Scale Stain: Multi-Resolution Feature Enhancement in Pathology Visualization
This addresses the challenge of efficient and accurate pathology review for clinicians, though it is incremental as it builds on existing visualization methods.
The paper tackled the problem of visualizing digital whole-slide pathology images by introducing a novel scale-space filtering approach based on color preference, which revealed diagnostically important patterns not visible otherwise. The result was a 15% increase in task efficiency with maintained accuracy, as demonstrated in a study with eight pathologists.
Digital whole-slide images of pathological tissue samples have recently become feasible for use within routine diagnostic practice. These gigapixel sized images enable pathologists to perform reviews using computer workstations instead of microscopes. Existing workstations visualize scanned images by providing a zoomable image space that reproduces the capabilities of the microscope. This paper presents a novel visualization approach that enables filtering of the scale-space according to color preference. The visualization method reveals diagnostically important patterns that are otherwise not visible. The paper demonstrates how this approach has been implemented into a fully functional prototype that lets the user navigate the visualization parameter space in real time. The prototype was evaluated for two common clinical tasks with eight pathologists in a within-subjects study. The data reveal that task efficiency increased by 15% using the prototype, with maintained accuracy. By analyzing behavioral strategies, it was possible to conclude that efficiency gain was caused by a reduction of the panning needed to perform systematic search of the images. The prototype system was well received by the pathologists who did not detect any risks that would hinder use in clinical routine.