Nimg-01. ai-based assessment of brain volume decrease after srs and wbrt

Abstract BACKGROUND Stereotactic radiosurgery (SRS) for 4-10 brain metastases has been shown to be associated with prolonged survival as compared to whole brain radiotherapy (WBRT). Brain volume decrease after WBRT is a marker for poor survival. We aimed at comparing brain volume decrease in patients treated with either SRS or WBRT. METHODS Patients treated with SRS were drawn from the prospective dataset of the STEREOBRAIN study (DRKS00014694) that recruited from 2017 to 2020. Patients that received WBRT for 4-10 brain metastases were included retrospectively from 2012 - 2017. Images were registered to the MNI305 space utilizing the Advanced Normalization Tools (ANTs) Toolkit. Brain extraction was performed using the deep-learning based HD-BET UNet. Anatomical brain structures were labelled by employing the current state-of-the-art pretrained transformer based UNesT network using the MONAI deep-learning framework. Labels were bundled and analysed. Last pre-radiotherapy scans were compared with the last post-radiotherapy scans. The proportion of the ventricular system to the total intracranial volume was implemented as a measure of brain volume decrease. RESULTS Overall, 65 patients were included. 29 patients (45%) received SRS and 36 patients (55%) were treated with WBRT. Patients treated with SRS showed no significant increase in the volume of the ventricular system compared to the total intracranial volume (p= 0.13), whereas patients in the WBRT cohort did (p< 0.01). The mean relative volume increase of the ventricular system was 33% in the SRS cohort. In the WBRT cohort, the mean increase was 54%. The median time between the two scans was 414 days in the SRS cohort and 244 days in the WBRT cohort. CONCLUSION Brain volume decrease is less extensive in patients treated with SRS than WBRT. The clinical implication of this finding, e.g., prolonged survival and better clinical status, is yet to be determined and quantified.