule. One of the important feature to diagnose of malignant thyroid nodule is based on echogenicity characteristic which is represented by the grey- level intensity of each nodule. Therefore, a computer-aided diagnosis (CADx) is necessary to examine the important features and classify which nodule is more likely to be a malignant or benign and should be given further treatment or not. This research proposes a scheme for classifying thyroid nodule based on texture features from histogram and laws' texture energy into four classes, i.e. anechoic, isoechoic, hypoechoic and markedly hypoechoic. Pre-processing step is conducted to enhance the ultrasound image followed by segmentation process using active contour without edge (ACWE). Feature extraction is performed by extracting 24 features and obtained 21 selected features based on information gain filter ranking. Then, these selected features are classified using multi-layer perceptron (MLP) algorithm. The classification results achieved the level of accuracy, sensitivity, specificity, PPV and NPV at 93.69%, 93.36%, 97.87%, 93.82% and 97.88%, respectively. These results indicate that the proposed scheme successfully classified the echogenicity of thyroid ultrasound nodules.

The radiologists diagnose thyroid cancer by analysing thyroid ultrasound nodule images. However, it tends to be subjective since it depends on the expertise and experience of the radiologists. Therefore, a computer aided diagnosis (CADx) system is necessary to to reduce subjectivity and to support the radiologists in final decision making of thyroid cancer diagnosis. This study aims to classify thyroid nodules of ultrasound images by analysing margin characteristics. The proposed approach is evaluated on 144 images with 64 smooth and 80 irregular margins. Some noises and artefacts are eliminated by employing adaptive median filter and speckle reducing bilateral filtering (SRBF). Thyroid nodule is then segmented based on morphological operation and active contour. In order to classify segmented nodules, a total of eight geometric features are extracted and subsequently undergo classification process. Two different kernels of support vector machine (SVM) consisting of linear and quadratic kernels are used to evaluate the performance of classification. Evaluation results show that the quadratic kernel has better performance than the linear ones with the accuracy of 92.30%, sensitivity of 91.88%, specificity of 92.73%, PPV of 92.80% and NPV of 91.80%. These results indicate that the proposed approach successfully classifies thyroid nodule based on margin characteristics and is useful for assisting the radiologists in diagnosing thyroid cancer by analysing thyroid ultrasound images.

Background. The inefficiency of the forehand stroke technique often stems from suboptimal execution of an athlete’s biomechanical movements. For a forehand stroke to be effective, each biomechanical component – the ankles, knees, hips, shoulders, and elbows – must function in an optimal manner. Disconnection of any of these elements can lead to ineffective technique. High speed, influenced by the racket speed at the point of impact, is a key indicator of a perfect forehand stroke. However, the challenge lies in the fact that an athlete’s movement and ball impact cannot be accurately observed with the naked eye, necessitating specialized tools for analysis. Study purpose. The study aims to develop software that assists in predicting ball speed outcomes based on an athlete’s biomechanical movement during a forehand stroke execution. Materials and methods. The research method employed R&D. Data collection techniques consisted of video recordings of athletes’ forehand strokes, which were later analyzed using software that examines movement angles of 10 national athletes. Results. The results indicated the average angles of elbows = 106.23, shoulders = 153.62, hips = 165.33, knees = 167.63, ankles = 164.54; and ball speed = 199.41 cm/s. Conclusions. The conclusion drawn is that to execute an effective forehand stroke with good ball speed, a moment of inertia must occur at the point of impact. The athletes should bend their elbow slightly, thereby reducing rotational resistance and increasing the speed of the racket head. The ankles, hips, and shoulders must move in synchronization within a continuous coordination chain, thereby allowing the athlete to fully leverage kinetic chain. The flexion movement of the elbow during the forward swing step is more effective than the extension movement where the elbow is slightly bent, resulting in a perfect shot.

Ultrasound image is one of the modalities that is widely used to examine the abnormality of thyroid gland since it is relatively low-cost and safety. Fine needle aspiration biopsy (FNAB) is usually used by radiologists to determine the thyroid nodule whether malignant or benign. Commonly, malignancy of thyroid nodule determined based on shape feature. This research proposes a scheme for classifying thyroid nodule based on shape feature analysis into two classes, i.e. round to oval and irregular classes. The proposed scheme is tested on 165 thyroid ultrasound images consisting of 61 round to oval images and 104 irregular images. The process is started by filtering image as the preprocessing step followed by segmentation process using active contour and morphological operation. Shape analysis is performed by extracting seven geometric features and 14 moment features. These features are then selected by using correlation based feature selection (CFS). Three selected features are classified using linear support vector machine (SVM). The classification results achieved the level of accuracy, sensitivity, specificity, PPV and NPV at 91.52%, 91.80%, 91.35%, 86.15%, and 95%, respectively. These results indicate that the proposed scheme successfully classified the shape of thyroid nodule.

Imaging modalities play a critical role in radiological procedures as they strive to achieve early disease detection. Among the existing modalities, ultrasound (US) is mostly utilized to investigate abnormalities of the glands such as in breast and thyroid screening.¹ US is real time, low cost, non-invasive, and user friendly.² The gold standard report of Breast Imaging Reporting and Data System (BIRADS)³ or Thyroid Imaging Reporting and Data System (TIRADS)⁴ is commonly used by radiologists to analyze US images. These quality assurances consist of valuable points describing shape, margin, orientation, and textural echo of suspicious lesions or nodules. It is worth noting that US visual analysis is expert dependent, which leads to high variabilities in interpretation and clinical recommendations.⁵ Therefore computer-aided diagnosis (CAD) systems have become a second-opinion reader by implementing appropriate image processing algorithms to improve radiologists’ diagnoses. All BIRADS and TIRADS features can be extracted properly only after the US objects are correctly segmented.⁶ Thus, the right segmentation method is a crucial part of accurate diagnosis in CAD systems.