Godfrey, Devon

Background/Objectives: Hypofractionated ablative radiation is an increasingly popular option for patients with hepatocellular carcinoma (HCC). However, concern remains about the risk for radiation-induced liver toxicity in patients with decompensated liver function. Methods: We retrospectively identified patients with underlying Child-Pugh (CP) B or C liver function treated at our University and Veterans Affairs (VA) departments from 2014 to 2019. Primary endpoints included treatment-related toxicity and dosimetric parameters. Results: 38 patients were included in the analysis. Most patients (98%) had CP B or Albumin-Bilirubin (ALBI) grade 2–3 (100%) liver disease. The median dose was 50 Gy (range 30–50) delivered in 5 or 10 fractions. Most patients had a single tumor treated (66%) with a median size of 3.1 cm (Interquartile Range (IQR) 2.3–4.1). The mean liver dose was 9.28 Gy (IQR 6.76–13.64) with a liver D800cc of 3.99 Gy (IQR 1.41–8.02). All patients completed their intended course with a median follow-up of 43 months. Four patients (10.3%) developed non-classical radiation-induced liver disease (RILD), comparable to the rate for patients with CP A function treated contemporaneously (8.3%). Otherwise, one patient (2.6%) experienced acute grade 3+ (non-RILD) hepatobiliary toxicity, while one patient (2.6%) experienced late grade 3+ hepatobiliary toxicity. Local control was promising with 2-year freedom from progression in the treated lesion of 73% (95% CI 38–91%). Median overall survival was 12 months (95% CI 5–25 months). Conclusions: Ablative radiation for patients with decompensated liver function and HCC appears well tolerated with low rates of RILD and encouraging local control. With careful selection, these patients should be considered for inclusion in future randomized trials.

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well- annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.