Meeting Banner
Abstract #2467

Automated segmentation of soft tissue sarcoma into distinct pathological regions using diffusion and T2 relaxation

Shu Xing1, Carolyn R. Freeman2, Sungmi Jung3, and Ives R. Levesque4,5

1Physics, McGill, Montreal, QC, Canada, 2Radiation Oncology, McGill University Health Center, Montreal, Canada, 3Pathology, McGill University Health Center, Montreal, Canada, 4Medical Physics Unit, McGill University, Montreal, QC, Canada, 5Research Institute, McGill University Health Center, Montreal, QC, Canada

In this work, we propose a novel method to automatically distinguish various pathological tissue types within tumors, in particular soft tissue sarcoma. Pathological tissue signatures within the tumor, including high cellularity, high T2 content, or necrosis, can be interpreted from the combination of T2-weighted images, DW-MRI (b=500-1000 s/mm2) and ADC maps. We propose an automated approach that compares the ADC, the T2, and a quantified surrogate for the high-b-value DW-MRI image, between the tumor and a reference tissue, to segment the tumor. Delineating tumor sub-regions is useful in assessing the overall tumor environment and may inform sub-region-targeted radiation dose-painting.

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

Join Here