Interested in machine learning/deep learning, data science, computer vision and artificial intelligence and enjoy researching and developing new technologies, which help to improve health and quality of life for a wide range of people. I completed a PhD in Computational Medical Image Analysis in 2015 and have published a number of articles in industry journals. I am currently developing deep learning (neural network) systems for segmenting and analysing skeletal muscle in real time via medical ultrasound equipment, to enable early diagnosis and monitoring of diseases such as motor neuron and dystonia.
Experienced in programming in a variety of languages, I am adept at converting concepts and ideas into usable software and implementing advanced algorithms from complex research. In previous roles, I developed web applications for a private sector firm and taught advanced programming at undergraduate level. A confident speaker with a passion for new developments in data science and artificial intelligence, I have gained science communication experience through delivering presentations and seminars at international conferences and university.
Specialties: Data Science | Big Data | Machine Learning | Statistical Analysis | Computer Programming | Artificial Intelligence | Computer Vision | Scientific Research | Neural Networks | MATLAB | Python | Java | C/C++
2012-2015
Ph.D, Computing, Manchester Metropolitan University
2009-2011
BSc, Artificial Intelligence, Manchester Metropolitan University
2007-2009
HND, Computing, The Manchester College
2019-present
Lecturer, Data Science, Manchester Metropolitan University
2015-2019
Postdoctoral Research Associate, Manchester Metropolitan University
2018-2018
Session Tutor, Mobile Applications Development, Manchester Metropolitan University
2017-2017
Session Tutor, Skills for Health Sciences (Statistics with IBM SPSS), Manchester Metropolitan University
2013-2014
Teaching Assistant (Advanced Programming, and Multimedia and Web Technologies), Manchester Metropolitan University
2011-2012
Software Engineer, Web Applications UK, Oldham
Programming Languages: Principles and Design: I currently teach a variety of programming languages based upon the fundamental principles of object orientation and functional programming. In the second term, through a combination of theoretical lectures and prctical lab session, I teach the students how to build a fully functional compiler which compiles high-level Java-like source code down to x64 GNU assembler.
High Performance Computing and Big Data: I currently teach (Deep Learning) TensorFlow as a high performance numerical computation framework.
PhD Computing (in progress): Application of Deep Learning to macro and micro facial expressions in long, high spatiotemporal resolution videos
Machine Intelligence, Deep Learning, Medical Image Analysis (Ultrasound, (f)MRI).
Publications:
Loram, I., Siddique, A., Sanchez Puccini, M. B. B., Harding, P., Silverdale, M., Kobylecki, C., & Cunningham, R. J. (2020). Objective analysis of neck muscle boundaries for cervical dystonia using ultrasound imaging and deep learning. IEEE Journal of Biomedical and Health Informatics, 1. doi:10.1109/jbhi.2020.2964098
Cunningham, R., & Loram, I. (2020). Estimation of Absolute States of Human Skeletal Muscle via Standard B-Mode Ultrasound Imaging and Deep Convolutional Neural Networks. Journal of the Royal Society Interface, 17(162).
Cunningham, R., Sánchez, M. B., Butler, P. B., Southgate, M. J., & Loram, I. D. (2019). Fully Automated Image-Based Estimation of Postural Point-Features in Children with Cerebral Palsy Using Deep Learning. Open Science, 6(11). doi:10.1098/rsos.191011
Cunningham, R., Sánchez, M., May, G., & Loram, I. (2018). Estimating Full Regional Skeletal Muscle Fibre Orientation from B-Mode Ultrasound Images Using Convolutional, Residual, and Deconvolutional Neural Networks. Journal of Imaging, 4(2), 15 pages. doi:10.3390/jimaging4020029
Cunningham, R., Harding, P., & Loram, I. (2017). Deep residual networks for quantification of muscle fiber orientation and curvature from ultrasound images. In Communications in Computer and Information Science Vol. 723 (pp. 63-73). Edinburgh, UK: Springer International Publishing AG. doi:10.1007/978-3-319-60964-5_6
Loram, I., Bate, B., Harding, P., Cunningham, R., & Loram, A. (2017). Proactive selective inhibition targeted at the neck muscles: this proximal constraint facilitates learning and regulates global control. IEEE Transactions on Neural Systems and Rehabilitation Engineering. doi:10.1109/TNSRE.2016.2641024
Cunningham, R., Harding, P., & Loram, I. (2016). Real-Time Ultrasound Segmentation, Analysis and Visualisation of Deep Cervical Muscle Structure. IEEE Transactions on Medical Imaging. doi:10.1109/TMI.2016.2623819
Harding, P., Hodson-Tole, E. F., Cunningham, R., Loram, I., & Costen, N. P. (2012). Automated detection of skeletal muscle twitches from B-mode ultrasound images: An application to Motor Neuron Disease. International Conference on Pattern Recognition, 2630-2633.
Darby, J., Li, B., Cunningham, R., & Costen, N. P. (2012). Object localization via action recognition. In International Conference on Pattern Recognition (pp. 817-820).
Cunningham., Loram, I. D., Gollee, H., & Zenzeri, J. (2016, August 16). Intermittent control of unstable multivariate systems with uncertain system parameters. In IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC). Orlando, FL, USA: IEEE. doi:10.1109/EMBC.2016.7590629
Cunningham, R., Sánchez, M. B., & Loram, I. D. (n.d.). Ultrasound Segmentation of Cervical Muscle during head motion: a Dataset and a Benchmark using Deconvolutional Neural Networks. Preprints. doi:10.31224/osf.io/fsa3c
Loram, I. D., Siddique, A., Sánchez, M. B., Harding, P., Silverdale, M., Kobylecki, C., & Cunningham, R. (n.d.). Automated analysis of neck muscle boundaries for cervical dystonia using ultrasound imaging and deep learning. doi:10.31224/osf.io/pkdwt
Cunningham, R., Sánchez, M., May, G., & Loram, I. (2018). Estimating Full Regional Skeletal Muscle Fibre Orientation from B-Mode Ultrasound Images Using Convolutional, Residual, and Deconvolutional Neural Networks. Journal of Imaging, 4(2), 15 pages. doi:10.3390/jimaging4020029
Loram, I., Bate, B., Harding, P., Cunningham, R., & Loram, A. (2017). Proactive selective inhibition targeted at the neck muscles: this proximal constraint facilitates learning and regulates global control. IEEE Transactions on Neural Systems and Rehabilitation Engineering. doi:10.1109/TNSRE.2016.2641024
£900,000 Research Co Investigator on an MRC-funded project (MR/T002034/1 "Quantification of head and trunk control for children with neuromotor and neuromuscular disorders”).