Abstract #0664

Deep learning based prediction of H3K27M mutation in midline gliomas on multimodal MRI

Priyanka Tupe Waghmare¹, Piyush Malpure², Manali Jadhav², Abhilasha Indoria³, Richa Singh Chauhan⁴, Subhas Konar⁵, Vani Santosh³, Jitender Saini⁶, and Madhura Ingalhalikar⁷

¹E &TC, Symbiosis Institute of Technology, Pune, India, ²Symbiosis Center for Medical Image Analysis, Pune, India, ³National Institute of Mental Health and Neurosciences, Bangalore, India, ⁴National Institute of Mental Health & Neurosciences, Pune, India, ⁵National Institute of Mental Health & Neurosciences, Bangalore, India, ⁶Department of Neuroimaging & Interventional Radiology, National Institute of Mental Health & Neurosciences, Bangalore, India, ⁷Symbiosis Center for Medical Image Analysis and Symbiosis Institute of Technology, Pune, India

In midline gliomas, patients with H3K27M mutation have poor prognosis and shorter median survival. Moreover, since these tumors are located in deep locations biopsy can be challenging with substantial risk of morbidity. Our work proposes a non-invasive deep learning-based technique on pre-operative multi-modal MRI to detect the H3K27M mutation. Results demonstrate a testing accuracy of 69.76% on 51 patients. Furthermore, the class activation maps illustrate the regions that support the classification. Overall, our preliminary results provide a testimony that multimodal MRI can support identifying H3K27M mutation and with further larger studies can be translated to clinical workflow.

This abstract and the presentation materials are available to members only; a login is required.

Join Here