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. Levesque^4,5

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