Real-time Demonstration

Over the past 15 years, the CIA Lab has developed a series of advanced image analysis algorithms for efficient and accurate segmentation of solid tumors, organs and tissues at various sites. The algorithms are integrated into the Lab-developed imaging platform that has been developed for fostering algorithm optimization and imaging biomarker validation.

A real-time demonstration of our lung lesion segmentation

As demonstrated by the real-time movie below, an operator manually initializes the algorithm by specifying an elliptical region-of-interest enclosing the lesion on one slice, and the algorithm will then automatically segment the lesion in 3D. The red contours superimposed on the lesion are generated by the algorithm.

Real Time Demo

Highlights of our lesion and organ segmentation algorithms

easy-to-use
fast
accurate
ready-to-go

An example of speed

A liver case consisting of 76 MR images/slices took our liver organ algorithm 23.7 seconds to complete for volumetric segmentation. There was no need for manual correction.

An example of accuracy

We received ~87% (Dice) mean overlap ratio for our lung lesion segmentation algorithm when applying it to the publicly accessible lung datasets of same-day repeat CT and LIDC.