One-class Gaussian process regressor for quality assessment of transperineal ultrasound images

Saskia M. Camps, Tim Houben, Davide Fontanarosa, Christopher Edwards, Maria Antico, Matteo Dunnhofer, Esther G.H.J. Martens, Jose A. Baeza, Ben G.L. Vanneste, Evert J. van Limbergen, Peter H.N. de With, Frank Verhaegen, Gustavo Carneiro

Abstract: The use of ultrasound guidance in prostate cancer radiotherapy workflows is not widespread. This can be partially attributed to the need for image interpretation by a trained operator during ultrasound image acquisition. In this work, a one-class regressor, based on DenseNet and Gaussian processes, was implemented to assess automatically the quality of transperineal ultrasound images of the male pelvic region. The implemented deep learning approach achieved a scoring accuracy of 94%, a specificity of 95% and a sensitivity of 93% with respect to the majority vote of three experts, which was comparable with the results of these experts. This is the first step towards a fully automatic workflow, which could potentially remove the need for image interpretation and thereby make the use of ultrasound imaging, which allows real-time volumetric organ tracking in the RT environment, more appealing for hospitals.

Keywords: Ultrasound, prostate, radiotherapy, USgRT, DenseNet, One class classifier, Gaussian Process

Author Affiliation: Eindhoven University of Technology, Queensland University of Technology, University of Udine, MAASTRO, the University of Adelaide