Ihab R. Kamel

Abernethy malformation is a rare congenital extrahepatic mesocaval shunt (CEMS) in which mesenteric venous blood bypasses the liver completely (type I) or partially (type II) and drains directly into the vena cava. In complete CEMS (type I), the intrahepatic portal vein is absent. The resulting lack of portal flow is associated with the development of hepatic nodules, such as focal nodular hyperplasia (FNH), hepatocellular adenoma (HCA), and hepatocellular carcinoma (HCC). These lesions have a higher risk of malignant transformation than conventional adenomas. The term hepatocellular neoplasm of uncertain malignant potential (HUMP) has been proposed for borderline lesions between HCA and well‐differentiated HCC, diagnosed based on atypical histological, genetic, or clinical features suggesting a possible malignant potential. However, the exact risk of malignant transformation is unknown. We present the case of a 32‐year‐old man with Type I Abernethy malformation who developed malignant transformation of a HUMP over a 15‐year period. Serial hepatic resections performed at other institutions demonstrated histological progression from HUMP to HCC with subsequent lung metastasis. This gradual transformation has been documented in several surgical specimens. This case highlights the need for careful recognition of HUMP in patients with Abernethy malformation, as timely liver transplantation may be essential to prevent malignant transformation and achieve curative outcomes.

Critical retained foreign objects (RFOs), including surgical instruments like sponges and needles, pose serious patient safety risks and carry significant financial and legal implications for healthcare institutions. Detecting critical RFOs using artificial intelligence remains challenging due to their rarity and the limited availability of chest X-ray datasets that specifically feature critical RFOs cases. Existing datasets only contain non-critical RFOs, like necklace or zipper, further limiting their utility for developing clinically impactful detection algorithms. To address these limitations, we introduce "Hopkins RFOs Bench", the first and largest dataset of its kind, containing 144 chest X-ray images of critical RFO cases collected over 18 years from the Johns Hopkins Health System. Using this dataset, we benchmark several state-of-the-art object detection models, highlighting the need for enhanced detection methodologies for critical RFO cases. Recognizing data scarcity challenges, we further explore image synthetic methods to bridge this gap. We evaluate two advanced synthetic image methods, DeepDRR-RFO, a physics-based method, and RoentGen-RFO, a diffusion-based method, for creating realistic radiographs featuring critical RFOs. Our comprehensive analysis identifies the strengths and limitations of each synthetic method, providing insights into effectively utilizing synthetic data to enhance model training. The Hopkins RFOs Bench and our findings significantly advance the development of reliable, generalizable AI-driven solutions for detecting critical RFOs in clinical chest X-rays.

Background: Deep learning (DL) models for accurate renal tumor characterization may benefit from multi‐center datasets for improved generalizability; however, data‐sharing constraints necessitate privacy‐preserving solutions like federated learning (FL).Purpose: To assess the performance and reliability of FL for renal tumor segmentation and classification in multi‐institutional MRI datasets.Study Type: Retrospective multi‐center study.Population: A total of 987 patients (403 female) from six hospitals were included for analysis. 73% (723/987) had malignant renal tumors, primarily clear cell carcinoma (n = 509). Patients were split into training (n = 785), validation (n = 104), and test (n = 99) sets, stratified across three simulated institutions.Field Strength/Sequence: MRI was performed at 1.5 T and 3 T using T2‐weighted imaging (T2WI) and contrast‐enhanced T1‐weighted imaging (CE‐T1WI) sequences.Assessment: FL and non‐FL approaches used nnU‐Net for tumor segmentation and ResNet for its classification. FL‐trained models across three simulated institutional clients with central weight aggregation, while the non‐FL approach used centralized training on the full dataset.Statistical Tests: Segmentation was evaluated using Dice coefficients, and classification between malignant and benign lesions was assessed using accuracy, sensitivity, specificity, and area under the curves (AUCs). FL and non‐FL performance was compared using the Wilcoxon test for segmentation Dice and Delong's test for AUC (p < 0.05).Results: No significant difference was observed between FL and non‐FL models in segmentation (Dice: 0.43 vs. 0.45, p = 0.202) or classification (AUC: 0.69 vs. 0.64, p = 0.959) on the test set. For classification, no significant difference was observed between the models in accuracy (p = 0.912), sensitivity (p = 0.862), or specificity (p = 0.847) on the test set.Data Conclusion: FL demonstrated comparable performance to non‐FL approaches in renal tumor segmentation and classification, supporting its potential as a privacy‐preserving alternative for multi‐institutional DL models.Evidence Level: 4.Technical Efficacy: Stage 2.