Study level

  • PhD
  • Master of Philosophy


Faculty of Health

School of Clinical Sciences

Topic status

In progress.


Associate Professor Davide Fontanarosa
Associate Professor (Medical Radiation Sciences)
Division / Faculty
Faculty of Health
Associate Professor Ajay Pandey
Associate Professor
Division / Faculty
Faculty of Engineering

External supervisors

  • Gustavo Carneiro, University of Adelaide
  • Jason Dowling, CSIRO


Our research in the space of advanced quantitative medical imaging is investigating how to use ultrasound as a real time volumetric mapping tool of human tissues, to guide in a reliable and accurate way complex medical procedures1. We have developed several novel methods which make use of the most cutting-edge artificial intelligence technology2. For example, to show where the treatment target and the organs at risk are at all times during treatments in radiation therapy3, 4; or to inform robots during autonomous minimally invasive surgery so they can perform safe and effective procedures5–8. We are also interested in novel modalities such as elastography, which allows clinicians to “palpate” non-invasively organs that are not physically accessible and, from their elastic properties, diagnose possible diseases9. Recently, we have focused our efforts to help in the fight against COVID-19, developing special ultrasound-based tools to diagnose automatically the disease in resource poor areas.

Several projects are available in this research space combining advanced medical imaging modalities, artificial intelligence and robotics. A large and established team is currently already working on these topics and is available to support new researchers.


1 M. Antico, F. Sasazawa, et al., Ultrasound guidance in minimally invasive robotic procedures, Med. Image Anal. 54, 149–167 (2019).

2 M. Dunnhofer, M. Antico,et al., Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images, Med. Image Anal. (2020).

3 A.S.M. Camps, T. Houben, et al, Automatic quality assessment of transperineal ultrasound images of the male pelvic region using deep learning, Ultrasound Med. Biol. (n.d.).

4 S.M. Camps, F. Verhaegen, et al., Automated patient-specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy, Med. Phys. (2018).

5 L. Wu, A. Jaiprakash, et al., 29 - Robotic and Image-Guided Knee Arthroscopy, in Handb. Robot. Image-Guided Surg., edited by M.H. Abedin-Nasab (Elsevier, 2020), pp. 493–514.

6 G. Kompella, M. Antico, et al., Segmentation of Femoral Cartilage from Knee Ultrasound Images Using Mask R-CNN, in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS(2019).

7 M. Antico, F. Sasazawa, et al., Deep Learning-Based Femoral Cartilage Automatic Segmentation in Ultrasound Imaging for Guidance in Robotic Knee Arthroscopy, Ultrasound Med. Biol. (2020).

8 M. Antico, D. Vukovic, et al., Deep learning for US image quality assessment based on femoral cartilage boundaries detection in autonomous knee arthroscopy, IEEE Trans. Ultrason. Ferroelectr. Freq. Control (2019).

9 C. Edwards, E. Cavanagh, et al., The use of elastography in placental research – A literature review, Placenta 99, 78–88 (2020).



Contact the supervisor for more information:

Davide Fontanarosa, PhD

Senior Lecturer, School of Clinical Sciences

Queensland University of Technology

Adjunct Professor, University of Canberra

IntelliU+ Intelligent Ultrasound Applications

Gardens Point campus, 2 George St, Brisbane, QLD 4000


Work Ph: +61 (7) 3138 2585

Mob Ph: +61 (0) 403862724