Bolan, Candice

Abstract Despite growing interest in AI for pancreatic cyst management, no prior study has systematically investigated how lesion characteristics influence model behavior or provided a comprehensive explainability analysis in IPMN malignancy risk stratification. We present the first multi-center study integrating explainable AI with uncertainty quantification to evaluate how cyst type, size, and location affect deep learning performance in IPMN malignancy prediction. Our retrospective study analyzed 170 IPMNs from seven centers using a radiomics-deep learning fusion model. Cases were stratified by dysplasia grade, IPMN type, size, and location; with model interpretability assessed using SHAP, LIME, Grad-CAM, and uncertainty quantification. Overall accuracy was 67.1%, with model uncertainty lower for correct versus incorrect predictions (0.72 vs 0.78, p < 0.001). On subgroup analysis: Low-Risk lesion accuracy exceeded High-Risk (81.3% vs. 42.9%, p < 0.001), BD accuracy was inversely correlated with cyst size while MD remained stable, and body and whole-pancreas cysts stratified more accurately than tail cysts (77.8%, 76.6% vs. 47.8%). AI models face significant, previously uncharacterized performance drops when evaluating complex high-risk IPMNs. Our study shows that integrating uncertainty quantification can successfully flag unreliable predictions, enabling a selective-prediction framework where clinicians can confidently rely on AI for low-risk, low-uncertainty lesions while deferring high-uncertainty cases to expert review.

Despite European colorectal liver metastases (CRLM) transplant trials having been performed entirely using deceased donor liver transplant (DDLT), there has been speculation about whether similar results can be achieved in the United States, given the lack of MELD score prioritization. A formal transplant protocol for unresectable CRLM was implemented in our center at the start of 2022 with the plan to utilize DDLT. Between 2022 and 2025, 86 patients with CRLM were referred to our program, and 19 patients underwent a formal transplant evaluation. Median time from listing until transplant was 31 days (range 3–115 d). Median allocation MELD was 8 (range 6–15). The donor livers were from DCDs, older donors, or National Share livers, which had been declined by all other centers. All but 2 of the cases underwent advanced perfusion. There were no cases of primary nonfunction, postreperfusion syndrome, acute kidney injury, hepatic artery thrombosis, or ischemic cholangiopathy. The length of stay for the median posttransplant was 5 days. Graft and patient survival were 100% at the time of maximal follow-up. Recurrence developed in 3 recipients (25.0%), 1 of whom was treated and has no evidence of disease. These findings support the viability of DDLT for CRLM using advanced perfusion, contingent on strict protocol adherence. Center-specific waitlist dynamics must inform the choice between DDLT and living donor liver transplant (LDLT).

Abstract Distinguishing high-risk intraductal papillary mucinous neoplasms (IPMNs), pancreatic cysts requiring surgery, from low-risk lesions remains a clinical challenge, often resulting in unnecessary procedures due to limited specificity of current methods. While radiomics and deep learning (DL) have been explored for pancreatic cancer, cyst-level malignancy risk stratification of IPMNs remains untapped. We conducted a multi-institutional study (seven centers, 359 T2W MRI images) to assess the feasibility of AI for predicting IPMN dysplasia grade using cyst-level image features. We developed and compared 2D and 3D radiomics-only, deep learning (DL)-only, and radiomics-DL fusion models, using expert radiologist scoring as a baseline reference. Model performance was evaluated using held-out test data. The radiomics-DL fusion model showed the highest discriminatory ability on the test set (AUC 0.692), outperforming the radiomics-only model (AUC 0.665). Expert accuracy varied widely (37.4%-66.7%). The fusion model integrating deep learning and radiomics features from routine T2W MRI (AUC: 0.692) demonstrates potential for objective, cyst-level risk stratification of IPMNs in a multi-center cohort, outperforming both radiomics-only models and expert radiologists. While performance requires improvement for standalone clinical use, this approach offers a scalable, non-invasive method to potentially improve diagnostic accuracy and reduce unnecessary surgical interventions.

Background. With donation after circulatory death (DCD) liver transplantation (LT), the goal of the recipient implantation procedure is to minimize surgical complexity to avoid a tenuous environment for an already marginal graft. The presence of portal vein thrombosis (PVT) at the time of LT adds surgical complexity, yet‚ to date, no studies have investigated the utilization of DCD liver grafts for patients with PVT. Methods. All DCD LT performed at Mayo Clinic-Florida, Mayo Clinic-Arizona, and Mayo Clinic-Rochester from 2006 to 2020 were reviewed (N = 771). Patients with PVT at the time of transplant were graded using Yerdel classification. A 1:3 propensity match between patients with PVT and those without PVT was performed. Results. A total of 91 (11.8%) patients with PVT undergoing DCD LT were identified. Grade I PVT was present in 62.6% of patients, grade II PVT in 27.5%, grade III in 8.8%, and grade 4 in 1.1%. At the time of LT, thromboendovenectomy was performed in 89 cases (97.8%). There was no difference in the rates of early allograft dysfunction (43.2% versus 52.4%; P = 0.13) or primary nonfunction (1.1% versus 1.1%; P = 0.41) between the DCD PVT and DCD without PVT groups, respectively. The rate of ischemic cholangiopathy was not significantly different between the DCD PVT (11.0%) and DCD without PVT groups (10.6%; P = 0.92). Graft (P = 0.58) and patient survival (P = 0.08) were similar between the 2 groups. Graft survival at 1-, 3-, and 5-y was 89.9%, 84.5%, and 79.3% in the DCD PVT group. Conclusions. In appropriately selected recipients with grades I–II PVT, DCD liver grafts can be utilized safely with excellent outcomes.

Cystic fibrosis (CF) is an autosomal recessive disease characterized by mutations in the gene that encodes for the cystic fibrosis transmembrane conductance regulator protein (CFTR). CFTR gene mutations manifest as epithelial cell dysfunction in the airways, biliary tract, pancreas, gut, sweat glands, paranasal sinuses, and genitourinary tract. The clinical manifestations of this dysfunction include respiratory tract infections, bronchiectasis, pancreatic insufficiency, malabsorption, intestinal obstruction, liver disease, and male infertility. The liver disease manifestations of CF can include biliary disease, multilobular cirrhosis, and portal hypertension with and without cirrhosis. Pulmonary disease is the main cause for morbidity and mortality in individuals with CF, and according to the International Society for Heart and Lung Transplantation, CF is the third most common indication for lung transplantation in adults, accounting for 16% of procedures performed. The survival after lung transplantation in individuals with CF continues to improve and is now the highest among end‐stage lung diseases requiring transplant. The survival rate at 10 years is close to 50%. Given the potential presence of liver disease in CF patients undergoing an evaluation for lung transplantation and in lung transplant recipients, it is important to understand the manifestations of liver disease in CF patients and the recommended workup and follow‐up. This review aims to discuss the current literature and provide guidance in the management of these patients.

Background Venous congestion after deep inferior epigastric artery perforator (DIEP) flap breast reconstruction is a complication that may be partially attributable to variations in venous abdominal wall anatomy. In previous work, we have shown that ferumoxytol may be used as a bloodpool contrast agent to perform high-resolution venous imaging. Our current aim was to use this technology to perform a detailed analysis of the venous anatomy among patients undergoing DIEP flap breast reconstruction. Methods All patients undergoing DIEP flap reconstruction with preoperative ferumoxytol-enhanced magnetic resonance angiography (FE-MRA) were retrospectively reviewed. A detailed anatomic analysis of each abdominal wall on FE-MRAwas performed before review of operative findings. Statistical analysis was used to determine venous characteristics associated with superficial inferior epigastric vein (SIEV) augmentation. Results From 2012 to 2016, 59 patients underwent preoperative FE-MRA. This resulted in imaging for 118 hemiabdomen and 99 flaps. Superficial-deep communication was identified in 117 of 118 hemiabdomen. Fifty (93%) of 59 patients had greater than 1-mm venous communication of the superficial system across midline. Reconstructed breasts were based on dominant medial row perforators in 82 (83%) of 99 flaps. The mean diameters of the SIEVand dominant venous perforator were 3.8 and 2.8mm, respectively. Anatomic characteristics associated with SIEVaugmentation included SIEVdiameter ( P = 0.01), dominant perforator diameter ( P = 0.04), and the ratio between these 2 variables ( P = 0.001). Conclusions Ferumoxytol-enhanced magnetic resonance angiography provides excellent imaging of the venous system. Anatomic characteristics such as the diameter of the SIEVand the diameter of the dominant perforator may be useful in determining which flaps require venous augmentation using the SIEV.