Abstract #4796

Feasibility of brain white matter segmentation on multi-echo T2-weighted images without registration: a Neural Network approach.

Jackie Yik^1,2, Roger Tam^3,4, Cristina Rubino⁵, Lara Boyd⁶, David K.B. Li^4,7, Cornelia Laule^1,2,4,8, and Hanwen Liu^1,2

¹Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada, ²International Collaboration on Repair Discoveries, Vancouver, BC, Canada, ³School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada, ⁴Radiology, University of British Columbia, Vancouver, BC, Canada, ⁵Rehabilitation Sciences, University of British Columbia, Vancouver, BC, Canada, ⁶Physical Therapy, University of British Columbia, Vancouver, BC, Canada, ⁷Medicine, University of British Columbia, Vancouver, BC, Canada, ⁸Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC, Canada

Most current methods of human brain white matter segmentation require registration to T₁image space. Artificial intelligence can reduce potential errors in, and speed up, this process by segmenting white matter from T₂-weighted images directly. A neural network was pre-trained using T₁-weighted images and FSL’s FAST followed by T₂-weighted images using transfer learning. The network could then segment new T₂-weighted images directly. T₁- and T₂-weighted image segmentations using the neural network were comparable to FSL’s FAST. Our work shows the feasibility of multi-echo T₂-weighted images for brain white matter segmentation without initial segmentation and registration of T₁-weighted images.

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

Join Here