Dr Shakes Chandra

Lecturer

School of Information Technology and Electrical Engineering
Faculty of Engineering, Architecture and Information Technology
shekhar.chandra@uq.edu.au
+61 7 336 58359

Overview

Shakes' expertise include image processing, machine/deep learning, image reconstruction and medical image analysis. He received his Ph.D in Theoretical Physics from Monash University, Melbourne in 2010 on a discrete theory of the Radon transform that utilises circulant matrices. He did a post-doctoral fellowship with CSIRO, Brisbane within the biomedical imaging group on musculoskeletal imaging. More specifically, he developed deformable model and machine learning algorithms for knee, hip and shoulder joint segmentation for deployment on the Siemens Syngo platform. He currently teaches the computer science courses Theory of Computation and Pattern Recognition and Analysis.

Research Interests

  • Machine learning
    Dimensionality reduction and Deep Learning
  • Magnetic Resonance Imaging
    Making MRI faster and more affordable through better image reconstruction, processing and analysis.
  • Image Processing
    Image reconstruction, segmentation and registration.
  • Fractals and Chaos
    Applying fractals and chaos to image processing and computer science.
  • Number Theory
    Applying number theory to image processing and computer science.
  • Medical Image Analysis
    Medical image segmentation and shape analysis

Qualifications

  • Doctor of Philosophy, Monash University

Publications

View all Publications

Supervision

View all Supervision

Available Projects

  • Magnetic resonance (MR) imaging has become an important non-invasive radiological modality for various clinical applications, such as cartilage assessment for Osteoarthritis and treatment planning for prostate cancer. MR images in 3D, while providing a wealth of anatomical information, including bones and soft tissue, are difficult to analyse due to the presence of a large number of complex structures. Thus, extracting meaningful clinical information without human interaction is a challenging task. Developing such automatic methods are important in order to reduce human errors and the time taken by clinicians in completing mundane tasks, such as marking or delineating 3D images by hand, from hours to just a few minutes by utilising computers.

    In this project, the student will develop novel algorithms to solve segmentation and detection problems for MR imaging that could possibly be deployed to MRI scanners and may eventually used for diagnostic purposes. The project will involve applying computer vision and machine learning techniques (including deep learning) to MR image processing and analysis.

View all Available Projects

Publications

Journal Article

Conference Publication

  • Marques, Matthew, Engstrom, Craig, Fripp, Jurgen, Crozier, Stuart and Chandra, Shekhar S. (2020). Fast high dynamic range MRI by Contrast Enhancement Networks. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, United States, 3-7 April 2020. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers . doi: 10.1109/isbi45749.2020.9098373

  • Min, Hang, Wilson, Devin, Huang, Yinhuang, Liu, Siyu, Crozier, Stuart, Bradley, Andrew P. and Chandra, Shekhar S. (2020). Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNN. 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, United States, 3-7 April 2020. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers (IEEE). doi: 10.1109/isbi45749.2020.9098732

  • Sun, Jiayu and Chandra, Shekhar S. (2018). SPIFFY: a simpler image viewer for medical imaging. 4th Information Technology and Mechatronics Engineering Conference (ITOEC2018), Chongqing, China, 14-16 December 2018. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers (IEEE). doi: 10.1109/ITOEC.2018.8740656

  • Min, Hang, Chandra, Shekhar S., Dhungel, Neeraj, Crozier, Stuart and Bradley, Andrew P. (2017). Multi-scale mass segmentation for mammograms via cascaded random forests. 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017, Melbourne, VIC, Australia, 18 - 21 April 2017. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/ISBI.2017.7950481

  • Neubert, Aleš, Fripp, Jurgen, Chandra, Shekhar S., Engstrom, Craig and Crozier, Stuart (2016). Automated intervertebral disc segmentation using probabilistic shape estimation and active shape models. Third International Workshop and Challenge, CSI 2015, Munich, Germany, 5 October 2015. Switzerland: Springer. doi: 10.1007/978-3-319-41827-8_15

  • Chandra, Shekhar S., Archchige, Ramitha, Ruben, Gary, Jin, Jin, Li, Mingyan, Kingston, Andrew M., Svalbe, Imants and Crozier, Stuart (2016). Finite radial reconstruction for magnetic resonance imaging: a theoretical study. International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016, Gold Coast, QLD, Australia, 30 November-2 December 2016. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/DICTA.2016.7797043

  • Neubert, Ales, Naser, Ibrahim, Paproki, Anthony, Engstrom, Craig, Fripp, Jurgen, Crozier, Stuart and Chandra, Shekhar S. (2016). Incremental shape learning of 3D surfaces of the knee, data from the osteoarthritis initiative. 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic, 13-16 April, 2016. Piscataway, United States: IEEE Operations Center. doi: 10.1109/ISBI.2016.7493406

  • Neubert, Ales, Chandra, Shekhar S., Engstrom, Craig, Fripp, Jurgen and Crozier, Stuart (2015). Shape reconstruction using EM-ICP mesh registration and robust statistical shape models. Symposium on Statistical Shape Models Applications, Delemont, Switzerland, 30 September - 2 October, 2015.

  • Dowling, J. A., Burdett, N., Greer, P. B., Sun, J., Parker, J., Pichler, P., Stanwell, P., Chandra, S., Rivest-Henault, D., Ghose, S., Salvado, O. and Fripp, J. (2014). Automatic Atlas Based Electron Density and Structure Contouring for MRI-based Prostate Radiation Therapy on the Cloud. XVII International Conference on the Use of Computers in Radiation Therapy, Melbourne, Australia, 6–9 May 2013. Bristol, United Kingdom: Institute of Physics Publishing. doi: 10.1088/1742-6596/489/1/012048

  • Yang, Zhengyi, Fripp, Jurgen, Engstrom, Craig, Chandra, Shekhar, Xia, Ying, Paproki, Anthony, Strudwick, Mark, Neubert, Ales and Crozier, Stuart (2014). Automatic Bone Segmentation for Shoulder {MRI} using Statistical Shape Models. 2014 – Joint Annual Meeting ISMRM-ESMRMB, 22nd Scientific Meeting and Exhibition, Milan, Italy, 10-16 May 2014. Berkeley, CA United States: International Society for Magnetic Resonance in Medicine.

  • Dowling, Jason, Dang, K., Fox, Chris D., Chandra, S., Gill, Suki, Kron, T., D Pham, D. and Foroudi, F. (2014). Fast cine-magnetic resonance imaging point tracking for prostate cancer radiation therapy planning. ICCR 2013: XVII International Conference on the Use of Computers in Radiation Therapy, Melbourme, VIC, Australia, 6–9 May, 2013. Temple Way, Bristol, United Kingdom: Institute of Physics Publishing. doi: 10.1088/1742-6596/489/1/012027

  • Svalbe, Imants, Kingston, Andrew, Guedon, Jeanpierre, Normand, Nicolas and Chandra, Shekhar S. (2013). Direct Inversion of Mojette Projections. 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne , Australia, 15 - 18 September 2013. Piscataway, NJ United States: IEEE. doi: 10.1109/ICIP.2013.6738214

  • Xia, Ying, Chandra, Shakes, Salvado, Oliver, Fripp, Jurgen, Schwartz, Raphael, Lauer, Lars, Engstrom, Craig M. and Crozier, Stuart (2012). Automated bone segmentation and bone-cartilage interface extraction from MR images of the hip. International Society for Magnetic Resonance in Medicine, Melbourme, VIC, Australia, 5-11 May 2012.

  • Yang, Zhengyi, Crozier, Stuart, Engstrom, Craig, Xia, Ying, Neubert, Ales, Brancato, Tania, Schwarz, Raphael, Lauer, Lars, Fripp, Jurgen, Chandra, Shekhar and Salvado, Olivier (2012). Morphology-based interslice interpolation on manual segmentations of joint bones and muscles in MRI. 2012 International Conference on Digital Image Computing Techniques and Applications (DICTA), Fremantle, WA, Australia, 3-5 December 2012. Piscataway, NJ, United States: IEEE. doi: 10.1109/DICTA.2012.6411678

  • Chandra, Shekhar, Xia, Yinq, Engstrom, Craig, Schwarz, Raphael, Lauer, Lars, Crozier, Stuart, Salvado, Olivier and Fripp, Jurgen (2012). Unilateral hip joint segmentation with shape priors learned from missing data. 9th IEEE International Symposium on Biomedical Imaging (ISBI), Barcelona, Spain, 2-5 March 2012. Piscataway, NJ, United States: IEEE. doi: 10.1109/ISBI.2012.6235909

  • Xia, Ying, Chandra, Shakes, Salvado, Olivier, Fripp, Jurgen, Schwarz, Raphael, Lauer, Lars, Engstrom, Craig and Crozier, Stuart (2011). Automated MR hip bone segmentation. International Conference on Digital Image Computing Techniques and Applications (DICTA), Noosa, QLD, Australia, 6-8 December 2011. Piscataway, NJ, United States: IEEE. doi: 10.1109/DICTA.2011.13

  • Chandra, Shekhar, Dowling, Jason, Shen, Kaikai, Pluim, Josien, Greer, Peter, Salvado, Olivier and Fripp, Jurgen (2011). Automatic segmentation of the prostate in 3D magnetic resonance images using case specific deformable models. International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011, Noosa Heads, Qld., Australia, 6-8 December 2011. Piscataway, NJ, United States: I E E E. doi: 10.1109/DICTA.2011.10

  • Dowling, Jason A., Fripp, Jurgen, Chandra, Shekhar, Pluim, Josien P. W., Lambert, Jonathan, Parker, Joel, Denham, James, Greer, Peter B. and Salvado, Olivier (2011). Fast automatic multi-atlas segmentation of the prostate from 3D MR images. 14th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2011), Toronto, Canada, 18-22 September 2011. Heidelberg, Germany: Springer. doi: 10.1007/978-3-642-23944-1_2

  • Svalbe, Imants and Chandra, Shekhar (2011). Growth of Discrete Projection Ghosts Created by Iteration. 16th International Conference on Discrete Geometry for Computer Imagery, Nancy France, 6 - 8 April 2011. Heidelberg, Germany: Springer. doi: 10.1007/978-3-642-19867-0_34

  • Svalbe, Imants, Nazareth, Nikesh, Chandra, Shekhar and Normand, Nicolas (2010). On constructing minimal ghosts. International Conference on Digital Image Computing: Techniques and Applications, DICTA 2010, Sydney, NSW Australia, 01 - 03 December 2010. Piscataway, NJ United States: I E E E. doi: 10.1109/DICTA.2010.56

  • Chandra, S. and Svalbe, I. (2009). A fast number theoretic finite radon transform. Digital Image Computing: Techniques and Applications, DICTA 2009, Melbourne, VIC Australia, 1 - 3 December 2009. Piscataway, NJ United States: I E E E. doi: 10.1109/DICTA.2009.67

  • Chandra, Shekhar and Svalbe, Imants (2008). A method for removing cyclic artefacts in discrete tomography using latin squares. 19th International Conference on Pattern Recognition (ICPR 2008), Tampa, Fl United States, 8 - 11 Dec 2008. Washington, DC United States: I E E E Computer Society. doi: 10.1109/ICPR.2008.4761615

  • Chandra, Shekhar, Svalbe, Imants and Guedon, Jean-Pierre (2008). An exact, non-iterative Mojette inversion technique utilising ghosts. 14th International Conference on Discrete Geometry for Computer Imagery, Lyon, France, 16 - 18 April 2008. Heidelberg, Germany: Springer. doi: 10.1007/978-3-540-79126-3_36

  • Svalbe, Imants, Chandra, Shekhar, Kingston, Andrew and Guédon, Jean-Pierre (2006). Quantised angular momentum vectors and projection angle distributions for discrete radon transformations. 13th International Conference on Discrete Geometry for Computer Imagery, DGCI 2006, , , October 25, 2006-October 27, 2006. Springer Verlag. doi: 10.1007/11907350_12

Other Outputs

PhD and MPhil Supervision

Current Supervision

Completed Supervision

Possible Research Projects

Note for students: The possible research projects listed on this page may not be comprehensive or up to date. Always feel free to contact the staff for more information, and also with your own research ideas.

  • Magnetic resonance (MR) imaging has become an important non-invasive radiological modality for various clinical applications, such as cartilage assessment for Osteoarthritis and treatment planning for prostate cancer. MR images in 3D, while providing a wealth of anatomical information, including bones and soft tissue, are difficult to analyse due to the presence of a large number of complex structures. Thus, extracting meaningful clinical information without human interaction is a challenging task. Developing such automatic methods are important in order to reduce human errors and the time taken by clinicians in completing mundane tasks, such as marking or delineating 3D images by hand, from hours to just a few minutes by utilising computers.

    In this project, the student will develop novel algorithms to solve segmentation and detection problems for MR imaging that could possibly be deployed to MRI scanners and may eventually used for diagnostic purposes. The project will involve applying computer vision and machine learning techniques (including deep learning) to MR image processing and analysis.