On 29 August, 2016, Niclas Nilsson, MPBME, will be presenting his master thesis with the title “Electromyography analysis by classification complexity estimation”
When? Monday, August 29 at 13:00 pm.
Where? Landahlsrummet (room 7430), Hörsalsvägen 11, 7th floor
Examiner: Tomas McKelvey
Intuitive control based on myoelectric pattern recognition (MPR) can be used in clinical applications such as prosthetic limbs and Phantom Limb Pain treatment. Electromyography (EMG) patterns representing limb movements are learned by a pattern recognition algorithms to enable classification of future EMG observations. These EMG patterns are commonly constituted by descriptive features extracted from raw EMG. The complexity of the classification task is highly influenced by both the selection of such features and the differentiation between movements in the raw EMG. A reliable estimation of classification complexity would facilitate selection of features and elimination of detrimental EMG patterns. Two such algorithms, Separability Index and Nearest Neighbor Separability, were found to be highly correlated with classification accuracy and enable efficient feature selection for three common MPR algorithms (Linear Discriminant Analysis, Multi-Layer Perception and Support Vector Machine).
The algorithms were implemented in the data analysis and feature selection modules of BioPatRec, an open source tool developed at Chalmers University of Technology for development and benchmarking of algorithms in MPR. The implementation included dedicated graphical user interfaces to ease visualization. This thesis deepens the understanding of the complexity of MPR and provides tools for prediction of classification performance and analysis of MPR applications.
On 17 August 2016, Henrik Fransson and Tobias Petrén, MPBME, will be presenting their master thesis with the title “Development of a motion tracking algorithm using a non-depth sensing camera to assist in rehabilitation of stroke and COPD patients”.
When? Wednesday, August 17 at 14.00
Where? Blå Rummet (room 6414), Hörsalsvägen 11, 6th floor
Examiner: Fredrik Kahl
Stroke and chronic obstructive pulmonary disease (COPD) are two common diseases and the patients suffering from them are in need of rehabilitation to improve their life quality. In order to facilitate the rehabilitation process, motion controlled computer games can be used, as studies suggest. This thesis involves the development of a tracking algorithm, used in such games, able to track the hands and head of a person in real time with a non-depth sensing camera, such as those found in laptops and tablets.
The resulting algorithm consists of four main parts: background subtraction, skin extraction using the RGB and HSV color spaces, classification of hands and head with a convolutional neural network (CNN) and tracking of the classified body parts with a Kanade-Lucas-Tomasi (KLT) tracker. Running the algorithm on video recordings obtained from a common motion pattern shows that the algorithm is able to correctly track the three body parts in approximately 88.9% of the 800 frames recorded at 30 FPS and the computation time is roughly 0.48 seconds per frame. The algorithm is able to recover from a situation in which not all body parts are tracked correctly and it can handle occlusions. Furthermore, the algorithm needs some preconditions, such as good lightning and no skin-colored background or clothes, to fully function.
It is concluded that the current implementation is too slow to function in real time. However, it is believed that the method used in the algorithm can be a viable approach for motion controlled games if implemented in a faster language than MATLAB and if further improvements are done to discard the currently required preconditions.Share this:
On 6 September you are welcome to attend a breakfast seminar at the Biotech Center. Business Sweden (the Swedish Trade council) in China has recently finished a study called – ”The Recipe for success – Lessons learned from Swedish SMEs in China” – targeting Swedish SME companies with an interest for China. The study is based on market analysis, interviews with Swedish SME companies that have found success in China and interviews with Chinese companies from selected industries. Life Science is one highlighted example of a high potential industry in China. Examples of interviewed companies were Mentice, Cellavision, Contextvision, Jiangsu Chancha and Zizhu Pharmaceuticals. The result is a number of established key success factors and practical tips for how enter, grow and handle challenges common to Swedish SMEs in China.
When? 6 September 2016, 8.00–9.30 am.
Where: Biotech Center, Arvid Wallgrens Backe 20, 413 46 Gothenburg
8.00-8.30: Registration and breakfast
8.30-9.30: Presentation of the study: The Recipe for success – Lessons learned from Swedish SMEs in China
Register here before 1 September>>
WHAT IS NEEDED TO MOVE THE ALZHEIMER FIELD FORWARD?
One of the major medical challenges is to prevent or delay the development of Alzheimer’s disease (AD) and related disorders, but still efficient treatment methods are lacking. Insufficient knowledge of subcortical small vessel disease (SSVD) in AD may explain the lack of success of AD trials. Underestimation of the impact of SSVD on cognition may explain why only few trials have been performed in SSVD. The Sahlgrenska university hospital memory clinic in Mölndal, hosts the largest ongoing longitudinal single-center study in patients seeking help for memory-related complaints. To date, 808 patients along the continuum subjective cognitive impairment to dementia and 136 healthy controls have been enrolled. We aim to clarify not only the characteristics of AD but also SSVD (1), using a multi-modal approach (MRI, CSF, cognitive examination etc.). Preliminary results point to different neurochemical and cognitive characteristics of SSVD and AD also early in the course of the disease (2). Combining markers from various modalities provides a powerful tool to more precisely identify appropriate patients for clinical trials of more homogeneous populations. Thereby, the results may promote therapeutic progress not only in SSVD but also in AD.
Very welcome to this lunch seminar with professor Anders Wallin from the Memory Clinic at Sahlgrenska University Hospital, Mölndal!
Where? Förmaket, Vita stråket 12, Sahlgrenska University Hospital
When? 7 Sep, 2016 at 11:30-12:30 (13:00 incl. lunch)
After the seminar, we offer a light lunch for registered participants. Click here to register before 13:00 pm. on 2 Sep. 2016>>
1. Wallin A, Nordlund A, Jonsson M, Lind K, Edman Å, Göthlin M, Stålhammar J, Eckerström M, Kern S, Börjesson-Hanson A, Carlsson M, Olsson E, Zetterberg H, Blennow K, Svensson J, Öhrfelt A, Bjerke M, Rolstad S, Eckerström C. The Gothenburg MCI study: Design and distribution of Alzheimer’s disease and subcortical vascular disease diagnoses from baseline to 6-year follow-up. J Cereb Blood Flow Metab. 2016 Jan;36(1):114-31.
2. Wallin A, Nordlund A, Jonsson M, Blennow K, Zetterberg H, Öhrfelt A, Stålhammar J, Eckerström M, Carlsson M, Olsson E, Göthlin M, Svensson J, Rolstad S, Eckerström C, Bjerke M. Alzheimer’s disease–subcortical vascular disease spectrum in a hospital-based setting: Overview of results from the Gothenburg MCI and dementia studies. J Cereb Blood Flow Metab. 2016 Jan;36(1):95-113.Share this:
On Friday 26 August, 2016 Eva Lendaro, MPBME, will present her master thesis with the title “Prediction of motor volition in the lower limbs: Towards a treatment for phantom limb pain”.
When? Friday, August 26th at 14.00
Where? Landahlsrummet (room 7430), Hörsalsvägen 11, 7th floor, Chalmers
Examiner: Sabine Reinfeldt
Supervisor: Max Ortiz Catalan
Introduction: Immediately after an amputation, patients commonly experience the vivid sensation that the amputated limb is still present. However, quite often the awareness of a phantom limb is also accompanied by persistent pain. The mechanisms underlying this condition, known as phantom limb pain (PLP), are not completely understood and many different treatment strategies have been proposed with limited results. PLP has been found repeatedly correlated to the changes taking place in the sensorimotor cortex after the loss of the limb, and a newly introduced rehabilitation treatment, which attempts to reverse these changes by training the patient to move the phantom limb, has shown promising results. The system promotes motor execution via Augmented Reality (AR), Virtual Reality (VR) and gaming, which are controlled by phantom motions decoded using myoelectric pattern recognition (MPR). The technology has been tested on upper limb amputees suffering from chronic PLP with good outcomes. However, since lower limb amputations are more frequent, it is necessary to also demonstrate the technology in the lower limbs. The goal of this master’s thesis work was to translate the aforementioned treatment to the lower limb in order to test its effectiveness on subjects with trans-femoral amputation.
Methods: The work started by investigating the feasibility of MPR in the lower limb for both healthy and amputee subjects. In order to overcome the difficulties of recording myoelectric signals from the lower limb, different methodologies for placing the electrodes over thigh muscles were compared in terms of their performance in classifying non-weight bearing movements. The results of the study were applied to the MPR/VR treatment and used to treat one patient with trans-femoral amputation suffering from PLP. The patient, amputated 35 years earlier and suffering from constant and intense PLP, was treated at the “Centre for the Advanced Reconstruction of Extremities (C.A.R.E.)” at Sahlgrenska University Hospital, approximately twice a week for a total of 25 sessions.
Results: The preferred electrode configuration was identified among the ones compared and then adopted for the MPR/VR therapy. Furthermore, the new recording technique makes also the electrode placement easier, which is essential in the perspective of a technology use by clinicians and patients. The subject, who could not find relief with any previous therapy, experienced a significant decrease in pain at the end of the treatment.
Conclusion: This work identifies a preferred methodology for acquiring EMG signals to be used to treat PLP and demonstrate the effectiveness of the MPR/VR therapy on one PLP patient. The positive results, despite being limited to a single patient, justify further investigation in a wider study.Share this:
On Tuesday, 23 August 2016, Bea Bengtsdotter, MPBME, will present her master thesis with the title “eNursing, the usage of ICT-solutions to improve elderly care – A solution to facilitate nurses daily work situation”.
Examiner: Bengt Arne Sjöqvist
When? Tuesday, August 23rd at 14.15
Where? Landahlsrummet (room 7430), Hörsalsvägen 11, 7th floor, Chalmers
With an aging population, the cost of high-quality elderly care increases rapidly in Sweden. The continuously expanding field of modern technology can provide solutions that meet the growing needs. An eNursing concept, connecting devices, such as phones, computers and tablets, with different ICT-systems, is one example involving several technologies. A field study within elderly care mapped the work processes, and resulted in two eNursing prototypes. A low-fidelity prototype produced with pen and paper, including an information screen-, tablet- and phone interfaces, and a Xamarin programmed high-fidelity prototype of a phone application. eNursing solutions must be adapted in each work category within the healthcare sector and designed to facilitate the work situation for the targeted healthcare workers. eNursing should connect different ICT-solutions and enable interoperability and communication in between. The use of eNursing technology may decrease the future cost within the healthcare sector.