MicronTracker uses stereoscopic vision in real time to detect and track specially-marked objects. MicronTracker can be used in a variety of clinical guided procedures including image-guided surgery, ablation, and biopsy, performed manually or using robotics. MicronTracker also supports augmented reality, which provides an intuitive approach for handling clinical procedures.
MicronTracker leads a new generation of trackers that use visible light and computer vision to detect fully passive marked targets and track them by processing standard video images.
Easy setup and tear down
Unlike competitive systems that require stocking, mounting and unmounting of single-use components or batteries for each tool being tracked, MicronTracker uses permanent steam sterilizable tool markers, making all tools always immediately ready for navigation.
Low purchase and operating costMicronTracker’s attractive cost is achieved by simple design and reliance on standard hardware components (no custom electronics). All savings are passed on to the users. With MicronTracker there are no additional costs for disposables. DuraMarks markers are sterializable and can be used at least 100 times.
Software that makes it easy to build a complete systemThe versatile MicronTracker software provides rich and flexible APIs, compliant with Windows, and Linux. The demo application included in the product, available in source code, provides an excellent starting point for booting up new application development.
MicronTracker incorporates a set of features designed to meet the needs of both clinical and research clients.
Reliable class-leading accuracy
MicronTracker features class-leading calibration accuracy of 0.2mm RMSE (root-mean-square error). Its advanced drift compensation algorithms keep it accurate in a wide range of ambient conditions. Internal checks provide alerts in the rare instances when conditions may cause degradation in accuracy.
Superior pinpointing reliability
Competing pose trackers use bright infrared spots to mark target locations. In these systems, target centers are pinpointed by computing the intensity of the centroid of the image produced by the spot. A smudge or a partial occlusion can affect the position of the centroid, leading to significant measurement errors. This condition is not detected and the user is not alerted.
MicronTracker computes target locations at the intersection of 4 high-contrast regions, called an Xpoint. Each of the four black and white boundary lines independently serves to pinpoint the location of the target. Portions of the Xpoint region hidden by smudges or occlusions are disregarded and have no effect on accuracy.
Validate and refine accuracy in the field
The MicronTracker camera is designed to solidly preserve the highly accurate optical calibration performed at the factory. As with all high-precision opto-mechanical instruments, its accuracy may degrade in the field as a result of minute changes caused by environmental stresses or rough handling.
Other position trackers on the market require customers to purchase expensive equipment to verify accuracy over time. When accuracy is found to fall short of specifications, the camera must be sent back to the factory for repair or recalibration. MicronTracker’s R-Fine kit (custom-made accuracy bar and software) allows users to verify and immediately restore the accuracy of the device. R-Fine is provided free of charge in every MicronTracker kit.
The R-Fine software contains a model of typical physical changes occurring in the mechanical structure of the camera. During the calibration procedure the model is adjusted to best match the data collected. The adjusted model is then used to refine the calibration of the camera. Because the R-Fine calibration procedure takes only a few minutes, it is possible to validate the accuracy of performance as often as necessary.
Unique visual calibration verification
The spatial relationship between markers and any object location (such as a tool tip) can be visually presented to the user to enable dynamic visual comparison. For example, after calibrating the relationship between a tool marker and the position and orientation of the tooltip, measurement of the tooltip pose can be overlaid on its expected image location, allowing the user to easily detect errors and inaccuracies.
High dynamic range mode
High dynamic range (HDR) mode is a technique that allows solid detection in situations of great illumination range. This feature enables MicronTracker to work reliably under a wide range of intensity levels found in operating rooms. For example the H3-60 model covers a 5-400,000Lux range.
Easy to position and use
The smallest, lightest camera
MicronTracker is by far the smallest and lightest camera in its class. It measures 164 x 43 x 54 mm and weighs only 342 g. It fits unobtrusively into cluttered environments where space is scarce. It does not require large supporting arms or tripods, and can even be mounted directly onto the patient holder/table, eliminating the need for a separate reference marker. It is less likely to be accidentally bumped into during an operation or experiment. MicronTracker is easy to move, store, and ship.
Easiest to position correctly
Initial positioning of the camera in a way that eliminates the need for repeated repositioning can be a major challenge for other pose trackers. MicronTracker’s FOM starts only 20cm in front of the camera. The camera can be placed right in front of the volume to be measured, eliminating the difficulty of estimating imaginary boundaries 1-2 meters away. Even more important, MicronTracker provides visible light video images, showing the user exactly what the camera sees and where the visibility boundaries are. If tracking of an instrument is lost, no guessing is necessary: a quick peek at the images is all it takes.
Adaptable Passive Targets
MicronTracker targets are simple, high-contrast visible patterns that can be printed on throwaway labels and reusable plastic, or painted directly on the instruments. They are lightweight, flat, and can be attached directly to the skin to eliminate cumbersome patient attachments. The DuraMarks targets provided by ClaroNav are sterilizable.
MicronTracker has the unique ability to track in practice an unlimited number of tools simultaneously, under any conditions.
Superior identification reliability allows MicronTracker to distinguish among markers that are only slightly different from each other. MicronTracker’s unlimited marker templates database allows it to distinguish between hundreds of different instruments. Even more important, the database may be updated at run-time, allowing new marker templates to be added simply by presenting them to the camera and assigning a name to them. Highly efficient algorithms and a fast in-memory interface to the application allow MicronTracker to track dozens of markers concurrently at full frame rates.
Marker identification reliability
The Xpoint method of marker identification used by MicronTracker reduces errors in identification and is not sensitive to bright reflection spots that are common in clinical environments.
Bright spots in an image contain no geometric information other than the location of their centers. By contrast, Xpoints have both a location and an orientation. This additional discriminating characteristic greatly reduces erroneous mismatches between targets seen on left and right images. It also reduces marker misidentification, where identification is carried out by matching the characteristics of the observed targets against templates. Misleading bright reflection spots are more common in an operating environment than Xpoints are, so that the use of Xpoints greatly reduces the risk of misidentification.
Smooth pose data
A unique jitter filter provides exceptionally smooth pose data for enhanced navigation experience.
Flexible uninterrupted FOM
FOM size can be increased easily by using larger markers or by the addition of inexpensive cameras. Multi-camera configurations also help eliminate sight interruptions, as tracking continues even if targets are hidden from one or more of the cameras.
Enlarging the FOM with MicronTracker is simple: you can add more cameras. Multiple cameras can be added easily while maintaining complete software compatibility with a single camera configuration. Registering the individual FOMs together is as simple as placing a single marker in the region where they overlap.
Reduced line of sight interruptions
With their small size and close FOM, the positioning of MicronTracker cameras reduces the incidence of interference by people or objects in the line of sight to the markers. Moreover, the small camera size, low cost, and excellent software support make multi-camera configurations both practical and affordable. By overlapping the FOMs of different cameras, tracking continues even when targets are hidden from one of the cameras Multi-facet marker.
Markers may contain an arbitrary number of facets. Designing a marker with more than one facet, in different orientations, increases the detection angle.
Choice of models
Easy to integrate
MicronTracker provides rich and flexible APIs compliant with Windows and Linux, with over 500 well-documented functions available both in native C and in C++, VB.Net, and C#. This places tracking operations under the full control of the application programmer. Low-level data, such as images and the objects identified in them, may be accessed directly, and various attributes of the tracking operation can be adjusted. Most users have found our demo application, available in source code, an excellent starting point for booting up their own applications.
The “native” API is provided in C, but it is object-oriented and can be easily accessed from high-level languages such as C++, Vb.Net, or C#.Net through available wrappers. Demonstration applications in source code format and a developer’s manual are available to your programmers to help them quickly integrate MicronTracker into your product.
Periodic software updates bring new system capabilities to developers.
Many of MicronTracker’s customers are among the most prestigious medical centers around the world. Here is a small sample: