Training robust T1-weighted magnetic resonance imaging liver segmentation models using ensembles of datasets with different contrast protocols and liver disease etiologies.

Image segmentation of the liver is an important step in treatment planning for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a generalizable deep learning model to segment the liver on T1-weighted MR images. In particular, three distinct deep learning architectures (nnUNet, PocketNet, Swin UNETR) were considered using data gathered from six geographically different institutions. A total of 819 T1-weighted MR images were gathered from both public and internal sources. Our experiments compared each architecture's testing performance when trained both intra-institutionally and inter-institutionally. Models trained using nnUNet and its PocketNet variant achieved mean Dice-Sorensen similarity coefficients>0.9 on both intra- and inter-institutional test set data. The performance of these models suggests that nnUNet and PocketNet liver segmentation models trained on a large and diverse collection of T1-weighted MR images would on average achieve good intra-institutional segmentation performance.

Metabolomics biomarkers of hepatocellular carcinoma in a prospective cohort of patients with cirrhosis.

Background & Aims: The effectiveness of surveillance for hepatocellular carcinoma (HCC) in patients with cirrhosis is limited, due to inadequate risk stratification and suboptimal performance of current screening modalities. Methods: We developed a multicenter prospective cohort of patients with cirrhosis undergoing surveillance with MRI and applied global untargeted metabolomics to 612 longitudinal serum samples from 203 patients. Among them, 37 developed HCC during follow-up. Results: We identified 150 metabolites with significant abundance changes in samples collected prior to HCC (Cases) compared to samples from patients who did not develop HCC (Controls). Tauro-conjugated bile acids and gamma-glutamyl amino acids were increased, while acyl-cholines and deoxycholate derivatives were decreased. Seven amino acids including serine and alanine had strong associations with HCC risk, while strong protective effects were observed for N-acetylglycine and glycerophosphorylcholine. Machine learning using the 150 metabolites, age, gender, and PNPLA3 and TMS6SF2 single nucleotide polymorphisms, identified 15 variables giving optimal performance. Among them, N-acetylglycine had the highest AUC in discriminating Cases and Controls. When restricting Cases to samples collected within 1 year prior to HCC (Cases-12M), additional metabolites including microbiota-derived metabolites were identified. The combination of the top six variables identified by machine learning (alpha-fetoprotein, 6-bromotryptophan, N-acetylglycine, salicyluric glucuronide, testosterone sulfate and age) had good performance in discriminating Cases-12M from Controls (AUC 0.88, 95% CI 0.83-0.93). Finally, 23 metabolites distinguished Cases with LI-RADS-3 lesions from Controls with LI-RADS-3 lesions, with reduced abundance of acyl-cholines and glycerophosphorylcholine-related lysophospholipids in Cases. Conclusions: This study identified N-acetylglycine, amino acids, bile acids and choline-derived metabolites as biomarkers of HCC risk, and microbiota-derived metabolites as contributors to HCC development. Impact and implications: The effectiveness of surveillance for hepatocellular carcinoma (HCC) in patients with cirrhosis is limited. There is an urgent need for improvement in risk stratification and new screening modalities, particularly blood biomarkers. Longitudinal collection of paired blood samples and MRI images from patients with cirrhosis is particularly valuable in assessing how early blood and imaging markers become positive during the period when lesions are observed to obtain a diagnosis of HCC. We generated a multicenter prospective cohort of patients with cirrhosis under surveillance with contrast MRI, applied untargeted metabolomics on 612 serum samples from 203 patients and identified metabolites associated with risk of HCC development. Such biomarkers may significantly improve early-stage HCC detection for patients with cirrhosis undergoing HCC surveillance, a critical step to increasing curative treatment opportunities and reducing mortality.

Training Robust T1-Weighted Magnetic Resonance Imaging Liver Segmentation Models Using Ensembles of Datasets with Different Contrast Protocols and Liver Disease Etiologies.

Image segmentation of the liver is an important step in several treatments for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a deep learning model to segment the liver on T1w MR images. We sought to determine the best architecture by training, validating, and testing three different deep learning architectures using a total of 819 T1w MR images gathered from six different datasets, both publicly and internally available. Our experiments compared each architecture's testing performance when trained on data from the same dataset via 5-fold cross validation to its testing performance when trained on all other datasets. Models trained using nnUNet achieved mean Dice-Sorensen similarity coefficients > 90% when tested on each of the six datasets individually. The performance of these models suggests that an nnUNet liver segmentation model trained on a large and diverse collection of T1w MR images would be robust to potential changes in contrast protocol and disease etiology.

Single-center Outcomes After Liver Transplantation With SARS-CoV-2-Positive Donors: An Argument for Increased Utilization.

Background: The COVID-19 pandemic has led to an increase in SARS-CoV-2-test positive potential organ donors. The benefits of life-saving liver transplantation (LT) must be balanced against the potential risk of donor-derived viral transmission. Although emerging evidence suggests that the use of COVID-19-positive donor organs may be safe, granular series thoroughly evaluating safety are still needed. Results of 29 consecutive LTs from COVID-19-positive donors at a single center are presented here. Methods: A retrospective cohort study of LT recipients between April 2020 and December 2022 was conducted. Differences between recipients of COVID-19-positive (n = 29 total; 25 index, 4 redo) and COVID-19-negative (n = 472 total; 454 index, 18 redo) deceased donor liver grafts were compared. Results: COVID-19-positive donors were significantly younger (P = 0.04) and had lower kidney donor profile indices (P = 0.04) than COVID-19-negative donors. Recipients of COVID-19-positive donor grafts were older (P = 0.04) but otherwise similar to recipients of negative donors. Donor SARS-CoV-2 infection status was not associated with a overall survival of recipients (hazard ratio, 1.11; 95% confidence interval, 0.24-5.04; P = 0.89). There were 3 deaths among recipients of liver grafts from COVID-19-positive donors. No death seemed virally mediated because there was no qualitative association with peri-LT antispike antibody titers, post-LT prophylaxis, or SARS-CoV-2 variants. Conclusions: The utilization of liver grafts from COVID-19-positive donors was not associated with a decreased overall survival of recipients. There was no suggestion of viral transmission from donor to recipient. The results from this large single-center study suggest that COVID-19-positive donors may be used safely to expand the deceased donor pool.

Mastocytosis-A Review of Disease Spectrum with Imaging Correlation.

Mastocytosis is a rare disorder due to the abnormal proliferation of clonal mast cells. Mast cells exist in most tissues, mature in situ from hematopoietic stem cells and develop unique characteristics of local effector cells. Mastocytosis develops by activation mutation of the KIT surface receptor which is involved in the proliferation of a number of cell lines such as mast cells, germ cells, melanocytes, and hematopoietic cells. It manifests as two main categories: cutaneous mastocytosis and systemic mastocytosis. Imaging can play an important role in detection and characterization of the disease manifestation, not only by radiography and bone scans, but also magnetic resonance imaging and computed tomography, which can be more sensitive in the assessment of distinctive disease patterns. Radiologists should be aware of various appearances of this disease to better facilitate diagnosis and patient management. Accordingly, this review will discuss the clinical presentation, pathophysiology, and role of imaging in detection and extent estimation of the systemic involvement of the disease, in addition to demonstration of appearance on varying imaging modalities. Familiarity with the potential imaging findings associated with mastocytosis can aid in early disease diagnosis and classification and accordingly can lead directing further work up and better management.

PTEN Hamartoma Tumor Syndrome/Cowden Syndrome: Genomics, Oncogenesis, and Imaging Review for Associated Lesions and Malignancy.

PTEN hamartoma tumor syndrome/Cowden syndrome (CS) is a rare autosomal dominant syndrome containing a germline PTEN mutation that leads to the development of multisystem hamartomas and oncogenesis. Benign tumors such as Lhermitte-Duclos disease and malignant tumors involving the breast, thyroid, kidneys, and uterus are seen in CS. Radiologists have an integral role in the comanagement of CS patients. We present the associated imaging findings and imaging screening recommendations. Knowledge of the types of cancers commonly seen in CS and their imaging findings can aid in early tumor recognition during cancer screening to help ensure near-normal life spans in CS patients.

Betrixaban for first-line venous thromboembolism prevention in acute medically ill patients with risk factors for venous thromboembolism.

INTRODUCTION: Compared to other direct oral anticoagulants, betrixaban has a longer half-life, smaller peak-trough variance, minimal renal clearance, and minimal hepatic Cytochrome P (CYP) metabolism. The Acute Medically Ill VTE Prevention with Extended Duration Betrixaban (APEX) trial evaluated the efficacy and safety of extended duration betrixaban compared to standard duration enoxaparin in acutely ill hospitalized patients. Areas covered: This article describes the role of betrixaban in the prevention of venous thromboembolism (VTE) in acutely ill medical patients. This article provides a consolidated summary of the primary APEX study findings as well as prespecified and exploratory substudies. This article also provides a review of the results of studies in which other direct factor Xa inhibitors have been evaluated in an extended duration regimen in this patient population. Expert commentary: While previous agents have demonstrated that extended duration VTE prophylaxis can be efficacious, betrixaban is the first agent to demonstrate efficacy without an increase in major bleeding. The totality of the data from the APEX trial supports extended duration betrixaban for VTE prophylaxis in the acute medically ill patient population. As such, betrixaban has been approved in the USA for extended VTE prophylaxis in at-risk acute medically ill patients.