1338 Automated Volumetric Segmentation Enables Post-Laser Interstitial Thermal Therapy Response Assessment

INTRODUCTION: Laser interstitial thermal therapy (LITT) allows for confirmatory tissue diagnosis, surgical cytoreduction, and faster return to systemic therapies for patients with brain tumors or radiation necrosis. Ablated tissue remains in situ following LITT, with post-LITT edema potentially associated with transient clinical worsening and complicating subsequent response assessment. METHODS: All patients receiving LITT at a single center for tumors or radiation necrosis from 2015 – 2023 with = 9 months of MRI follow-up were retrospectively reviewed. A 3D U-net segmentation model implemented in nnU-Net was developed for automated segmentation of Contrast-enhancing Lesion Volume (CeLV) of LITT-treated lesions on T1-weighted post-contrast MR images. CeLVs were analyzed to perform volumetric post-LITT response assessments. RESULTS: Sixty-one LITT-treated lesions and 6 control cases of medically-managed radiation necrosis were analyzed across 384 unique MRI exams. Automated segmentation was qualitatively accurate in 367/384 (95.6%) images. CeLV increased to a median of 68.3% (IQR 35.1 – 109.2%) from baseline at 1 – 3 months from LITT (P = 0.0012) and returned to baseline thereafter. Median overall survival (mOS) for LITT-treated patients was 39.1 (9.2 – 93.4) months. In accordance with previously established volumetric thresholds, volumetric disease progression was defined as CeLV increase = 40% from volumetric nadir or baseline. Twenty-one of 56 (37.5%) patients experienced volumetric progression with a progression-free survival of 21.4 (6.0 – 93.4) months. Volumetric progression was associated with lower mOS (17.3 vs 62.1 months, P = 0.0015). CONCLUSIONS: CeLV increased to nearly 70% from baseline at 1 - 3 months following LITT, resolving within 3 - 6 months of the procedure. To facilitate inclusion of LITT patients in clinical trials, we developed and demonstrated feasibility of response assessment criteria to account for this transient post-ablation CeLV expansion. Automated lesion segmentation may increase the rate of adoption for volumetric response assessment in clinical practice.