Orientation regression in hand radiographs: a transfer learning approach

Ivo M. Baltruschat, Axel Saalbach, Mattias P. Heinrich, Hannes Nickisch, Sascha Jockel


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°.

Original languageEnglish
Title of host publicationMedical Imaging 2018: Image Processing
EditorsElsa D. Angelini, Bennett A. Landman
Number of pages8
Publication date02.03.2018
Article number105741W
ISBN (Print)978-151061637-0
Publication statusPublished - 02.03.2018
EventSPIE Medical Imaging 2018
- Marriott Marquis Houston, Houston, United States
Duration: 10.02.201815.02.2018


Dive into the research topics of 'Orientation regression in hand radiographs: a transfer learning approach'. Together they form a unique fingerprint.

Cite this