A visual analytics system for breast tumor evaluation.

OBJECTIVE

To develop a system for the interactive exploration and examination of histologically derived data that is associated with breast tumors and may be used to evaluate the histologic grade of the tumor.

STUDY

DESIGN

The system integrates pathologist-generated prognostic data with 2-dimensional (2-D) image analysis data, 2-D digital tissue cross-sections and annotations, 3-dimensional (3-D) tumor reconstructions and volumetric analysis, 3D spatial tumor display and recorded prognostic information from available cases in the Drexel University College of Medicine tumor databank. The system consists of 3 components: (1) a user interface for applying 2-D image processing, segmentation and annotation to a digitized histology slide, (2) a distance field interpolation method for contour-based 3D reconstruction of breast tumors and volumetric model analysis routines and (3) a Web-based database management interface for interactive data browsing and searching and multimodality visualization.

RESULTS

The system has been implemented and deployed with data from 36 breast cancer cases, 7 of which have been reconstructed in 3-D.

CONCLUSION

Interactive visual analytics technology may be used to create an effective breast tumor evaluation system.