Ultrasound Image Dataset for Image Analysis Algorithms Evaluation

Camilo Cortes 1,2,3, Luis Kabongo 1,3, Ivan Macia 1,3, Oscar E. Ruiz 2 and Julian Florez 1

1 eHealth and Biomedical Application, Vicomtech -IK4, Mikeletegi Pasealekua 57,
20009 San Sebastián - Donostia (Spain)
2 Laboratorio de CAD CAM CAE, Universidad EAFIT, Carrera 49 No. 7 Sur-50, 050022 Medellín (Colombia)
3 Biodonostia Health Research Center, San Sebastián - Donostia (Spain)

Publication available here.


The use of ultrasound (US) imaging as an alternative for real time computed assisted interventions is increasing, in despite of its lower imaging quality compared to other existing techniques and subsequently its difficulty to be used with image analysis algorithms. Nevertheless, it is still difficult to find sufficient data to perform studies and evaluation of solutions for navigation, registration and reconstruction at research level. Furthermore, current publicly available datasets present quality limitations inherent to their manually-driven acquisition. To address these limitations, we present a database of tracked sequences of US images from medical phantoms acquired with a methodology that ensures the spatial and force control of the US probe along prescribed trajectories by using a robotic arm and an optical tracking system.