Floyd, Scott

Abstract Background Multi-modality therapy has improved survival for many patients with brain metastases. However, neurocognitive sequelae remain a challenge. While advances in radiotherapy have reduced toxicity, the potential interaction with targeted therapy and immunotherapy and the consequent impact on neurocognitive outcomes remain poorly defined. We appraised the current evidence on neurocognitive outcomes in the era of modern combined-modality therapy. Methods This systematic review adhered to PRISMA guidelines and included clinical trials reporting neurocognitive outcomes in patients with brain metastases receiving radiotherapy ± concurrent systemic therapies. Studies published through December 31, 2024 were identified through PubMed/Medline, EMBASE, and Web of Science using pre-defined MeSH term-based search strings. Results 39 studies from 1997-2024 involving 6,617 patients met inclusion criteria (n = 27 whole-brain radiotherapy [WBRT]; n = 12 radiosurgery), including six studies evaluating combined-modality therapy in 1,161 patients. Baseline cognitive evaluation was performed inconsistently, but neurocognitive deficits were frequently observed prior to treatment. Most randomized trials reported improved cognitive outcomes and quality of life with advanced radiotherapy techniques (e.g., hippocampal avoidance, radiosurgery) vs WBRT. Among 20 randomized trials comparing radiotherapy with or without a concurrent investigational systemic therapy, only four included neurocognitive assessments. There was no evidence of cognitive sequelae with combined-modality therapy, though evaluable trials were limited due to inconsistent reporting of neurocognitive functioning. Conclusion As survival improves in patients with brain metastases, preserved cognition is an important outcome measure. The lack of neurocognitive endpoints in pivotal brain metastasis trials represents a critical evidence gap. The interaction between radiotherapy and novel systemic therapies, and their combined effects on neurocognition, remain unknown. To address this, we recommend 1) integrating sensitive, pragmatic, and tailored neurocognitive assessments into oncology trials to quantify additive toxicity, 2) early and systematically incorporating neuropsychology into care pathways, 3) expanding radiation dose-sparing and radioprotective strategies, and 4) evaluating the utility of cognitive rehabilitation programs.

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.

Abstract Neurocognitive function (NCF) deficits are common in patients with brain metastases, occurring in up to 90% of cases. NCF deficits may be caused by tumor-related factors and/or treatment for the metastasis, including surgery, radiation therapy, chemotherapy, and immunotherapy. In recent years, strategies to prevent negative impact of treatments and ameliorate cognitive deficits for patients with brain tumors have gained momentum. In this review, we report on research that has established the efficacy of preventative and rehabilitative therapies for NCF deficits in patients with brain metastases. Surgical strategies include the use of laser interstitial thermal therapy and intraoperative mapping. Radiotherapy approaches include focal treatments such as stereotactic radiosurgery and tailored approaches such as hippocampal avoidant whole-brain radiotherapy (WBRT). Pharmacologic options include use of the neuroprotectant memantine to reduce cognitive decline induced by WBRT and incorporation of medications traditionally used for attention and memory problems. Integration of neuropsychology into the care of patients with brain metastases helps characterize cognitive patterns, educate patients and families regarding their management, and guide rehabilitative therapies. These and other strategies will become even more important for long-term survivors of brain metastases as treatment options improve.