Agata M. Wijata

Breast Cancer Segmentation Method in Ultrasound Images

The most common type of cancer among women is breast cancer. The early diagnosis is crucial in a treatment process. The radiology support system in the diagnostic process allows faster and more accurate radiographic contouring. The aim of the paper is to present a new method for ultrasound image segmentation of breast lesions. The segmentation technique is based on active contour models whereas anisotropic diffusion is used for preprocessing. The Dice Index calculated in most of analyzed cases was greater than 80%. Delineation of the tumor can also be used to calculate the size and volume automatically, and shortened the time of the diagnosis.

Impact of Music on the Effectiveness of Performing Mathematical-Logical Tasks

The article is the result of studies on the effects of music on human characteristics, with particular emphasis on the effectiveness of the performance of mathematical and logical operations. The material describes briefly some problems in the field of music therapy and presents results of a pilot study concerning possible improving of the intellectual work efficiency. A group of students who was faced with performance-related stress (standardized psychological tests and mathematical tasks) under music (Mozart and Beethoven) and no music condition was examined. Analyses showed that there was no significant difference in time of solving the tasks in silent and Mozart’s music condition. Also, time of performing exercises was longer during Beethoven stimulation than during silent condition. It may be concluded that commonly applied Mozart’s work does not always give the expected results and the other work can have stronger (but not necessarily better) effect on human being.

Image Guided Core Needle Biopsy of the Breast

This study presents the development of a multimodal data acquisition system dedicated to assist a core needle biopsy of the breast. The system consists of the following elements: optical and electromagnetic tracking devices, Time-of-Flight camera, thermovision camera and video camera. The system has been prepared for cooperating with any ultrasound machine. The aim of proposed system is to record locations of the tissue samples. The accuracy of calibration as well as patient registration is reported.

Evaluation of Puberty in Girls by Spectral Analysis of Voice

In this paper, a method for girls’ pubertal status evaluation is presented. The proposed algorithm uses voice features. Spectral analysis, Support Vector Machine and Random Forest Trees were employed. The obtained results are promising. Sensitivity reached 89.38%, when all features were included in the calculations (SVM). The highest specificity was achieved when only standard deviations were used (80.14% for the RF). Accuracy was greater than 80% for both classifiers when all features were used.

Preliminary Development of an Automatic Breast Tumour Segmentation Algorithm from Ultrasound Volumetric Images

Breast tumour is a leading cause for woman mortality. While cancer screening is mostly performed by the use of mammography, 3D ultrasound seems better suited for the purpose. It gives 3D view of the breast structure, is less painful and can be considered less invasive, as the patient is not exposed to x-ray radiation. Therefore, the development of automatic algorithms that remove from the diagnostician the tedious and time consuming task of finding suspicious regions in large volumetric images is of key importance. The paper concludes a preliminary study for the development of an automatic method for breast tumour segmentation in ultrasound volumetric images. The method is based on multiscale blob detector, watershed transform with the final precise segmentation performed by an active contour approach. The method has been evaluated using 16 volumes acquired from a breast phantom containing nodules. The obtained results reached up to 94.68% sensitivity, 100.00% specificity, 92.63% Dice index, 99.95% Accuracy, 92.61% Cohen’s Kappa index and 86.28% Jaccard index.

Signal to Noise Ratio in Intrauterine Environment During Acoustic Stimulation

Acoustic stimulation in prenatal period is the issue that interest growing group of people. In this paper the ratio of maternal internal sounds (noise) and attenuated sounds from external environment (signal) is considered. There is indicated that only narrow range of frequencies is not drowned by internal sounds. The problem of a distance of sound source was also considered. It was noticed that the application of sound source on maternal abdomen does not increase the sound level in the uterus.

Detection and Tracking of the Biopsy Needle Using Ultrasound Images

The aim of this work is to develop a method of detecting and tracking the needle tip using only two-dimensional ultrasound images. A novel method based on Hough transform, Shock filter and Gabor filter is proposed. The algorithm employs a US image to extract the needle tip. First derivative analysis is used for verification and correction the tip coordinates. The proposed method including the needle tip detection correction has an efficiency of 80%. The method may support radiologist during a core needle biopsy.

Longitudinal Voice Study (LoVoiS) Methodology and Preliminary Research Results

The paper describes an approach to the kids and youth pubertal evaluation using voice signal. The results of preliminary study conducted on a group of 109 children (58 boys and 51 girls aged 10–18 years) has been presented. The analysis of the voice fundamental frequency proves that this parameter strongly depends on the age (for boys) and on the time of the first menarche (for girls). Such a method for girls and boys maturation assessment is very important for, among others, anthropologist in their studies on social inequalities and observing secular trends.

Pre and Post Menarche—Girls’ Bodies Parameters Comparison

The article presents changes in body composition in adolescent girls. A review of available measurement techniques is preceded by an analysis of the physiology of puberty, whose social significance is very high, especially in the present stage of development of civilization. Measurement techniques are classified depending on the used equipment, with attention to the bioelectrical impedance. Girls aged 9.3 to 18.6 y. from schools in Cieszyn were analysed. On the basis of their status of maturation they were divided into two groups: before menarche and after menarche. The comparison of body composition of pre– and post–menarcheal girls had shown the change in all body components. However, increased weight associated with the development and maturation is mainly the result of the growth of fatness, which was reflected in both the anthropometric parameters (waist, hip circumferences, skinfolds) and BIA analysis.