Dr Shakes Chandra
Dr

Shakes Chandra

Email: 
Phone: 
+61 7 336 58359

Background

Shakes an imaging expert that leads a strong deep learning, artificial intelligence (AI) focused research team interested in medical image analysis and signal/image processing applied to many areas of science and medicine. He received his Ph.D in Theoretical Physics from Monash University, Melbourne and has been involved in applying machine learning in medical imaging for over a decade.

Shakes’ past work has involved developing shape model-based algorithms for knee, hip and shoulder joint segmentation that is being developed and deployed as a product on the Siemens syngo.via platform. More recent work involves deep learning based algorithms for semantic segmentation and manifold learning of imaging data. Broadly, he is interested in understanding and developing the mathematical basis of imaging, image analysis algorithms and physical systems. He has developed algorithms that utilise exotic mathematical structures such as fractals, turbulence, group theoretic concepts and number theory in the image processing approaches that he has developed.

He is currently a Senior Lecturer and leads a team of 20+ researchers working image analysis and AI research across healthcare and medicine. He currently teaches the computer science courses Theory of Computation and Pattern Recognition and Analysis.

Availability

Dr Shakes Chandra is:
Available for supervision

Fields of research

Artificial intelligence Biomedical engineering Biomedical imaging Combinatorics and discrete mathematics (excl. physical combinatorics) Computational imaging Computer vision and multimedia computation Deep learning Engineering Image processing Information and Computing Sciences Machine learning Mathematical Sciences Pure mathematics Theory of computation

Qualifications

  • Doctor of Philosophy, Monash University

Research interests

  • Magnetic Resonance Imaging

    Making MRI faster and more affordable through better image reconstruction, processing and analysis.

  • Image Processing

    Image reconstruction, segmentation and registration.

  • Deep learning

    Dimensionality reduction, machine learning and Artificial Intelligence

  • 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

Research impacts

Times Higher Education - A joint effort: machine learning’s search for the first MRI-based biomarker of osteoarthritis

UQNews - Making magnetic resonance imaging (MRI) faster using fractals and turbulence.

Search Professor Shakes Chandra’s works on UQ eSpace

106 works between 2006 and 2025
All (106) Journal Article (52) Other Outputs (5) Conference Publication (49)

41 - 60 of 106 works

2022

Journal Article

CAN3D: Fast 3D medical image segmentation via compact context aggregation

Dai, Wei, Woo, Boyeong, Liu, Siyu, Marques, Matthew, Engstrom, Craig, Greer, Peter B., Crozier, Stuart, Dowling, Jason A. and Chandra, Shekhar S. (2022). CAN3D: Fast 3D medical image segmentation via compact context aggregation. Medical Image Analysis, 82 102562, 1-17. doi: 10.1016/j.media.2022.102562

CAN3D: Fast 3D medical image segmentation via compact context aggregation

2022

Journal Article

Deep neural networks predict the need for CT in pediatric mild traumatic brain injury: a corroboration of the PECARN rule

Ellethy, Hanem, Chandra, Shekhar S. and Nasrallah, Fatima A. (2022). Deep neural networks predict the need for CT in pediatric mild traumatic brain injury: a corroboration of the PECARN rule. Journal of the American College of Radiology, 19 (6), 769-778. doi: 10.1016/j.jacr.2022.02.024

Deep neural networks predict the need for CT in pediatric mild traumatic brain injury: a corroboration of the PECARN rule

2022

Journal Article

Automated 3D analysis of clinical magnetic resonance images demonstrates significant reductions in cam morphology following arthroscopic intervention in contrast to physiotherapy

Bugeja, Jessica M., Xia, Ying, Chandra, Shekhar S., Murphy, Nicholas J., Eyles, Jillian, Spiers, Libby, Crozier, Stuart, Hunter, David J., Fripp, Jurgen and Engstrom, Craig (2022). Automated 3D analysis of clinical magnetic resonance images demonstrates significant reductions in cam morphology following arthroscopic intervention in contrast to physiotherapy. Arthroscopy, Sports Medicine, and Rehabilitation, 4 (4), e1353-e1362. doi: 10.1016/j.asmr.2022.04.020

Automated 3D analysis of clinical magnetic resonance images demonstrates significant reductions in cam morphology following arthroscopic intervention in contrast to physiotherapy

2022

Journal Article

Automated volumetric and statistical shape assessment of cam-type morphology of the femoral head-neck region from clinical 3D magnetic resonance images

Bugeja, Jessica M., Xia, Ying, Chandra, Shekhar S., Murphy, Nicholas J., Eyles, Jillian, Spiers, Libby, Crozier, Stuart, Hunter, David J., Fripp, Jurgen and Engstrom, Craig (2022). Automated volumetric and statistical shape assessment of cam-type morphology of the femoral head-neck region from clinical 3D magnetic resonance images. Quantitative Imaging in Medicine and Surgery, 12 (10), 4941. doi: 10.21037/qims-22-332

Automated volumetric and statistical shape assessment of cam-type morphology of the femoral head-neck region from clinical 3D magnetic resonance images

2022

Conference Publication

Anomaly-aware 3D segmentation of knee magnetic resonance images

Woo, Boyeong, Engstrom, Craig, Fripp, Jurgen, Crozier, Stuart and Chandra, Shekhar S. (2022). Anomaly-aware 3D segmentation of knee magnetic resonance images. 5th International Conference on Medical Imaging with Deep Learning, Zurich, Switzerland, 6-8 July 2022. Cambridge, MA United States: ML Research Press.

Anomaly-aware 3D segmentation of knee magnetic resonance images

2022

Conference Publication

Undersampled MRI reconstruction with side information-guided normalisation

Liu, Xinwen, Wang, Jing, Peng, Cheng, Chandra, Shekhar S., Liu, Feng and Zhou, S. Kevin (2022). Undersampled MRI reconstruction with side information-guided normalisation. Medical Image Computing and Computer Assisted Intervention – MICCAI, Singapore, Singapore, 18-22 September 2022. Cham, Switzerland: Springer Nature Switzerland. doi: 10.1007/978-3-031-16446-0_31

Undersampled MRI reconstruction with side information-guided normalisation

2022

Conference Publication

FDGATII: Fast Dynamic Graph Attention with Initial Residual and Identity

Kulatilleke, Gayan K., Portmann, Marius, Ko, Ryan and Chandra, Shekhar S. (2022). FDGATII: Fast Dynamic Graph Attention with Initial Residual and Identity. 35th Australasian Joint Conference on Artificial Intelligence: AI 2022, Perth, WA Australia, 5–8 December 2022. Cham, Switzerland: Springer. doi: 10.1007/978-3-031-22695-3_6

FDGATII: Fast Dynamic Graph Attention with Initial Residual and Identity

2021

Conference Publication

Slim-YOLO: a simplified object detection model for the detection of pigmented iris freckles as a potential biomarker for cutaneous melanoma

Naranpanawa, D. Nathasha U., Gu, Yanyang, Chandra, Shekhar S., Betz-Stablein, Brigid, Sturm, Richard A., Soyer, H. Peter and Eriksson, Anders P. (2021). Slim-YOLO: a simplified object detection model for the detection of pigmented iris freckles as a potential biomarker for cutaneous melanoma. Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, Australia, 29 November - 1 December 2021. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/dicta52665.2021.9647150

Slim-YOLO: a simplified object detection model for the detection of pigmented iris freckles as a potential biomarker for cutaneous melanoma

2021

Journal Article

Automated analysis of immediate reliability of T2 and T2* relaxation times of hip joint cartilage from 3 T MR examinations

Bugeja, Jessica M., Chandra, Shekhar S., Neubert, Aleš, Fripp, Jurgen, Lockard, Carly A., Ho, Charles P., Crozier, Stuart and Engstrom, Craig (2021). Automated analysis of immediate reliability of T2 and T2* relaxation times of hip joint cartilage from 3 T MR examinations. Magnetic Resonance Imaging, 82, 42-54. doi: 10.1016/j.mri.2021.06.008

Automated analysis of immediate reliability of T2 and T2* relaxation times of hip joint cartilage from 3 T MR examinations

2021

Journal Article

The detection of mild traumatic brain injury in paediatrics using artificial neural networks

Ellethy, Hanem, Chandra, Shekhar S. and Nasrallah, Fatima A. (2021). The detection of mild traumatic brain injury in paediatrics using artificial neural networks. Computers in Biology and Medicine, 135 104614, 1-9. doi: 10.1016/j.compbiomed.2021.104614

The detection of mild traumatic brain injury in paediatrics using artificial neural networks

2021

Journal Article

Deep learning in magnetic resonance image reconstruction

Chandra, Shekhar S., Bran Lorenzana, Marlon, Liu, Xinwen, Liu, Siyu, Bollmann, Steffen and Crozier, Stuart (2021). Deep learning in magnetic resonance image reconstruction. Journal of Medical Imaging and Radiation Oncology, 65 (5) 1754-9485.13276, 564-577. doi: 10.1111/1754-9485.13276

Deep learning in magnetic resonance image reconstruction

2021

Journal Article

Bespoke fractal sampling patterns for discrete Fourier space via the kaleidoscope transform

White, Jacob Michael, Crozier, Stuart and Chandra, Shekhar Suresh (2021). Bespoke fractal sampling patterns for discrete Fourier space via the kaleidoscope transform. IEEE Signal Processing Letters, 14 (8), 1-5. doi: 10.1109/lsp.2021.3116510

Bespoke fractal sampling patterns for discrete Fourier space via the kaleidoscope transform

2021

Conference Publication

Can3d: Fast 3D knee mri segmentation via compact context aggregation

Dai, Wei, Woo, Boyeong, Liu, Siyu, Marques, Matthew, Tang, Fangfang, Crozier, Stuart, Engstrom, Craig and Chandra, Shekhar (2021). Can3d: Fast 3D knee mri segmentation via compact context aggregation. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, France, 13-16 April 2021. Piscataway, NJ United States: IEEE. doi: 10.1109/isbi48211.2021.9433784

Can3d: Fast 3D knee mri segmentation via compact context aggregation

2021

Journal Article

On the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks

Liu, Xinwen, Wang, Jing, Sun, Hongfu, Chandra, Shekhar S, Crozier, Stuart and Liu, Feng (2021). On the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks. Magnetic resonance imaging, 77, 159-168. doi: 10.1016/j.mri.2020.12.019

On the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks

2021

Journal Article

Discrete element and finite element methods provide similar estimations for hip joint contact mechanics during walking gait

Li, Mao, Venäläinen, Mikko S., Chandra, Shekhar S., Patel, Rushabh, Fripp, Jurgen, Engstrom, Craig, Korhonen, Rami K., Töyräs, Juha and Crozier, Stuart (2021). Discrete element and finite element methods provide similar estimations for hip joint contact mechanics during walking gait. Journal of Biomechanics, 115 110163, 1-11. doi: 10.1016/j.jbiomech.2020.110163

Discrete element and finite element methods provide similar estimations for hip joint contact mechanics during walking gait

2021

Conference Publication

End-to-end ugly duckling sign detection for melanoma identification with transformers

Yu, Zhen, Mar, Victoria, Eriksson, Anders, Chandra, Shakes, Bonnington, Paul, Zhang, Lei and Ge, Zongyuan (2021). End-to-end ugly duckling sign detection for melanoma identification with transformers. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, Strasbourg, France, 27 September-1 October 2021. Cham, Switzerland: Springer Nature Switzerland. doi: 10.1007/978-3-030-87234-2_17

End-to-end ugly duckling sign detection for melanoma identification with transformers

2021

Journal Article

The application of statistical shape modeling for lung morphology in aerosol inhalation dosimetry

Xi, Jinxiang, Talaat, Mohamed, Si, Xiuhua April and Chandra, Shekhar (2021). The application of statistical shape modeling for lung morphology in aerosol inhalation dosimetry. Journal of Aerosol Science, 151 105623, 105623. doi: 10.1016/j.jaerosci.2020.105623

The application of statistical shape modeling for lung morphology in aerosol inhalation dosimetry

2020

Journal Article

Automatic lesion detection, segmentation and characterization via 3D multiscale morphological sifting in breast MRI

Min, Hang, McClymont, Darryl, Chandra, Shekhar S., Crozier, Stuart and Bradley, Andrew P. (2020). Automatic lesion detection, segmentation and characterization via 3D multiscale morphological sifting in breast MRI. Biomedical Physics and Engineering Express, 6 (6) 065027, 065027. doi: 10.1088/2057-1976/abc45c

Automatic lesion detection, segmentation and characterization via 3D multiscale morphological sifting in breast MRI

2020

Journal Article

Fast geometric distortion correction using a deep neural network: implementation for the 1 Tesla MRI-Linac system

Li, Mao, Shan, Shanshan, Chandra, Shekhar S., Liu, Feng and Crozier, Stuart (2020). Fast geometric distortion correction using a deep neural network: implementation for the 1 Tesla MRI-Linac system. Medical Physics, 47 (9) mp.14382, 4303-4315. doi: 10.1002/mp.14382

Fast geometric distortion correction using a deep neural network: implementation for the 1 Tesla MRI-Linac system

2020

Conference Publication

Deep simultaneous optimization of sampling and reconstruction for multi-contrast MRI

Liu, Xinwen, Wang, Jing, Tang, Fangfang, Chandra, Shekhar S., Liu, Feng and Crozier, Stuart (2020). Deep simultaneous optimization of sampling and reconstruction for multi-contrast MRI. ISMRM & SMRT Virtual Conference & Exhibition, 2020, Online, 8-14 August 2020.

Deep simultaneous optimization of sampling and reconstruction for multi-contrast MRI

Current funding

  • 2026 - 2029
    Next generation magnetic resonance imaging through vision
    ARC Future Fellowships
    Open grant
  • 2025 - 2027
    Cost effective and portable low-field musculoskeletal MRI for high performance sport
    Australia's Economic Accelerator Innovate Grants
    Open grant
  • 2020 - 2026
    PREDICT-TBI - PREdiction and Diagnosis using Imaging and Clinical biomarkers Trial in Traumatic Brain Injury: the value of Magnetic Resonance Imaging
    NHMRC MRFF Traumatic Brain Injury Mission
    Open grant

Past funding

  • 2022 - 2025
    Advancing the visualisation and quantification of nephrons with MRI
    ARC Discovery Projects
    Open grant
  • 2022 - 2025
    Robust, valid and interpretable deep learning for quantitative imaging
    ARC Linkage Projects
    Open grant
  • 2021 - 2024
    ChondralHealth Productization: Automated Musculoskeletal MR Image Analysis Algorithms
    Siemens Healthcare Pty Ltd
    Open grant
  • 2021 - 2024
    Osteoarthritis Compass: Personalized prediction of disease onset and progression. (NHMRC Ideas Grant administered by Griffith University)
    Griffith University
    Open grant
  • 2018 - 2022
    MR Hip Intervention and Planning System to enhance clinical and surgical outcomes
    NHMRC Development Grant
    Open grant

Availability

Dr Shakes Chandra is:
Available for supervision

Looking for a supervisor? Read our advice on how to choose a supervisor.

Available projects

  • Next generation magnetic resonance imaging MRI through vision

    Summary: Magnetic resonance imaging (MRI) is crucial for diagnosing diseases within the human body. In this project, we develop new AI methods that leverage human visual perception to make MRI faster and more affordable.

    Technologies such as magnetic resonance imaging (MRI) are essential in healthcare for non-invasively seeing inside the human body for disease diagnosis and assessment. However, imaging cost for MRI is so prohibitive that it is seldom used unless there is no other option despite its effectiveness. The cost is largely because MRI is a slow imaging modality compared to other options that do not provide as much information and soft tissue contrast needed to detect diseases such as cancer. Although some progress has been made to improve acquisition speed, all current methods do not make any allowances for the way that human experts read and understand regions of interest. A reduction in scan time will make MRI cheaper and therefore allow the technology to be more readily utilised in the future.

    This project aims to create new artificial intelligence (AI) models and unify them with MRI acquisition directly in its measurement domain, helping us explain such models and create acquisitions more akin to human vision that only acquires the areas an operator needs, thereby reducing scan times.

Supervision history

Current supervision

Completed supervision

Enquiries

For media enquiries about Dr Shakes Chandra's areas of expertise, story ideas and help finding experts, contact our Media team:

communications@uq.edu.au