A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images.

Biomechanical and clinical gait research observes muscles and tendons in limbs to study their functions and behaviour. Therefore, movements of distinct anatomical landmarks, such as muscle-tendon junctions, are frequently measured. We propose a reliable and time efficient machine-learning approach to track these junctions in ultrasound videos and support clinical biomechanists in gait analysis. In order to facilitate this process, a method based on deep-learning was introduced. We gathered an extensive dataset, covering 3 functional movements, 2 muscles, collected on 123 healthy and 38 impaired subjects with 3 different ultrasound systems, and providing a total of 66864 annotated ultrasound images in our network training. Furthermore, we used data collected across independent laboratories and curated by researchers with varying levels of experience. For the evaluation of our method a diverse test-set was selected that is independently verified by four specialists. We show that our model achieves similar performance scores to the four human specialists in identifying the muscle-tendon junction position. Our method provides time-efficient tracking of muscle-tendon junctions, with prediction times of up to 0.078 seconds per frame (approx. 100 times faster than manual labeling). All our codes, trained models and test-set were made publicly available and our model is provided as a free-to-use online service on https://deepmtj.org/.

System identification and mathematical modeling of the pandemic spread COVID-19 in Serbia.

This paper presents applications of control system theory in biomedical engineering. These methodologies are used in engineering sciences to obtain a mathematical model of systems, but system identification as scientific methodology is rarely used in biomedical engineering. The paper presents exemplarily control theory and system identification as methods for obtaining a mathematical model of the spread SARS-CoV-2 virus. The models obtained in the course of this are data-driven and strongly data-dependent. The available dataset allowed us to consider a model of a pandemic spread in the context of both the number of tested individuals and the number of infected individuals and with a resultant model that is nonlinear. We also considered a mathematical model for the dependence between the number of confirmed infected individuals and the number of deaths caused by the disease. The resulting model is linear given with the transfer function corresponding to the second-order differential equation. The mathematical models developed were additionally analyzed in accordance with controllability and observability.

Automatic Tracking of the Muscle Tendon Junction in Healthy and Impaired Subjects using Deep Learning.

Recording muscle tendon junction displacements during movement, allows separate investigation of the muscle and tendon behaviour, respectively. In order to provide a fully-automatic tracking method, we employ a novel deep learning approach to detect the position of the muscle tendon junction in ultrasound images. We utilize the attention mechanism to enable the network to focus on relevant regions and to obtain a better interpretation of the results. Our data set consists of a large cohort of 79 healthy subjects and 28 subjects with movement limitations performing passive full range of motion and maximum contraction movements. Our trained network shows robust detection of the muscle tendon junction on a diverse data set of varying quality with a mean absolute error of 2.55 ± 1 mm. We show that our approach can be applied for various subjects and can be operated in real-time. The complete software package is available for open-source use.

[Analysis of image quality and dose calculation accuracy in cone beam CT acquisitions with limited projection data (half scan, half fan) with regard to usability for adaptive radiation therapy treatment planning]. / Untersuchung von Bildqualität und Genauigkeit der Dosisberechnung bei cone-beam-CT-Aufnahmen mit reduziertem Projektionsdatensatz (half scan, half fan) im Hinblick auf die Verwendbarkeit für die adaptive Bestrahlungsplanung.

UNLABELLED: Subject of this study is the question of whether cone beam CT (CBCT) images with reduced projection data are suitable for use in adaptive radiation therapy (ART) treatment planning. For this purpose image quality and dose calculation accuracy depending on imaging modality were analysed. In this context, two CBCT-methods will be indicated having reduced projection data sets: Scans acquired with 200° rotation angle in order to accelerate the CBCT process (half scan), or scans with an asymmetric cone beam and detector offset, used to enlarge the field-of-view (half fan). METHODS: For three different CBCT-modes (On-Board-Imaging, Varian Medical Systems), two of them based on reduced projection data, and a conventional multidetector CT system, the main image quality parameters were studied. Treatment plans for two phantoms were transferred to all datasets and re-computed to analyse dose calculation accuracy. Furthermore imaging dose was measured for all modalities. RESULTS: All three CBCT-modes showed similar results with regard to image quality. It was found, that a reduction in projection data does not necessarily involve deterioration in image quality parameters. For dose calculation based on CBCT images, a good agreement with the reference plan was found, with a maximum deviation for the mean dose in regions of interest of 1.1%. Imaging dose was found to be 2.5 cGy and 2.9 cGy for the large-FOV mode and the partial rotation mode, respectively, and 5.4 cGy for the 360°-full fan mode.

Investigation of electric current perception thresholds of different EHS groups.

An increasing number of persons with health symptoms of unclear origin take refuge in the hypothesis that they suffer from electromagnetic hypersensitivity (EHS). So far EHS is not an accepted diagnosis and there is no validated test to verify the proposed relationship between electromagnetic fields and symptoms. Groups reporting EHS are very heterogeneous but share a belief that they have an increased sensitivity to electromagnetic fields. It was studied to which extent a quantitative indicator for electrosensitivity, the electric current perception threshold, and its variability coefficient, depend on the recruitment strategy for self-declared hypersensitive persons. Individual electrosensitivity was investigated by provocation of the lower arms to directly coupled 50 Hz electric currents. Self-declared EHS persons were selected from members of a self aid group, from responders to a newspaper call, and from persons actively asking for investigations in their search for help. It turned out that quantitative electrosensitivity was quite different among the three groups. It is interesting that the members of the EHS self aid group exhibit a considerable overlap with general population sample. Pooled together it could be shown that hypersensitive persons as a group differ significantly from the general population sample, however with a pronounced overlap with the normal range. It can be concluded that EHS groups are very inhomogeneous and contain numerous persons with no increased ability to perceive low frequency electric or magnetic fields. This investigation shows the importance of the study design, in particular of the recruitment strategies of EHS persons for the final outcome.

Does "electromagnetic pollution" cause illness? An inquiry among Austrian general practitioners.

More and more self-declared electromagnetic hypersensitive patients are entering physicians' practices seeking help. To assess the prevalence of cases and the opinion of Austrian physicians regarding the potential health-relevance of environmental electromagnetic fields ("electromagnetic pollution"), a statistical investigation among general practitioners was undertaken, with surprising results. Only one-third report on never having been asked about the health impact of electromagnetic pollution by patients. An overwhelming percentage of general practitioners (up to 96%) to some degree, or totally, believe in a health-relevant role of environmental electromagnetic fields, and only 39% have never associated health symptoms with "electromagnetic pollution". Two-thirds are consulted occasionally or even frequently by self-declared electromagnetic hypersensitive patients. However, sound information seems to be lacking. Knowledge on existing electromagnetic exposure limits and on environmental field levels in relation to them is poor. It is remarkable that authorities play a marginal role in informing physicians. Only 4% mention having received information on "electromagnetic pollution" from such a source. It is rather remarkable that there is such a widespread contradiction between physicians' opinions and established national and international health risk assessment. With respect to the frequency with which doctors are confronted with this issue, the results demonstrate an urgent need for action.

Electrosensibility and electromagnetic hypersensitivity.

Electromagnetic sensibility, the ability to perceive electric and electromagnetic exposure, and electromagnetic hypersensitivity (EHS), developing health symptoms due to exposure to environmental electromagnetic fields, need to be distinguished. Increased electrosensibility is a necessary, however, not a sufficient condition for electromagnetic hypersensitivity. At an extended sample of the general population of 708 adults, including 349 men and 359 women aged between 17 and 60 years, electrosensibility was investigated and characterized by perception threshold and its standard deviation. By analyzing the probability distributions of the perception threshold of electric 50 Hz currents, evidence could be found for the existence of a subgroup of people with significantly increased electrosensibility (hypersensibility) who as a group could be differentiated from the general population. The presented data show that the variation of the electrosensibility among the general population is significantly larger than has yet been estimated by nonionizing radiation protection bodies, but much smaller than claimed by hypersensitivity self-aid groups. These quantitative results should contribute to a less emotional discussion of this problem. The investigation method presented, is capable of exclusion diagnostics for persons suffering from the hypersensitivity syndrome.