Company or Institution
Institute of Space Technology Islamabad
Sustainable Development Goals (SDGs)
SDG 3: Good Health and Well-being
SDG 8: Decent Work and Economic Growth
SDG 9: Industry, Innovation and Infrastructure
SDG 11: Sustainable Cities and Communities
SDG 12: Responsible Consumption and Production
General description of the AI solution
Brain tumors are a threat to life for every other human being, be it adults or children. Gliomas are one of the deadliest brain tumors with extremely difficult diagnosis. The reason is their complex and heterogenous structure which give rise to subjective as well as objective errors. Their manual segmentation is a lubricous task due to their complex behavior and irregular appearance. To cater all of these issues, a lot of research has been done and is being going on to develop AI based solutions that can help doctors and radiologist in effective diagnosis of gliomas with least subjective and objective errors, but an end-to-end system is still missing. An all-in-one framework has been proposed in this research. The idea here is to develop an end-to-end multi-task learning (MTL) model with feature attention that can detect, classify, and segment gliomas by leveraging task relationships between similar tasks. Uncertainty estimation has also been incorporated in the framework to enhance the confidence level of healthcare practitioners. BRATS 2019 and 2020 datasets were used for experimental purposes. It is evident from results that deep learning based MTL models have the potential to automate the whole brain tumor analysis process and give efficient results with least human intervention.
1. Maria Nazir, Muhammad Junaid Ali, Hafiz Zahid Tufail, Ahmad Raza Shahid, Basit Raza, Sadia Shakil, Khurram Khurshid, "Multi-task learning architecture for brain tumor detection and segmentation in MRI images," J. Electron. Imag. 31(5) 051606 (27 August 2022) https://doi.org/10.1117/1.JEI.31.5.051606
2. Maria Nazir, Sadia Shakil, Khurram Khurshid,, Role of deep learning in brain tumor detection and classification (2015 to 2020): A review, Computerized Medical Imaging and Graphics, Volume 91, 2021, 101940, ISSN 0895-6111, https://doi.org/10.1016/j.compmedimag.2021.101940.
1. I participated in alocal 3MT (three minute thesis competition) and got second prize overall.
2. I also participated in National idea bank competition and got selected in first 12 positions at city level fromm 12000 participants.
HPC resources and/or Cloud Computing Services