Abstract
Accurate diagnosis of disease often depends on the exhaustive examination of Whole Slide Images (WSI) at microscopic resolution. Efficient handling of these data-intensive images requires lossy compression techniques. This paper investigates the limitations of the widely-used JPEG algorithm, the current clinical standard, and reveals severe image artifacts impacting diagnostic fidelity.
Type
Publication
Machine Learning in Medical Imaging
Rickmer Braren
Deputy Director Institute for Diagnostic and Interventional Radiology
Jens Kleesiek
Professor of Translational Image-guided Oncology
