Research Information System
PHYSICS & IMAGING IN RADIATION ONCOLOGY, vol.36, 2025 (ESCI, Scopus)
Background and purpose: Delineating clinical target volumes (CTVs) for glioma is challenging as consistency with the neuroanatomy needs to be carefully verified. We developed an automated approach that incorporates tumor infiltration pathways and anatomic barriers to improve the neuroanatomical consistency and efficiency of CTV delineation. Materials and methods: A deep learning model for brain structure segmentation was developed based on manual delineations of hemispheres, brainstem, cerebellum, optic chiasm, optic nerves, ventricles, and midline on CT images of ninety-nine glioma patients. Brain structures predictions are integrated into a constrained distance transform that defines the CTV as a 15-mm expansion of the gross tumor volume. Connecting structures with white matter tracts allow for expansions across different structure boundaries, e.g., cerebellum and brainstem connecting at the cerebellar peduncles. Results: Mean (+std) Dice Similarity Coefficient (DSC) for the hemispheres, brainstem, cerebel-lum, chiasm, optic nerves, midline and ventricles were (98.5 + 0.8)%, (92.5 + 2.8)%, (96.7 + 2.2)% (63.9 + 12.2)%, (83.8 + 9.0)%, (81.2 + 7.0) and (91.5 + 3.9)%. Mean (+std) 95 % Hausdorff distance (HD95) were, in mm, 1.9 + 2.5, 7.0 + 5.4, 1.8 + 1.2, 7.2 + 3.2, 2.3 + 1.0, 9.5 + 10.5, and 3.8 + 3.1, respectively. Auto-generated CTVs are compared against reference CTVs (15-mm expansion constrained by manually-contoured brain structures). The automatic CTVs showed excellent similarity to the reference CTVs with mean (+std) Surface DSC with 2 mm tolerance and HD95 scores of (95.6 + 3.4)% and (1.4 + 1.2) mm, respectively. A physician's quality assessment reported that the automated method would result in a substantial amount of time saved in 85 % of CTV delineations. Conclusion: We have successfully incorporated expert knowledge to improve the neuroanatom-ical consistency of automatically-generated CTVs for glioma.