Citations

Importance Anhydramnios from fetal kidney failure causes lethal pulmonary hypoplasia. Serial amnioinfusions have shown promise in mitigating pulmonary disease from bilateral renal agenesis, but efficacy and safety for other causes of fetal kidney failure are unproven. Objective To assess the efficacy of serial amnioinfusions initiated before 26 weeks’ gestation to mitigate lethal pulmonary hypoplasia in cases of anhydramnios due to fetal kidney failure. Design, Setting, and Participants Prospective, nonrandomized clinical trial conducted at 13 US fetal therapy centers from December 2018 to February 2025. Outcomes for maternal-fetal pairs with anhydramnios before 22 weeks’ gestation due to fetal kidney failure without bilateral renal agenesis are reported; data collection for surviving infants continued until February 13, 2026. Exposure Thirty-two participants underwent serial amnioinfusions with isotonic fluid beginning before 26 weeks’ gestation. Main Outcomes and Measures The primary end point was neonatal survival for 14 days or longer with dialysis access placement. Secondary outcome measures of survival to discharge home and kidney transplant are reported. Results Twenty-nine of 32 participants (91%) had a live birth, with a median (IQR) gestational age at delivery of 34 weeks 1 day (31 weeks 5 days to 34 weeks 6 days). All participants delivered before 37 weeks’ gestation. No unexpected serious maternal adverse events occurred, and the most common maternal complications were preterm prelabor rupture of membranes in 19 participants (56%) and chorioamniotic separation in 10 (29%). The primary outcome occurred in 19 (65.5%) of 29 live-born neonates (95% CI, 45.7%-82.1%). Factors associated with survival to the primary outcome included receiving more amnioinfusions (median [IQR], 14 [9-18] in survivors vs 7 [4-11] in nonsurvivors; P = .01), longer time interval from first amnioinfusion to preterm prelabor rupture of membranes (63.5 [60.5-74.5] days in survivors vs 29.0 [22.0-56.0] days in nonsurvivors; P = .01), gestational age greater than 32 weeks (79% of survivors vs 38% of nonsurvivors; P = .03), and higher birth weight (2029 [1770-2250] g in survivors vs 1635 [1185-1915] g in nonsurvivors; P = .01). Fourteen live-born infants (48%) survived to hospital discharge at a median (IQR) age of 4.7 (3.4-5.7) months. Of the 11 infants surviving to date, 7 (64%) have undergone kidney transplant between ages 2 years to 5 years. Conclusions and Relevance Serial amnioinfusions mitigated lethal pulmonary hypoplasia in neonates with anhydramnios due to fetal kidney failure. Significant neonatal morbidity and mortality independent of early lung function was noted. Factors associated with survival were consistent with the Renal Anhydramnios Fetal Therapy trial’s bilateral renal agenesis cohort, suggesting common mechanistic pathways for mitigating pulmonary hypoplasia. Trial Registration ClinicalTrials.gov Identifier: NCT03101891

Abstract Medical imaging is undergoing a transformation driven by the advent of new, highly effective, machine learning techniques paired with increases in computational capabilities (Cheng et al. 2021; Gilson et al. 2023; Almeida et al. 2024; Krishna et al. 2024). These advanced algorithms have the potential to improve disease detection, diagnosis, prognosis, and treatment outcomes. However, the complexity of machine learning models, the large amounts of curated and annotated data required by some methods, and the potential for bias and error make it challenging for individuals to safely and effectively leverage these methods (Lin et al. 2024; Guo et al. 2024; Xu et al. 2024; Linguraru et al. 2024; Wood et al. 2019). To address these challenges, the American Association of Physicists in Medicine (AAPM), American College of Radiology (ACR), Radiological Society of North America (RSNA), and Society for Imaging Informatics in Medicine (SIIM) have worked together to develop a syllabus detailing a recommended set of competencies for medical imaging professionals interacting with these systems. This guide is aimed at four different personas: users of AI systems, purchasers of AI systems, individuals who provide clinical expertise during the development of AI systems (“clinical collaborators”), and developers of AI systems.1 This is a syllabus, not a curriculum, and is intentional in this scope. Recognizing that individuals may benefit from different presentations of the same material, this work enumerates a series of relevant competencies but does not prescribe, nor offer, a method of instruction (Schuur, Rezazade Mehrizi, and Ranschaert 2021; Garin et al. 2023). By addressing the task‐specific demands of each role, this guide will enable medical imaging professionals to utilize machine learning systems more safely and effectively, ultimately improving patient care and outcomes.

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.

ImportanceEarly anhydramnios during pregnancy, resulting from fetal bilateral renal agenesis, causes lethal pulmonary hypoplasia in neonates. Restoring amniotic fluid via serial amnioinfusions may promote lung development, enabling survival.ObjectiveTo assess neonatal outcomes of serial amnioinfusions initiated before 26 weeks’ gestation to mitigate lethal pulmonary hypoplasia.Design, Setting, and ParticipantsProspective, nonrandomized clinical trial conducted at 9 US fetal therapy centers between December 2018 and July 2022. Outcomes are reported for 21 maternal-fetal pairs with confirmed anhydramnios due to isolated fetal bilateral renal agenesis without other identified congenital anomalies.ExposureEnrolled participants initiated ultrasound-guided percutaneous amnioinfusions of isotonic fluid before 26 weeks’ gestation, with frequency of infusions individualized to maintain normal amniotic fluid levels for gestational age.Main Outcomes and MeasuresThe primary end point was postnatal infant survival to 14 days of life or longer with dialysis access placement.ResultsThe trial was stopped early based on an interim analysis of 18 maternal-fetal pairs given concern about neonatal morbidity and mortality beyond the primary end point despite demonstration of the efficacy of the intervention. There were 17 live births (94%), with a median gestational age at delivery of 32 weeks, 4 days (IQR, 32-34 weeks). All participants delivered prior to 37 weeks’ gestation. The primary outcome was achieved in 14 (82%) of 17 live-born infants (95% CI, 44%-99%). Factors associated with survival to the primary outcome included a higher number of amnioinfusions (P = .01), gestational age greater than 32 weeks (P = .005), and higher birth weight (P = .03). Only 6 (35%) of the 17 neonates born alive survived to hospital discharge while receiving peritoneal dialysis at a median age of 24 weeks of life (range, 12-32 weeks).Conclusions and RelevanceSerial amnioinfusions mitigated lethal pulmonary hypoplasia but were associated with preterm delivery. The lower rate of survival to discharge highlights the additional mortality burden independent of lung function. Additional long-term data are needed to fully characterize the outcomes in surviving neonates and assess the morbidity and mortality burden.Trial RegistrationClinicalTrials.gov Identifier: NCT03101891