My research area focuses on employing deep-learning based techniques in a wide range of data analysing problems, specifically, computer vision tasks such as pattern recognition, object detection, classification and segmentation.
In my latest research, I am exploring medical image analysis by performing two projects of lung cancer detection from CT scans using semantic segmentation techniques and early diagnosis of Parkinson disease from MR images.
My research interests are mainly:
- Deep learning approaches for computer vision tasks such as pattern recognition, object detection, classification and segmentation
- Medical image analysis
- Data analytics of biomedical data
I am currently involved in the teaching of:
- Data analytics Foundation
- Advanced Data Analytics
Hesamian, MH, Jia, W, He, X & Kennedy, P 2019, 'Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges.', Journal of Digital Imaging, vol. 32, no. 4, pp. 582-596.View/Download from: Publisher's site
Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.
Hesamian, MH, Jia, W, He, X & Kennedy, PJ 2019, 'Atrous Convolution for Binary Semantic Segmentation of Lung Nodule', ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Brighton. UK, pp. 1015-1019.View/Download from: Publisher's site
© 2019 IEEE. Accurately estimating the size of tumours and reproducing their boundaries from lung CT images provides crucial information for early diagnosis, staging and evaluating patients response to cancer therapy. This paper presents an advanced solution to segment lung nodules from CT images by employing a deep residual network structure with Atrous convolution. The Atrous convolution increases the field of view of the filters and helps to improve classification accuracy. Moreover, in order to address the significant class imbalance issue between the nodule pixels and background non-nodule pixels, a weighted loss function is proposed. We evaluate our proposed solution on the widely adopted benchmark dataset LIDC. A promising result of an average DCS of 81.24% is achieved, outperforming the state of the arts. This demonstrates the effectiveness and importance of applying the Atrous convolution and weighted loss for such problems.