Isuru Wijesinghe

Profile

I am Isuru Wijesinghe, a PhD candidate at the University of Leeds, School of Mechanical Engineering.  My primary research interests lie in the broad areas of medical image analysis through deep learning in particular classification, segmentation, content-based image retrieval, and linear and non-linear optimization. In fact, I am expressly passionate about applying engineering principles in the field of Computer Science. I’m currently in my first year of PhD and my research is based on Intelligent Image-Driven Motion Management for Adaptive Precision Radiotherapy.

I hold a Degree in Master of Science (Major Component by research) of Engineering, specialized in Medical Image Analysis through Deep Learning from the University of Moratuwa.  Additionally, I hold a Degree of Bachelor of the Science (Honours) of Engineering, specialized in Computer Science & Engineering from the University of Moratuwa.

During my MSc research, I have developed a prediction model to classify severity level of Diabetic Retinopathy using retinal images through an ensemble of deep CNNs and then extended this classification model to a content-based image retrieval model architecture to search the collections for retinal images that have characteristics similar to the case(s) of interest. Moreover, I've involved with two collaborative research projects, one is to detect wound boundaries of the diabetic patients through deep learning and the other project is to classify anomalies in Gastrointestinal-Tract through Endoscopic Imagery with deep learning. I have written several research papers during this time and they were accepted as full-paper oral presentations at 31st  ICTAI in the USA, 28th  ICANN in Germany, 19th  BIBE in Greece and 05th  Mercon in Sri Lanka. Moreover, I was fortunate to win a silver award at 21st National ICT AWARDS – NBQSA 2019 for my MSc research.

Prior to commencing my MSc studies, I have worked in the software industry. I did my undergraduate internship at Sysco LABS (Pvt) Ltd. I have worked at WSO2 Lanka (Pvt) Ltd as a Software Engineer for one year and as a Senior Software Engineer for another year. Then I have worked at Linear Squared (Pvt) Ltd as a Senior Data Engineer for one year.

Research interests

"Transfer Learning with Ensemble Feature Extraction and Low-rank Matrix Factorization for Severity Stage Classification of Diabetic Retinopathy", Published In the 31st IEEE International Conference on Tools with Artificial Intelligence (ICTAI) Conference, USA – 2019  DOI: https://doi.org/10.1109/ICTAI.2019.00132

"Deep Supervised Hashing through Ensemble CNN Feature Extraction and Low-rank Matrix Factorization for Retinal Image Retrieval of Diabetic Retinopathy", Published In the 19th IEEE International Conference on Bioinformatics and Bio-engineering (BIBE) Conference, Greece. – 2019  DOI: https://doi.org/10.1109/BIBE.2019.00061

"Instance-based Segmentation for Boundary Detection of Neuropathic Ulcers through Mask-RCNN", Published In the 28th International Conference on Artificial Neural Networks (ICANN) Springer Conference, Germany – 2019  DOI: https://doi.org/10.1007/978-3-030-30493-5_49

"Automatic Scoring of Diabetic foot Ulcers through Deep CNN based Feature Extraction with Low Rank Matrix Factorization", Published In the 19th IEEE International Conference on Bioinformatics and Bio-engineering (BIBE) Conference, Greece – 2019  DOI: https://doi.org/10.1109/BIBE.2019.00069

"A Smart Telemedicine System with Deep Learning to Manage Diabetic Retinopathy and Foot Ulcers", Published In the 5th IEEE International Multidisciplinary Engineering Research Conference (Mercon), Sri Lanka – 2019  DOI: https://doi.org/10.1109/mercon.2019.8818682

"GI-Net: Anomalies Classification in Gastrointestinal Tract through Endoscopic Imagery with Deep Learning", Published In the 05th IEEE International Multidisciplinary Engineering Research Conference (Mercon), Sri Lanka – 2019  DOI: https://doi.org/10.1109/mercon.2019.8818929

"Socioeconomic Status Classification of Geographic Regions in Sri Lanka Through Anonymized Call Detail Records", Published In the 1st EAI International Conference on Big Data Innovation for Sustainable Cognitive Computing (BDCC) Springer Conference, India  DOI: https://doi.org/10.1007/978-3-030-19562-5_30

“Relationship Among the Diameter of the Area of Influence and Refill Usage of Sri Lanka Using Anonymized Call Detail Records,” ICST Trans. Scalable Inf. Syst., vol. 4, no. 12, p. 152104, Jan. 2017  DOI:  https://eudl.eu/doi/10.4108/eai.18-1-2017.152104

Qualifications

• MSc in Computer Science and Engineering
• BSc in Computer Science and Engineering

Research groups and institutes

• Computational Medicine