Keywords: radiomics; neuroimaging; medical image analysis; clinical decision support; MRI; deep learning
 

"Quantitative neuroimaging with handcrafted and deep radiomics in neurological diseases"

This thesis explores the potential of "radiomics" for early diagnosis and treatment selection in neurology. This automated approach makes the medical imaging data, collected from the previous clinical cases, to bring useful recommendations for the future patients. While radiomics has shown promising results in oncology, its application in neurology is relatively limited. This thesis aimed to investigate feasibility of the neuroimaging applications of radiomics, detect the related challenges, and suggest the possible solutions. It starts with revealing neuro-oncology biomarkers, expands to non-oncological neurology, and brings up some useful solutions such as automated image segmentation and open-source medical imaging analysis tools. Overall, according to this work, radiomics shows promise in improving neurological disease diagnosis and monitoring, with potential for early detection and precision medicine advancements through collaboration and innovation.

Click here for the live stream.