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/.

Long-term life history predicts current gut microbiome in a population-based cohort study.

Extensive scientific and clinical microbiome studies have explored contemporary variation and dynamics of the gut microbiome in human health and disease1-3, yet the role of long-term life history effects has been underinvestigated. Here, we analyzed the current, quantitative microbiome composition in the older adult Bruneck Study cohort (Italians, Bruneck, n = 304 (male, 154; female, 150); age 65-98 years) with extensive clinical, demographic, lifestyle and nutritional data collected over the past 26 years4. Multivariate analysis of historical variables indicated that medication history, historical physical activity, past dietary habits and specific past laboratory blood parameters explain a significant fraction of current quantitative microbiome variation in older adults, enlarging the explanatory power of contemporary covariates by 33.4%. Prediction of current enterotype by a combination of past and contemporary host variables revealed good levels of predictability (area under the curve (AUC), 0.78-0.83), with Prevotella and dysbiotic Bacteroides 2 being the best predicted enterotypes. These findings demonstrate long-term life history effects on the microbiota and provide insights into lifestyle variables and their role in maintaining a healthy gut microbiota in later life.

UStEMG: an Ultrasound Transparent Tattoo-based sEMG System for Unobtrusive Parallel Acquisitions of Muscle Electro-mechanics.

Human machine interfaces follow machine learning approaches to interpret muscles states, mainly from electrical signals. These signals are easy to collect with tiny devices, on tight power budgets, interfaced closely to the human skin. However, natural movement behavior is not only determined by muscle activation, but it depends on an orchestration of several subsystems, including the instantaneous length of muscle fibers, typically inspected by means of ultrasound (US) imaging systems. This work shows for the first time an ultra-lightweight (7 g) electromyography (sEMG) system transparent to ultrasound, which enables the simultaneous acquisition of sEMG and US signals from the same location. The system is based on ultrathin and skin-conformable temporary tattoo electrodes (TTE) made of printed conducting polymer, connected to a tiny, parallel-ultra-low power acquisition platform (BioWolf). US phantom images recorded with the TTE had mean axial and lateral resolutions of 0.90±0.02 mm and 1.058±0.005 mm, respectively. The root mean squares for sEMG signals recorded with the US during biceps contractions were at 57±10 µV and mean frequencies were at 92±1 Hz. We show that neither ultrasound images nor electromyographic signals are significantly altered during parallel and synchronized operation.Clinical relevance- Modern prosthetic engineering concepts use interfaces connected to muscles or nerves and employ machine learning models to infer on natural movement behavior of amputated limbs. However, relying only on a single data source (e.g., electromyography) reduces the quality of a fine-grained motor control. To address this limitation, we propose a new and unobtrusive device capable of capturing the electrical and mechanical behavior of muscles in a parallel and synchronized fashion. This device can support the development of new prosthetic control and design concepts, further supporting clinical movement science in the configuration of better simulation models.

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.

Improved Tracking of Muscle Tendon Junctions in Ultrasound Images Using Speckle Reduction.

Ultrasound imaging enables in-vivo investigations of muscle and tendon behaviour during human movement. Individual contributions of muscles and tendons to the behaviour of the whole muscle-tendon unit during locomotion are versatile. Therefore, movements of distinct landmarks, such as muscle tendon junctions are recorded and tracked in order to investigate internal dynamics of the muscle-tendon complex. In this study, we use a semi-automatic tracking method based on image segmentation and investigate how tracking accuracy can be improved using a sticks filter. We demonstrate that a speckle reduction decreases the root-mean-square error of the tracking result by up to 78.1%, depending on the chosen window size of the sticks filter.

Ultrasound as a Tool to Study Muscle-Tendon Functions during Locomotion: A Systematic Review of Applications.

Movement science investigating muscle and tendon functions during locomotion utilizes commercial ultrasound imagers built for medical applications. These limit biomechanics research due to their form factor, range of view, and spatio-temporal resolution. This review systematically investigates the technical aspects of applying ultrasound as a research tool to investigate human and animal locomotion. It provides an overview on the ultrasound systems used and of their operating parameters. We present measured fascicle velocities and discuss the results with respect to operating frame rates during recording. Furthermore, we derive why muscle and tendon functions should be recorded with a frame rate of at least 150 Hz and a range of view of 250 mm. Moreover, we analyze why and how the development of better ultrasound observation devices at the hierarchical level of muscles and tendons can support biomechanics research. Additionally, we present recent technological advances and their possible application. We provide a list of recommendations for the development of a more advanced ultrasound sensor system class targeting biomechanical applications. Looking to the future, mobile, ultrafast ultrasound hardware technologies create immense opportunities to expand the existing knowledge of human and animal movement.

What's new in small cell lung cancer - extensive disease? An overview on advances of systemic treatment in 2016.

Systemic therapy options for small cell lung cancer patients with extensive disease remain poor. After an initial response on first-line therapy, virtually all patients develop disease progression. For those who showed an initial response only few therapy options with low response rates are currently available. Until now, many experimental and targeted agents have failed to yield convincing clinical benefits, and new therapy options are clearly warranted for these patients. In this year's oncological congresses, several new therapy strategies, including checkpoint inhibition, showed promising results in ongoing trials. Furthermore, a potential benefit of new agents targeting DLL3, Aurora A kinase and PARP-inhibitor was reported. In this review we summarize new developments and critically highlight the most important and promising data in the relapsed small cell lung cancer disease.

Treatment of patients with refractory metastatic cancer according to molecular profiling on tumor tissue in the clinical routine: an interim-analysis of the ONCO-T-PROFILE project.

INTRODUCTION: Patients with refractory metastatic cancer have been shown to benefit from molecular profiling of tumor tissue. The ONCO-T-PROFILE project was launched in March 2014 at the Innsbruck Medical University. Within 2 years our project aims to recruit 110 patients with stage IV cancer refractory to standard therapy. Our data presented here are based on an interim-analysis. METHODS: Tumor tissue specimens were submitted for molecular profiling to the certified laboratory (Caris Life Science, USA). Druggable tumor targets were selected based on biomarker status to agents with potential clinical benefit. Clinical benefit was defined as a PFS ratio (=PFS upon treatment according to the molecular profile/ PFS upon the last prior therapy) ≥ 1.3. RESULTS: As of April 2015, tumors from 50 patients have been molecularly profiled and one or more targets were detectable in 48 specimens (98%). So far, 19 (38%) patients have been treated according to their molecular tumor profile. To date, 8 (42%) patients have reached a PFS ratio of ≥ 1.3. CONCLUSIONS: We could show that molecular profiling is feasible in the clinical routine. A proportion of patients might benefit from an individualized treatment approach based on molecular profiling. As a result, we will proceed to enroll patients in ONCO-T-PROFILE.

Improved survival of older patients with multiple myeloma in the era of novel agents.

Multiple myeloma (MM) is the most common hematologic malignancy in Europe. Although remaining an incurable disease, substantial progress has been made within the last two decades. However, until recently, improvement in overall survival (OS) was only documented in younger, transplant-eligible patients. In this analysis, we retrospectively investigated the outcome of older patients with newly diagnosed MM in an unselected patient population with a special focus on the use of novel agents in a routine care community-based, non-university setting. A total of 107 patients older than 65 years of age or patients aged 60-65 years with relevant comorbidities precluding the use of autologous stem cell transplantation diagnosed with MM between 2000 and 2011 at the two largest non-university hospitals of Eastern Switzerland were analyzed. Patients were grouped into two six-year periods by date of initial diagnosis, 2000-2005 and 2006-2011. The median follow-up was 6.9 (range of 2.1 to 9.4) years. The median OS for the entire cohort was 3.0 years (95% confidence interval, 2.4-4.4). The median OS was significantly longer for patients in the 2006-2011 group (4.3 years) compared with the 2000-2005 group (2.6 years, p = 0.04). The 5-year estimated OS improved from 26% to 38%; 1-year survival was similar in both groups (86% in the 2000-2005 group and 84% in the 2006-2011 group respectively). The use of novel agents showed a statistically significant correlation with OS, whereas the impact of age was only of borderline significance. In conclusion, we demonstrate improved OS outcomes in an unselected population of older patients with MM during the last decade. This improvement is associated with an increased use of novel agents for the treatment of transplant-ineligible MM patients in daily clinical practice. Copyright © 2015 John Wiley & Sons, Ltd.

Bilateral posterior ischaemic optic neuropathy after severe diabetic ketoacidosis, cardiopulmonary resuscitation and respiratory failure.

A 44-year-old male European with type I diabetes mellitus fell into diabetic ketoacidosis. In the emergency room, he developed an episode of asystole and respiratory failure requiring one cycle of cardiopulmonary resuscitation and extracorporeal membrane oxygenation (ECMO). Waking up 7 days later, he presented a bilateral complete loss of vision. Ophthalmological examination including funduscopy on days 1 and 10, after extubation, showed bilateral large round pupils non-reactive to light and a normal fundus. Neuroimaging studies, including MRI and MRA of the brain, were all within normal limits. A lumbar puncture and comprehensive serological testing excluded an infectious or rheumatic cause. An empirical high-dose intravenous steroid treatment administered for 5 days had no effect on his vision. His eye examination at 1.5 months follow-up showed a normal fundus except for progressive bilateral optic nerve disc pallor, which pointed towards the diagnosis of a posterior ischaemic optic neuropathy.

Structure and evolution of a rocksalt-mudrock-tectonite: The haselgebirge in the Northern Calcareous Alps.

The Northern Calcareous Alps are part of the Eastern Alps in Austria and Germany. The Mesozoic units of this fold-and-thrust belt were detached, thrusted and stacked along the evaporitic Haselgebirge Formation. Exposed in salt mines, rocksalt and mudrock form a two component tectonite: The rock type "haselgebirge" consists of 10-70 wt % halite with silt- to gravel- or block-sized components within a halite matrix, and the "kerngebirge" with >70 wt % halite. All rock types studied are fault rocks. By use of a temperature-independent subgrain size piezometer, the paleo-differential stress of halite was calculated at ca. 2.5 MPa in Altaussee and ca. 4.5 MPa in Berchtesgaden. Including data from a grain-size piezometer, temperatures were estimated at ca. 150 ± 20 °C and 110 ± 10 °C. This implies very high strain rates, which are about 10-10-10-9 s-1. During the tectonic movement, the halite deformed, recrystallized, and crystallized as veins in mudrock fractures. We interpret high overpressure of the pore fluid to have significantly contributed to fracturing of the mudrock.

Diagnostic accuracy and reliability of muscle strength and endurance measurements in patients with chronic low back pain.

OBJECTIVE: Dynamometric trunk muscle strength and endurance tests are performed widely within the rehabilitation management of chronic low back pain. The aim of this study was to examine the accuracy and long-term reliability of these measurements in patients with chronic low back pain. DESIGN: Cross-sectional study. SUBJECTS: Thirty-two patients with chronic low back pain, 19 healthy controls and 15 patients with chronic headache matched for age, sex and body mass index. METHODS: Both patient groups and healthy controls performed isokinetic and isometric trunk extensor and flexor tests on a Biodex 2000 dynamometer. The Biering-Sørensen test served to examine back muscle endurance. Borg-Category-Ratio-Scales CR-10 rated participants' body experience immediately before and after the testing. Patients with chronic low back pain repeated measurements after 3 weeks. RESULTS: Among dynamometric tests, isokinetic measurements revealed the best area under the curve (AUC = 0.89) for the discrimination between patients with chronic low back pain and healthy controls. Reliability testing revealed highly significant learning effects for isometric trunk flexion and isokinetic measurements. The Biering-Sørensen test demonstrated excellent accuracy (AUC = 0.93) and no learning effects. Borg-category-ratio-scale ratings were not associated with the observed changes. CONCLUSION: In chronic low back pain dynamometric trunk muscle measures are limited to muscle function assessment purposes. Monitoring treatment outcome in these patients with these measures appears to be problematic because of learning effects. Based on our findings, we recommend the Biering-Sørensen test for management of chronic low back pain rehabilitation.

Isolated vertebral fractures give elevated serum protein S-100B levels.

BACKGROUND: Serum protein S-100B determinations have been widely proposed in the past as markers of traumatic brain injury and used as a predictor of injury severity and outcome. The purpose of this prospective observational case series was therefore to determine S-100B serum levels in patients with isolated injuries to the back. METHODS: Between 1 February and 1 May 2008, serum samples for S-100B analysis were obtained within 1 hour of injury from 285 trauma patients. All patients with a head injury, polytrauma, and intoxicated patients were excluded to select isolated injuries to the spine. 19 patients with isolated injury of the back were included. Serum samples for S-100B analysis and CT spine were obtained within 1 hours of injury. RESULTS: CT scans showed vertebral fractures in 12 of the 19 patients (63%). All patients with fractures had elevated S-100B levels. Amongst the remaining 7 patients without a fracture, only one patient with a severe spinal contusion had an S-100B concentration above the reference limit. The mean S-100B value of the group with fractures was more than 4 times higher than in the group without fractures (0.385 vs 0.087 microg/L, p = 0.0097). CONCLUSION: Our data, although limited due to a very small sample size, suggest that S-100B serum levels might be useful for the diagnosis of acute vertebral body and spinal cord injury with a high negative predictive power. According to the literature, the highest levels of serum S-100B are found when large bones are fractured. If a large prospective study confirms our findings, determining the S-100B level may contribute to more selective use of CT and MRI in spinal trauma.

Low-back pain assessment based on the Brief ICF Core Sets: diagnostic relevance of motor performance and psychological tests.

OBJECTIVE: The Brief International Classification of Functioning, Disability and Health (ICF) Core Sets for chronic low-back pain (cLBP) have included the three body functional categories sensation of pain, muscle functions, and emotional functions. As the latter two categories represent umbrella terms, the objective of this research was to identify those clinical tests that most expediently substantiate these two categories. DESIGN: This case-control study included 32 consecutive cLBP patients and 19 nonathletic healthy controls (HC), matched in age, body mass index, and sex. All patients and HCs underwent a comprehensive standardized clinical examination, with objective muscle functions tests that measured trunk muscle strength, endurance, and postural performance. Assessment of the category emotional functions included the Symptom Checklist 90-Revised, the Beck depression inventory, the Fear-Avoidance Beliefs Questionnaire (FABQ-D), and body experience (Borg category ratio scales about exertion, tension, fear of harm, and (re-)/injury). RESULTS: Logistic regression analyses revealed back muscle endurance and somatization to explain 50% of the between-group variances. Furthermore, the variables of Sensory Organization Test (SOT) composite score and FABQ were best associated with disablement in cLBP. CONCLUSIONS: In the Brief ICF Core Set for cLBP, back muscle endurance tests best examined the category muscle functions, whereas somatization best examined that of emotional functions. Furthermore, both the SOT and the FABQ would, in addition to the aforementioned tests, optimize the functional diagnostic relevance of the two ICF categories for cLBP.

Low-grade malignant fibrosarcoma of the dental follicle of an unerupted third molar without clinical evidence of any follicular lesion.

BACKGROUND: Sarcomas are rarely seen in the head and neck region. They make up less than 1% of all malignant head and neck tumours. Not only the location, size and systemic manifestation, but also the histological differentiation plays an essential role in establishing the best treatment. If resectable, surgical removal of the tumour with clear margins is the preferred method. Adjuvant chemo- and/or radiotherapy might be considered in the case of high-grade lesions or narrow surgical margins. PATIENT: This paper reports a 23-year-old female patient who underwent routine surgical removal of unerupted wisdom teeth without clinical evidence of any follicular lesion and was diagnosed with a low-grade malignant fibrosarcoma of the dental follicle of the lower left unerupted third molar. CONCLUSION: This case report raises the question as to whether histological examination of all removed dental follicles should be carried out on a routine basis.

Validation of 3D-laser surface registration for image-guided cranio-maxillofacial surgery.

AIM: Image-data-based navigation plays an important role during surgical treatment in anatomically complex areas. Conventional patient-to-image registration techniques on the basis of skin and bone markers require expensive and time-consuming logistic support. A new markerless, high-resolution laser surface scan technique for patient registration has been tested in experimental and clinical settings. METHODS: In a phantom study, a skull model was registered with laser scanning and marker-based algorithms. The registration procedure was repeated 25 times in each group. The values for the root mean-square error were calculated as a measure of the deviation of the forecast position from the actual position and the target difference. In a clinical setting, 21 consecutive patients who presented with cranio-maxillofacial disorders were scheduled for navigational surgery using laser surface scanning for patient-to-image registration. Here the accuracy was determined by anatomical landmark localization. RESULTS: In the experimental study, a root mean-square error of 1.3+/-0.14 mm, and a mean target deviation of 2.08+/-0.49 mm were found for laser scanning. In contrast, a root mean-square error of 0.38+/-0.01 mm and a mean target deviation of 0.99+/-0.15 mm were found for marker registration. The differences were statistically significant (p<0.005). A strong correlation between the root mean-square error and the target deviation was found for laser (r=0.96) and marker registration (r=0.95). During the 21 clinical procedures, the overall accuracy of laser scan registration determined by the root mean-square error was 1.21+/-0.34 mm, and the mean clinical precision was 1.8+/-0.5 mm. CONCLUSIONS: Three-dimensional laser surface registration offers an interesting approach for selected image-guided procedures in cranio-maxillofacial surgery.