Search

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 clinical environments and providing personalized volumetric reports to patients undergoing BM treatment., Competing Interests: Conflicts of Interest No conflicts of interest to disclose.

Objective: Although most musculoskeletal MRI examinations are interpreted by radiologists, some nonradiologists provide interpretations as well. We aimed to study day of week (weekday vs weekend), site of service, and patient complexity differences between radiologists and nonradiologists interpreting lower extremity MRI examinations on Medicare beneficiaries., Materials and Methods: Using fee-for-service carrier claims for a 5% sample of Medicare beneficiaries nationally from 2012 through 2014, we identified all lower extremity joint MRI examinations. Services were classified by physician specialty, day of week, and site of service. Charlson comorbidity index (CCI) values were calculated for all patients. Chi-square statistical testing was performed., Results: Of all 125,800 billed lower extremity joint MRI examinations, 118,295 (94.0%) were performed on weekdays and 7505 (6.0%) on weekends. Of the weekday examinations, radiologists interpreted 85,991 (83.3%) and nonradiologists 17,260 (16.7%). Of the weekend examinations, radiologists interpreted 6212 (92.8%) and nonradiologists 485 (7.2%). Of examinations performed in inpatient hospital and emergency department settings, radiologists interpreted 6499 (99.2%) and nonradiologists 51 (0.8%). Of the examinations on the most clinically complex patients (CCI ≥ 3), radiologists interpreted 4228 (90.2%) and nonradiologists 461 (9.8%). All interspecialty differences were statistically significant (p < 0.001)., Conclusion: In the Medicare population, radiologists interpret most lower extremity joint MRI examinations. Compared with nonradiologists, radiologists disproportionately provide services on weekends, in the highest acuity settings, and on the most clinically complex patients. To promote patient access and minimize disparities, future pay-for-performance metrics should consider temporal, acuity, and complexity parameters.

Objective: Endovascular stenting is a safe, effective treatment of hepatic artery stenosis after liver transplant, but no detailed evaluation has been completed of changes in ultrasound monitoring parameters after stenting. This study aims to improve poststenting surveillance by delineating the expected postoperative findings., Materials and Methods: Thirty-one stent procedures were performed at our institution for hepatic artery stenosis after liver transplant between October 2010 and October 2012. Of these, 28 (90%) were technically successful, of which 23 met the minimum follow-up time (76 days, defined by the earliest diagnosed restenosis). These patients were followed with serial ultrasound, per the following schedule: within 1 week of stenting, 3 months after stenting, 6 months after stenting, and every 6 months thereafter; additional, unscheduled examinations were frequently performed when indicated on the basis of deterioration of clinical and laboratory status. Follow-up examinations (mean, 268 days total follow-up) were compared with prestenting examinations to evaluate changes in peak systolic velocity (PSV), resistive index (RI), and tardus-parvus waveforms. Data were analyzed to determine a normal range for postprocedure values and time course of change in values., Results: Of the 23 patients, six experienced restenosis. In all patients, mean PSV decreased by 124 cm/s, and mean RI increased by 0.13 within 48 hours after stenting. PSV differed between patency and restenosis groups only at more than 90 days after stenting (mean PSV, 234 and 400 cm/s, respectively), with PSV above 300 cm/s serving as a high-sensitivity threshold for the determination of restenosis. Prestenting RI of below 0.40 had a strong correlation with restenosis. Poststenting RI differed between patency and restenosis groups only at more than 48 hours after stenting, with RI of below 0.55 having a strong correlation with restenosis. Tardus-parvus waveform resolution was often delayed well beyond 48 hours after stenting, and time to tardus-parvus waveform resolution had no correlation with patency or restenosis., Conclusion: Ultrasound is convenient and useful to follow stents in hepatic artery stenosis after liver transplant. Prestenting hemodynamics can have value in predicting restenosis. Diagnosis of restenosis can be made with RI and PSV, whereas resolution time of tardus-parvus waveform is of less concern. These parameters can guide which patients require closer monitoring and aggressive treatment.