Advanced Deep Learning Methods for Characterization and Prediction of Volumetric Growth Rate of Brain Tumours

Preoperative manual assessments of a Brain tumour is a crucial step for pre-surgical planning. Meningiomas constitute approximately 35% of intracranial tumours managed by Neurosurgeons. Understanding the exact characteristics of this type of Brain tumour as well as estimating its growth rate, can improve scientific knowledge of Neurosurgeons’s and contribute towards an optimal tumour management and intervention. There is currently a lack of research in this field for automatic prediction of meningiomas growth rates, while a few attempts have been focused on genetic characterization assessments.

Given the lack of reports, this study aims to develop advanced technology, based on deep learning strategies, for the automatic prediction of tumour growth rate and characterization of tumour features associated with the growth. We aim to use archived data from Auckland Hospital to develop automated algorithms for the prediction of meningiomas growth rate, and characterize associated contributing parameters, in a cohort of different ethnic participants (including Pākehā, Māori and Pasifika populations). Explorations will provide novel insights into automatic assessments for volumetric growth patterns in intracranial meningiomas and answer the research question regarding the possibilities of predicting tumour growth rates associated with different ethnic groups. Such visions could be helpful for longitudinal surgical planning and/or prescribing certain medicine regimes. 

•  An enthusiastic team-player with interests in the application of technology and advanced machine learning in healthcare (brain tumours). 
  
  
• Confident proficiency in coding, machine-learning, signal and image processing.
  
  
• Evidence of interest in the topic, self-motivation, and creative and critical thinking.
  
  
• Previous experience and background in one or more of computer science, biomedical engineering, coding and machine learning (deep-learning), and neurophysiological signal processing would be advantageous.
  

Page expires: 23 July 2024