Bartron Medical Imaging, Inc. (BMI) is a Maryland based corporation with its headquarters in Largo, Maryland and its Research and Development Laboratory in New Haven, Connecticut. BMI is a high technology Minority Business Enterprise (MBE) that is dedicated to the development of advanced image analysis and data mining for biomedical applications. BMI has adapted the use of NASA-pioneered technology to medical imaging. The company's licenses and patents enable novel analyses and evaluation of conventional medial imaging at levels never before achieved; pixels or sub-pixels. These methods are presently being applied to a variety of medical images. BMI developed the Bartron Medical Imaging MED-SEG™ system, which is classified as a Picture Archiving and Communications System (PACS). Bartron received its first patent in December 2007 and also obtained patents in India and Japan in 2010.
BMI technology has been developed specifically for medical image processing utilizing NASA Goddard Space Flight Center-licensed software. Other BMI-patented or patent-pending IP has come from licensed and modified software from CalTech/JPL and the Kennedy Space Flight Center. It is based on Recursive Hierarchical Segmentation (RHSEG), a partitioning of an image into related sections or an entire region formed by aggregated feature values. When powered by parallel processing computer clusters, this provides the clinician with rapid, sensitive, specific and precise analysis since each image pixel is treated separately. The result is an accurate graphical representation of the imagery data with fine resolution of detail and minimal distortion. Because the only information being analyzed originated in the actual image being processed, there is less distortion and better resolution, resulting in a more accurate and reliable analysis of the image. This furnishes the clinician with more fine-grain information, leading to a quicker and more analysis.
BMI is presently extending the MED-SEG™ System to include the processing of three-dimensional images
(See Press Room), as well as digitized two-dimensional images. Images originate from radiological, ultrasound, magnetic imaging (MRI) and other sources. These applications all require unique algorithms and extremely powerful computational facilities. In order to use the MED-SEG™ System for two-dimensional images, BMI developed a 64-node SCYLD Beowulf cluster. BMI is presently completing the assembly of a 500-fold cluster that will be needed for the processing of three-dimensional images and the Oracle 11g Cluster to process and mine the data that is produced by these operations. Thus, BMI offers the entire range of hardware and software necessary for any sized image-generating biomedical provider to rapidly and precisely process and analyze contemporary, high quality images and to mine data from past images.