group focuses on fundamental and applied research in the life sciences domains. We design and develop applied computational methods for the understanding, analysis and integration of data primarily coming from multi-modal medical imaging modalities as well as multi-omics data. We also teach courses such as, medical image processing and bioinformatics (with a focus on data analysis) to students at the bachelor, master and PhD levels.
Incorporating Evolving Biological Information in Protein Function Prediction
Covid-19 Detection using Chest Radiographs
The knowledge of protein functions plays an essential role in understanding biological cells which have a significant impact on human life in areas, such as, personalized medicine, better crops and therapeutic interventions. The technological advancement in the field of biology is improving the level of biological information associated with proteins. A key issue that has received little or no attention is how to incorporate and take advantage from the ever evolving biological information in building effective models for protein function predictions. In this project, we will address this issue by examining proposing and analyzing predictive models suitable for this task.
The Corona Virus Disease 2019 (COVID-19) is a lethal disease, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, which is affecting millions of people worldwide. Infected patients exhibit symptoms such as high fever, cough, shortness of breath etc. Currently, the gold standard test to detect COVID-19 is the real-time reverse transcription polymerase chain reaction (RT-PCR) test, while it is also an expensive, manual and time-consuming screening method. An alternative method used for the detection of COVID-19 disease is the visual examination of chest X-rays. Although the X-ray images provide good contrast for the presence of COVID-19 disease but their quality is often affected due to various factors, most importantly:
These problems result in vague appearance of the opacities, as well as variability in the shape of the opacity in X-ray radiographs. To overcome these problems, this works conceptualizes the development of a constrained size, cascaded deep learning model that will improve the segmentation of lungs in the chest X-ray images, in order to improve the screening of COVID-19 disease.
IEEE,2021
,2021
Elsevier,2021
Elsevier,2020
John Wiley and Sons Inc.,2020
Springer US,2020
IEEE,2019
Springer, Cham,2021
MediaEval,2020
IEEE,2020
Springer Nature,2020
IEEE,2019
