Kari Antila

Estimating Intensity of Physical Activity: A Comparison of Wearable Accelerometer and Gyro Sensors and 3 Sensor Locations

Automatic estimation of physical activity using wearable sensors can be used for promotion of a healthier lifestyle. In this study, accelerometers and gyroscopes attached to ankle, wrist and hip were used to estimate intensity of physical activity. The estimates are compared to metabolic equivalent (MET) obtained from a portable cardiopulmonary exercise testing system. Data from common everyday tasks and exercise were collected with 11 subjects. The tasks include, e.g., ironing, vacuuming, walking, running and cycling on exercise bicycle (ergometer). The strongest linear correlation with metabolic equivalent was obtained with the tri-axial accelerometer attached to the ankle (r=0.86).

Methods of Artificial Enlargement of the Training Set for Statistical Shape Models

Due to the small size of training sets, statistical shape models often over-constrain the deformation in medical image segmentation. Hence, artificial enlargement of the training set has been proposed as a solution for the problem to increase the flexibility of the models. In this paper, different methods were evaluated to artificially enlarge a training set. Furthermore, the objectives were to study the effects of the size of the training set, to estimate the optimal number of deformation modes, to study the effects of different error sources, and to compare different deformation methods. The study was performed for a cardiac shape model consisting of ventricles, atria, and epicardium, and built from magnetic resonance (MR) volume images of 25 subjects. Both shape modeling and image segmentation accuracies were studied. The objectives were reached by utilizing different training sets and datasets, and two deformation methods. The evaluation proved that artificial enlargement of the training set improves both the modeling and segmentation accuracy. All but one enlargement techniques gave statistically significantly (p < 0.05) better segmentation results than the standard method without enlargement. The two best enlargement techniques were the nonrigid movement technique and the technique that combines principal component analysis (PCA) and finite element model (FEM). The optimal number of deformation modes was found to be near 100 modes in our application. The active shape model segmentation gave better segmentation accuracy than the one based on the simulated annealing optimization of the model weights.

Compliance and technical feasibility of long-term health monitoring with wearable and ambient technologies.

We developed a system consisting of both wearable and ambient technologies designed to monitor personal wellbeing for several months during daily life. The variables monitored included bodyweight, blood pressure, heart-rate variability and air temperature. Two different user groups were studied: there were 17 working-age subjects participating in a vocational rehabilitation programme and 19 elderly people living in an assisted living facility. The working-age subjects collected data for a total of 1406 days; the average participation period was 83 days (range 43–99). The elderly subjects collected data for a total of 1593 days; the average participation period was 84 days (range 19–107). Usage, technical feasibility and usability of the system were also studied. Some technical and practical problems appeared which we had not expected such as thunder storm damage to equipment in homes and scheduling differences between staff and the subjects. The users gave positive feedback in almost all their responses in a questionnaire. The study suggests that the data-collection rate is likely be 70–90% for typical health monitoring data.

Artificial enlargement of a training set for statistical shape models: application to cardiac images

Different methods were evaluated to enlarge artificially a training set which is used to build a statistical shape model. In this work, the shape model was built from MR data of 25 subjects and it consisted of ventricles, atria and epicardium. The method adding smooth non-rigid deformations to original training set examples produced the best results. The results indicated also that artificial deformation modes model better an unseen object than an equal number of standard PCA modes generated from original data.

The PredictAD project: development of novel biomarkers and analysis software for early diagnosis of the Alzheimer's disease.

Alzheimers disease (AD) is the most common cause of dementia affecting 36 million people worldwide. As the demographic transition in the developed countries progresses towards older population, the worsening ratio of workers per retirees and the growing number of patients with age-related illnesses such as AD will challenge the current healthcare systems and national economies. For these reasons AD has been identified as a health priority, and various methods for diagnosis and many candidates for therapies are under intense research. Even though there is currently no cure for AD, its effects can be managed. Today the significance of early and precise diagnosis of AD is emphasized in order to minimize its irreversible effects on the nervous system. When new drugs and therapies enter the market it is also vital to effectively identify the right candidates to benefit from these. The main objective of the PredictAD project was to find and integrate efficient biomarkers from heterogeneous patient data to make early diagnosis and to monitor the progress of AD in a more efficient, reliable and objective manner. The project focused on discovering biomarkers from biomolecular data, electrophysiological measurements of the brain and structural, functional and molecular brain images. We also designed and built a statistical model and a framework for exploiting these biomarkers with other available patient history and background data. We were able to discover several potential novel biomarker candidates and implement the framework in software. The results are currently used in several research projects, licensed to commercial use and being tested for clinical use in several trials.

Long-Term Subjective and Objective Sleep Analysis of Total Sleep Time and Sleep Quality in Real Life Settings

Sleep quality is one of the key elements of the human health status. By observing sleep patterns we can gain information about personal wellbeing. Consumer electronic sleep analysis solutions are now available for use in long-term conditions. In this study we compare different measures for total sleep time and sleep quality. We analyzed visually long- term sleep data collected with actigraphy, sleep logs and ambient sensors to gain more reliable results and compared these results to each single methods output. Correlations of visually analyzed total sleep time between actigraphy total sleep time (correlation coefficient (r)=0.662, p<0.01) and sleep log total sleep time (r=0.787, p<0.01) were high. Also comparison between subjective and objective sleep quality was analyzed and small, but significant correlation was found (r=0.270, p<0.01).

Automatic segmentation for detecting uterine fibroid regions treated with MR-guided high intensity focused ultrasound (MR-HIFU)

PURPOSE Up to 25% of women suffer from uterine fibroids (UF) that cause infertility, pain, and discomfort. MR-guided high intensity focused ultrasound (MR-HIFU) is an emerging technique for noninvasive, computer-guided thermal ablation of UFs. The volume of induced necrosis is a predictor of the success of the treatment. However, accurate volume assessment by hand can be time consuming, and quick tools produce biased results. Therefore, fast and reliable tools are required in order to estimate the technical treatment outcome during the therapy event so as to predict symptom relief. METHODS A novel technique has been developed for the segmentation and volume assessment of the treated region. Conventional algorithms typically require user interaction ora priori knowledge of the target. The developed algorithm exploits the treatment plan, the coordinates of the intended ablation, for fully automatic segmentation with no user input. RESULTS A good similarity to an expert-segmented manual reference was achieved (Dice similarity coefficient = 0.880 ± 0.074). The average automatic segmentation time was 1.6 ± 0.7 min per patient against an order of tens of minutes when done manually. CONCLUSIONS The results suggest that the segmentation algorithm developed, requiring no user-input, provides a feasible and practical approach for the automatic evaluation of the boundary and volume of the HIFU-treated region.

Automatic extraction of mandibular bone geometry for anatomy-based synthetization of radiographs

We present an automatic method for segmenting Cone-Beam Computerized Tomography (CBCT) volumes and synthetizing orthopantomographic, anatomically aligned views of the mandibular bone. The model-based segmentation method was developed having the characteristics of dental CBCT, severe metal artefacts, relatively high noise and high variability of the mandubular bone shape, in mind. First, we applied the segmentation method to delineate the bone. Second, we aligned a model resembling the geometry of orthopantomographic imaging according to the segmented surface. Third, we estimated the tooth orientations based on the local shape of the segmented surface. These results were used in determining the geometry of the synthetized radiograph. Segmentation was done with excellent results: with 14 samples we reached 0.57 ± 0.16 mm mean distance from hand drawn reference. The estimation of tooth orientations was accurate with error of 0.65 ± 8.0 degrees. An example of these results used in synthetizing panoramic radiographs is presented.

Cohort Description for MADDEC – Mass Data in Detection and Prevention of Serious Adverse Events in Cardiovascular Disease

The risk for mortality and prevalence of comorbidities of patients treated for cardiovascular diseases are high. Several risk estimation algorithms based on traditionally obtainable clinical information have failed in recognition of patients at risk even when medical interventions would be available. Usually the poor performance of risk prediction algorithms is attributable to heterogeneity in risk factors related hazards between different populations, national health care systems and even hospitals.