Tom Williamson1, Wa Cheung2, Stuart K Roberts3, Sunita Chauhan4. 1. Department of Mechanical and Aerospace Engineering, Monash University, Lab 298, New Horizon Building, Wellington Rd, Clayton, Melbourne, VIC, 3800, Australia. tom.williamson@monash.edu. 2. Department of Radiology, The Alfred, Commercial Road, Melbourne, Australia. 3. Department of Gastroenterology, The Alfred, Commercial Road, Melbourne, Australia. 4. Department of Mechanical and Aerospace Engineering, Monash University, Lab 298, New Horizon Building, Wellington Rd, Clayton, Melbourne, VIC, 3800, Australia.
Abstract
PURPOSE: With the ongoing shift toward reduced invasiveness in many surgical procedures, methods for tracking moving targets within the body become vital. Non-invasive treatment methods such as stereotactic radiation therapy and high intensity focused ultrasound, in particular, rely on the accurate localization of targets throughout treatment to ensure optimal treatment provision. This work aims at developing a robust, accurate and fast method for target tracking based on ultrasound images. METHODS: A method for tracking of targets in real-time ultrasound image data was developed, based on the combination of template matching, dense optical flow and image intensity information. A weighting map is generated from each of these approaches which are then normalized, weighted and combined, with the weighted mean position then calculated to predict the current position. The approach was evaluated on the Challenge for Liver Ultrasound Tracking 2015 dataset, consisting of a total of 24 training and 39 test datasets with a total of 53 and 85 annotated targets throughout the liver, respectively. RESULTS: The proposed method was implemented in MATLAB and achieved an accuracy of [Formula: see text] (95%: 1.91) mm and [Formula: see text] (95%: 1.85) mm on the training and test data, respectively. Tracking frequencies of between 8 and 36 fps (mean of 22 fps) were observed, largely dependent on the size of the region of interest. The achieved results represent an improvement in mean accuracy of approximately 0.3 mm over the reported methods in existing literature. CONCLUSIONS: This work describes an accurate and robust method for the tracking of points of interest within 2D ultrasound data, based on a combination of multi-template matching, dense optical flow and relative image intensity information.
PURPOSE: With the ongoing shift toward reduced invasiveness in many surgical procedures, methods for tracking moving targets within the body become vital. Non-invasive treatment methods such as stereotactic radiation therapy and high intensity focused ultrasound, in particular, rely on the accurate localization of targets throughout treatment to ensure optimal treatment provision. This work aims at developing a robust, accurate and fast method for target tracking based on ultrasound images. METHODS: A method for tracking of targets in real-time ultrasound image data was developed, based on the combination of template matching, dense optical flow and image intensity information. A weighting map is generated from each of these approaches which are then normalized, weighted and combined, with the weighted mean position then calculated to predict the current position. The approach was evaluated on the Challenge for Liver Ultrasound Tracking 2015 dataset, consisting of a total of 24 training and 39 test datasets with a total of 53 and 85 annotated targets throughout the liver, respectively. RESULTS: The proposed method was implemented in MATLAB and achieved an accuracy of [Formula: see text] (95%: 1.91) mm and [Formula: see text] (95%: 1.85) mm on the training and test data, respectively. Tracking frequencies of between 8 and 36 fps (mean of 22 fps) were observed, largely dependent on the size of the region of interest. The achieved results represent an improvement in mean accuracy of approximately 0.3 mm over the reported methods in existing literature. CONCLUSIONS: This work describes an accurate and robust method for the tracking of points of interest within 2D ultrasound data, based on a combination of multi-template matching, dense optical flow and relative image intensity information.
Authors: Spyretta Golemati; Antonio Sassano; M John Lever; Anil A Bharath; Surinder Dhanjil; Andrew N Nicolaides Journal: Ultrasound Med Biol Date: 2003-03 Impact factor: 2.998
Authors: Robert Timmerman; Rebecca Paulus; James Galvin; Jeffrey Michalski; William Straube; Jeffrey Bradley; Achilles Fakiris; Andrea Bezjak; Gregory Videtic; David Johnstone; Jack Fowler; Elizabeth Gore; Hak Choy Journal: JAMA Date: 2010-03-17 Impact factor: 56.272
Authors: David P Gierga; Johanna Brewer; Gregory C Sharp; Margrit Betke; Christopher G Willett; George T Y Chen Journal: Int J Radiat Oncol Biol Phys Date: 2005-04-01 Impact factor: 7.038
Authors: Tim Idzenga; Evghenii Gaburov; Willem Vermin; Jan Menssen; Chris de Korte Journal: IEEE Trans Ultrason Ferroelectr Freq Control Date: 2014-01 Impact factor: 2.725
Authors: R O Illing; J E Kennedy; F Wu; G R ter Haar; A S Protheroe; P J Friend; F V Gleeson; D W Cranston; R R Phillips; M R Middleton Journal: Br J Cancer Date: 2005-10-17 Impact factor: 7.640
Authors: Juan A Sánchez-Margallo; Lisette Tas; Adriaan Moelker; John J van den Dobbelsteen; Francisco M Sánchez-Margallo; Thomas Langø; Theo van Walsum; Nick J van de Berg Journal: Med Phys Date: 2021-10-31 Impact factor: 4.506