A Multi-Constraint Scheme with Authorized Mechanism for the Patient Safety.

Many research works have attempted to introduce passive RFID technology into medical systems to reduce medical errors. However, most of these proposed works focused on identifying patients and objects. If an RFID based medical system is only good for identifying patients and medical objects but not capable of halting any medical process immediately, then it is not possible to prevent medical errors from happening. Our research focuses on a mechanism to detect and to avoid medical harm before it occurs to patients. In this paper, we propose to incorporate multiple-constraints into the authorization scheme and used this scheme as a basis for implementing a medical management system avoiding medical errors to assist medical staff. Specifically, our scheme ensures that a medical operation is if and only if enabled when the constraints are being satisfied that an "identified patient" is being treated by a "certified medical staff member" within an "authorized area". In practical environments, our authorization scheme can be applied to various healthcare applications, and we develop a prototype system and test it in three applications: X-ray control, specimen collection, and blood transfusion management. The experimental results show that the system can be used to enable X-ray when the X-ray is in authorized location and operated by authorized operator. For the specimen collection and blood transfusion, the logs showing which medical staff has done specimen or blood transfusion on which patient at authorized location are correctly recorded into Hospital Information System (HIS). The locating process can be performed within 10 to 20 seconds, and the locating error is less than 2 meters.

Identifying regions of interest in medical images using self-organizing maps.

Advances in data acquisition, processing and visualization techniques have had a tremendous impact on medical imaging in recent years. However, the interpretation of medical images is still almost always performed by radiologists. Developments in artificial intelligence and image processing have shown the increasingly great potential of computer-aided diagnosis (CAD). Nevertheless, it has remained challenging to develop a general approach to process various commonly used types of medical images (e.g., X-ray, MRI, and ultrasound images). To facilitate diagnosis, we recommend the use of image segmentation to discover regions of interest (ROI) using self-organizing maps (SOM). We devise a two-stage SOM approach that can be used to precisely identify the dominant colors of a medical image and then segment it into several small regions. In addition, by appropriately conducting the recursive merging steps to merge smaller regions into larger ones, radiologists can usually identify one or more ROIs within a medical image.