2 March 2018 Orientation regression in hand radiographs: a transfer learning approach
Author Affiliations +
Most radiologists prefer an upright orientation of the anatomy in a digital X-ray image for consistency and quality reasons. In almost half of the clinical cases, the anatomy is not upright orientated, which is why the images must be digitally rotated by radiographers. Earlier work has shown that automated orientation detection results in small error rates, but requires specially designed algorithms for individual anatomies. In this work, we propose a novel approach to overcome time-consuming feature engineering by means of Residual Neural Networks (ResNet), which extract generic low-level and high-level features, and provide promising solutions for medical imaging. Our method uses the learned representations to estimate the orientation via linear regression, and can be further improved by fine-tuning selected ResNet layers. The method was evaluated on 926 hand X-ray images and achieves a state-of-the-art mean absolute error of 2.79°.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ivo M. Baltruschat, Ivo M. Baltruschat, Axel Saalbach, Axel Saalbach, Mattias P. Heinrich, Mattias P. Heinrich, Hannes Nickisch, Hannes Nickisch, Sascha Jockel, Sascha Jockel, } "Orientation regression in hand radiographs: a transfer learning approach", Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105741W (2 March 2018); doi: 10.1117/12.2291620; https://doi.org/10.1117/12.2291620

Back to Top