Kollia, Sofia

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.

BACKGROUND AND OBJECTIVES: The intraosseous subarcuate loop (SL) is a unique variant of the anterior inferior cerebellar artery (AICA), where a loop of the artery is trapped in the petrous bone's subarcuate fossa (SF). Recognizing this variant is crucial for planning cerebellopontine angle (CPA) surgeries; however, data regarding its frequency and management vary in the published literature. A cohort from a single center was studied using MRI to assess its prevalence, and the findings were compared with the existing literature. In addition, an intraoperative guide for mobilizing the intraosseous AICA's SL was provided through a detailed step-by-step cadaveric dissection. METHODS: Two hundred fifty-eight patients who had undergone MRI scans of the CPA (516 sides) were retrospectively reviewed. MRIs displaying vascular loops visible in the axial view were analyzed using multiplanar reconstruction, and the intraosseous loop frequency was evaluated. A scoping review was undertaken to provide an overview of previously published data on its prevalence. One embalmed and latex-injected specimen with intraosseous AICA's SL was dissected through a retrosigmoid approach, and 1 surgical case was detailed, describing the procedure to release it. RESULTS: Intraosseous AICA's SL mobilization involves the identification of its entry and exit points within the petrous bone, dural incision to expose the SF, SF drilling, subarcuate artery division, and detaching the vascular loop. Preservation of a dural cuff is crucial to prevent vascular injury. We analyzed 258 brain MRIs (mean age 55 years, 42% male). The intraosseous AICA's SL was present in 4 of 516 evaluated CPAs (0.8%). The prevalence of the vascular anomaly in the reviewed literature using different radiological modalities ranged from 0.2% to 1.6%. CONCLUSION: The intraosseous AICA's SL is an uncommon anatomic variation detectable by MRI, posing an added risk in CPA surgery. Identifying and properly mobilizing it is crucial for safe vascular preservation.