highlights
• mechatronics
• optics
• image processing and analysis
• black-box modelling, machine learning and AI
• clinical studies and medical device regulations
• production
how does the HandScan work?
The HandScan uses a red and a near-infrared laser plus a system of rotating mirrors to create a scanning light spot underneath the hands. Cameras register light transmission through the hands. The contour of each hand and the approximate location of joints is automatically determined through image processing, and the laser spot is turned off outside the hand contour to prevent saturating the camera. During a measurement, a pressure cuff around each lower arm is temporarily inflated to obstruct venous blood flow back to the heart, and the resulting gradual changes in light transmission due to blood pooling give additional information about hemodynamic effects related to joint inflammation. Multispectral stacks of images captured during a measurement are processed and extracted parameters fed into inflammation models that output an inflammation score for each joint in the hand.
A data reduction of many orders of magnitude is first obtained by fitting the measured response curve of each pixel in a stack of images to a nonlinear mathematical model for hemodynamic response. This is followed by combining the extracted parameters of each pixel within a joint ROI (region of interest) and an (assumedly non-inflamed) reference ROI near the joint. This results in 10-20 parameters per ROI, and an automatically selected subset of less than 5 of these parameters forms the input for the inflammation scoring models. Reference data for training the inflammation scoring models is obtained from several clinical studies in which an expert ultrasonographer complements the raw image stacks of HandScan scans with target scores for use in supervised learning. Models are finally selected for clinical use based on their AUC value, a measure for the reliability of the inflammation scores. Inflammation scoring models can range from simple linear regression to multilayer perceptron networks in trade-offs between simplicity (minimizing overfitting risk) and accuracy.
what were our challenges?
One of our main challenges in our role as development partner for Hemics was to ensure stable and accurate alignment of the scanning laser illumination pattern underneath both hands, using a combination of rotating mirrors and computer vision based switching patterns with the two lasers.
our role developing this system.
We were a development partner from the start. We were responsible for the concept design as well as the detailed design and documentation. In addition, we made the hardware prototype and accompanying software and are now responsible for production of the HandScan.
“glad with enthused patient reactions.”
A recent patient brimmed with enthusiasm about the HandScan. Patients value it to objectively see what they feel in their joints and see this imaging device as a considerable added value to disease monitoring. For us it is great to see how happy patients are with it.
more cases & tech insights.
Autonomous water-pipe inspection robot
Guaranteeing drinking water quality and preventing water spillage requires good management of the huge pipeline networks. Commissioned by the drinking water companies, recently united in the company SubMerge, we have developed a prototype inspection robot.
Read more
The other side of the coin
After shipment of forty million coins from the Netherlands to their destination country, it appeared that an estimated one percent of the coins showed missing chips and discoloration. An on-site sorting machine was urgently required and Demcon built it within four weeks.
Read more
Piezoelectric damping of a 6-DoF vibration isolation frame
The performance of precision mechanisms can be limited by disturbing vibrations that are amplified at parasitic eigenfrequencies. Piezoelectric patches that are integrated into flexures have been shown to be a promising approach for actively suppressing parasitic modes.
Read more
Vibration isolation for nanometer measurement device
In this article, we present the model-based design steps for a high-performance vibration isolation system to support a metrology frame. During the design phase, several improvements were shown to increase the vibration isolation performance.
Read more