Informatics in radiology: Hesse rendering for computer-aided visualization and analysis of anomalies at chest CT and breast MR imaging

• Published in: Radiographics Vol. 32; no. 1; p. 289
• Main Authors: Wiemker, Rafael, Dharaiya, Ekta D, Bülow, Thomas
• Format: Journal Article
• Language: English
• Published: United States 01.01.2012
• Subjects: Algorithms; Breast Diseases - pathology; Humans; Imaging, Three-Dimensional - methods; Pattern Recognition, Automated - methods; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Radiography, Thoracic - methods; Reproducibility of Results; Sensitivity and Specificity; Tomography, X-Ray Computed - methods
• ISSN: 1527-1323
• DOI: 10.1148/rg.321105076

A volume-rendering (VR) technique known as Hesse rendering applies image-enhancement filters to three-dimensional imaging volumes and depicts the filter responses in a color-coded fashion. Unlike direct VR, which makes use of intensities, Hesse rendering operates on the basis of shape properties, such that nodular structures in the resulting renderings have different colors than do tubular structures and thus are easily visualized. The renderings are mouse-click sensitive and can be used to navigate to locations of possible anomalies in the original images. Hesse rendering is meant to complement rather than replace conventional section-by-section viewing or VR. Although it is a pure visualization technique that involves no internal segmentation or explicit object detection, Hesse rendering, like computer-aided detection, may be effective for quickly calling attention to points of interest in large stacks of images and for helping radiologists to avoid oversights.