f-AnoGAN: Fast Unsupervised Anomaly Detection with Generative Adversarial Networks
The detection and localization of imaging biomarkers correlating with disease status is important for initial diagnosis, assessment of treatment response and follow-up examinations. Spiculation patterns of lung nodules in lung CT scans (Zwirewich et al., 1991), microcalcification in X-ray mammography images for breast screening (Wang et al., 2014), or macular fluid in OCT scans of the retina (Schmidt-Erfurth et al., 2018) are examples of imaging biomarkers used in clinical routine. Training of highly accurate deep learning methods for the i dentification of imaging biomarkers has shown promising results reaching clinical expert level accuracies, but requires expert annotated data (Kooi et al., 2017; Esteva et al., 2017; Rajpurkar et al., 2017; Grewal et al., 2017).
Source: Medical Image Analysis - Category: Radiology Authors: Thomas Schlegl, Philipp Seeb öck, Sebastian M. Waldstein, Georg Langs, Ursula Schmidt-Erfurth Source Type: research
More News: CT Scan | Learning | Mammography | PET Scan | Radiology | Training | Universities & Medical Training