Interpreting image data is a complex and challenging task

The human mind has a remarkable ability to make sense of images, identify objects and patterns and extract insights from them. It handles ambiguous or partial information by making inferences based on the image as a whole, the relationship between individual objects and the intelligent use of external, contextual information.

From studying distant galaxies to probing minute biological structures, an increasing number of industries rely on images to understand their environment. The number of images and image capturing devices is rapidly proliferating and presents an urgent problem: how to release the wealth of information and insights contained within images.

Despite increases in computational power, fundamental advances in automating image analysis have been limited. The problem is that for any image there may be many plausible interpretations and there is no way to determine the correct interpretation with absolute certainty. The difficulties take the form of varied shading and colors, partially-hidden objects and determining three-dimensional depth from two-dimensional projections.

Definiens made a radical departure from conventional image analysis approaches

Our technology examines pixels not in isolation, but in context. It builds up a picture iteratively, recognizing groups of pixels as objects. Just like the human mind, it uses the color, shape, texture and size of objects as well as their context and relationships to draw the same conclusions and inferences that an experienced analyst would draw.

As the world's No.1 Enterprise Image Intelligence® company, Definiens' technology is used to analyze and interpret images on every scale - from non-invasive body scans to tissue samples and cell-based assays: 

		More than 70 per cent of all data generated in the Life Sciences is in image form and the volume is increasing. High-throughput machines in the laboratory can produce thousands of images a day. There is a need for automated image analysis solutions that provide fast and consistent results across the enterprise and the multi-facetted image analysis tasks.
		Image analysis is one of the principal 'bottlenecks' in effective clinical trials and diagnosis since it relies on a limited pool of experts. Yet the number of images and imaging technologies is proliferating. As a result, radiologists and other medical experts are unable to release the wealth of information and insights contained within the images they capture.