Interactive Segmentation Relabeling for Classification of Whole-Slide Histopathology Imagery

Collecting ground-truth or gold standard annotations from expert pathologists for developing histopathology analytic algorithms and computer-aided diagnosis for cancer grading is an expensive and time consuming process. Efficient visualization and annotation tools are needed to enable groundtruthing large whole-slide imagery. KOLAM is our scalable, cross-platform framework for interactive visualization of 2D, 2D+t and 3D imagery of high spatial, temporal and spectral resolution. In the current work KOLAM has been extended to support rapid interactive labeling and correction of automatic image classifier-based region labels of the tissue microenvironment by pathologists. Besides annotating regionsof-interest (ROIs), KOLAM enables extraction of the corresponding large polygonal image sub-regions for input into automatic segmentation algorithms, single-click region label reassignment and maintaining hierarchical image sub-regions. Experience indicates that clinicians prefer simple-to-u...

• Type: Journal
• Year: 2015
• Where: CBMS
• Authors: Anoop Haridas, Filiz Bunyak, Kannappan Palaniappan
• Keywords: CBMS 2015, Medical Imaging