Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials.

Prostate cancer is the most frequent cancer in men and a leading cause of cancer death. Determining a patient's optimal therapy is a challenge, where oncologists must select a therapy with the highest likelihood of success and the lowest likelihood of toxicity. International standards for prognostication rely on non-specific and semi-quantitative tools, commonly leading to over- and under-treatment. Tissue-based molecular biomarkers have attempted to address this, but most have limited validation in prospective randomized trials and expensive processing costs, posing substantial barriers to widespread adoption. There remains a significant need for accurate and scalable tools to support therapy personalization. Here we demonstrate prostate cancer therapy personalization by predicting long-term, clinically relevant outcomes using a multimodal deep learning architecture and train models using clinical data and digital histopathology from prostate biopsies. We train and validate models using five phase III randomized trials conducted across hundreds of clinical centers. Histopathological data was available for 5654 of 7764 randomized patients (71%) with a median follow-up of 11.4 years. Compared to the most common risk-stratification tool-risk groups developed by the National Cancer Center Network (NCCN)-our models have superior discriminatory performance across all endpoints, ranging from 9.2% to 14.6% relative improvement in a held-out validation set. This artificial intelligence-based tool improves prognostication over standard tools and allows oncologists to computationally predict the likeliest outcomes of specific patients to determine optimal treatment. Outfitted with digital scanners and internet access, any clinic could offer such capabilities, enabling global access to therapy personalization.

AI recognition of patient race in medical imaging: a modelling study.

BACKGROUND: Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images. METHODS: Using private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race. FINDINGS: In our study, we show that standard AI deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities, which was sustained under external validation conditions (x-ray imaging [area under the receiver operating characteristics curve (AUC) range 0·91-0·99], CT chest imaging [0·87-0·96], and mammography [0·81]). We also showed that this detection is not due to proxies or imaging-related surrogate covariates for race (eg, performance of possible confounders: body-mass index [AUC 0·55], disease distribution [0·61], and breast density [0·61]). Finally, we provide evidence to show that the ability of AI deep learning models persisted over all anatomical regions and frequency spectrums of the images, suggesting the efforts to control this behaviour when it is undesirable will be challenging and demand further study. INTERPRETATION: The results from our study emphasise that the ability of AI deep learning models to predict self-reported race is itself not the issue of importance. However, our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images, often when clinical experts cannot, creates an enormous risk for all model deployments in medical imaging. FUNDING: National Institute of Biomedical Imaging and Bioengineering, MIDRC grant of National Institutes of Health, US National Science Foundation, National Library of Medicine of the National Institutes of Health, and Taiwan Ministry of Science and Technology.

High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep Learning.

IMPORTANCE: Early detection and characterization of increased left ventricular (LV) wall thickness can markedly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating causes of increased wall thickness, such as hypertrophy, cardiomyopathy, and cardiac amyloidosis. OBJECTIVE: To assess the accuracy of a deep learning workflow in quantifying ventricular hypertrophy and predicting the cause of increased LV wall thickness. DESIGN, SETTINGS, AND PARTICIPANTS: This cohort study included physician-curated cohorts from the Stanford Amyloid Center and Cedars-Sinai Medical Center (CSMC) Advanced Heart Disease Clinic for cardiac amyloidosis and the Stanford Center for Inherited Cardiovascular Disease and the CSMC Hypertrophic Cardiomyopathy Clinic for hypertrophic cardiomyopathy from January 1, 2008, to December 31, 2020. The deep learning algorithm was trained and tested on retrospectively obtained independent echocardiogram videos from Stanford Healthcare, CSMC, and the Unity Imaging Collaborative. MAIN OUTCOMES AND MEASURES: The main outcome was the accuracy of the deep learning algorithm in measuring left ventricular dimensions and identifying patients with increased LV wall thickness diagnosed with hypertrophic cardiomyopathy and cardiac amyloidosis. RESULTS: The study included 23 745 patients: 12 001 from Stanford Health Care (6509 [54.2%] female; mean [SD] age, 61.6 [17.4] years) and 1309 from CSMC (808 [61.7%] female; mean [SD] age, 62.8 [17.2] years) with parasternal long-axis videos and 8084 from Stanford Health Care (4201 [54.0%] female; mean [SD] age, 69.1 [16.8] years) and 2351 from CSMS (6509 [54.2%] female; mean [SD] age, 69.6 [14.7] years) with apical 4-chamber videos. The deep learning algorithm accurately measured intraventricular wall thickness (mean absolute error [MAE], 1.2 mm; 95% CI, 1.1-1.3 mm), LV diameter (MAE, 2.4 mm; 95% CI, 2.2-2.6 mm), and posterior wall thickness (MAE, 1.4 mm; 95% CI, 1.2-1.5 mm) and classified cardiac amyloidosis (area under the curve [AUC], 0.83) and hypertrophic cardiomyopathy (AUC, 0.98) separately from other causes of LV hypertrophy. In external data sets from independent domestic and international health care systems, the deep learning algorithm accurately quantified ventricular parameters (domestic: R2, 0.96; international: R2, 0.90). For the domestic data set, the MAE was 1.7 mm (95% CI, 1.6-1.8 mm) for intraventricular septum thickness, 3.8 mm (95% CI, 3.5-4.0 mm) for LV internal dimension, and 1.8 mm (95% CI, 1.7-2.0 mm) for LV posterior wall thickness. For the international data set, the MAE was 1.7 mm (95% CI, 1.5-2.0 mm) for intraventricular septum thickness, 2.9 mm (95% CI, 2.4-3.3 mm) for LV internal dimension, and 2.3 mm (95% CI, 1.9-2.7 mm) for LV posterior wall thickness. The deep learning algorithm accurately detected cardiac amyloidosis (AUC, 0.79) and hypertrophic cardiomyopathy (AUC, 0.89) in the domestic external validation site. CONCLUSIONS AND RELEVANCE: In this cohort study, the deep learning model accurately identified subtle changes in LV wall geometric measurements and the causes of hypertrophy. Unlike with human experts, the deep learning workflow is fully automated, allowing for reproducible, precise measurements, and may provide a foundation for precision diagnosis of cardiac hypertrophy.

Pediatric Hepatoblastoma, Hepatocellular Carcinoma, and Other Hepatic Neoplasms: Consensus Imaging Recommendations from American College of Radiology Pediatric Liver Reporting and Data System (LI-RADS) Working Group.

Appropriate imaging is imperative in evaluating children with a primary hepatic malignancy such as hepatoblastoma or hepatocellular carcinoma. For use in the adult patient population, the American College of Radiology created the Liver Imaging Reporting and Data System (LI-RADS) to provide consistent terminology and to improve imaging interpretation. At present, no similar consensus exists to guide imaging and interpretation of pediatric patients at risk for developing a liver neoplasm or how best to evaluate a pediatric patient with a known liver neoplasm. Therefore, a new Pediatric Working Group within American College of Radiology LI-RADS was created to provide consensus for imaging recommendations and interpretation of pediatric liver neoplasms. The article was drafted based on the most up-to-date existing information as interpreted by imaging experts comprising the Pediatric LI-RADS Working Group. Guidance is provided regarding appropriate imaging modalities and protocols, as well as imaging interpretation and reporting, with the goals to improve imaging quality, to decrease image interpretation errors, to enhance communication with referrers, and to advance patient care. An expanded version of this document that includes broader background information on pediatric hepatocellular carcinoma and rationale for recommendations can be found in Appendix E1 (online).

Deep learning to automate Brasfield chest radiographic scoring for cystic fibrosis.

BACKGROUND: The aim of this study was to evaluate the hypothesis that a deep convolutional neural network (DCNN) model could facilitate automated Brasfield scoring of chest radiographs (CXRs) for patients with cystic fibrosis (CF), performing similarly to a pediatric radiologist. METHODS: All frontal/lateral chest radiographs (2058 exams) performed in CF patients at a single institution from January 2008-2018 were retrospectively identified, and ground-truth Brasfield scoring performed by a board-certified pediatric radiologist. 1858 exams (90.3%) were used to train and validate the DCNN model, while 200 exams (9.7%) were reserved for a test set. Five board-certified pediatric radiologists independently scored the test set according to the Brasfield method. DCNN model vs. radiologist performance was compared using Spearman correlation (ρ) as well as mean difference (MD), mean absolute difference (MAD), and root mean squared error (RMSE) estimation. RESULTS: For the total Brasfield score, ρ for the model-derived results computed pairwise with each radiologist's scores ranged from 0.79-0.83, compared to 0.85-0.90 for radiologist vs. radiologist scores. The MD between model estimates of the total Brasfield score and the average score of radiologists was -0.09. Based on MD, MAD, and RMSE, the model matched or exceeded radiologist performance for all subfeatures except air-trapping and large lesions. CONCLUSIONS: A DCNN model is promising for predicting CF Brasfield scores with accuracy similar to that of a pediatric radiologist.

Technical Feasibility and Clinical Effectiveness of Transjugular Intrahepatic Portosystemic Shunt Creation in Pediatric and Adolescent Patients.

PURPOSE: To examine the technical feasibility and clinical efficacy of transjugular intrahepatic portosystemic shunt (TIPS) creation in children and adolescents. MATERIALS AND METHODS: Retrospective review was performed of 59 patients (mean age 12.6 y [range, 1.5-20 y], mean weight 47.5 kg [range, 11.4-112.2 kg], mean Model for End-stage Liver Disease/Pediatric End-stage Liver Disease score 12.5 [range, 6-33]) who underwent 61 TIPS attempts at 3 tertiary children's hospitals from 2001 to 2017 for acute esophageal or gastroesophageal variceal bleeding, primary and secondary prevention of variceal bleeding, and refractory ascites. Pediatric liver disease etiologies included biliary atresia, cystic fibrosis, and ductal plate anomalies. Technical, hemodynamic, and clinical success and patency rates were reported at 1, 6, 12, and 24 months. Statistical analysis evaluated reasons for clinical failure. Kaplan-Meier analysis measured clinical success, patency, and transplant-free survival. RESULTS: Technical success was 93.4% (57/61) in 59 consecutive patients. Most common TIPS indications were treating and preventing esophageal and gastroesophageal variceal bleeding (57/59; 96.6%). Hemodynamic success was 94% (47/50). Clinical success was 80.7% (45/56). Two-year clinical success for acute variceal bleeding and ascites was 94.1% and 100%, respectively. Overall patency at 1, 6, 12, and 24 months was 98.0%, 97.8%, 94.3%, and 91.3%. Two-year transplant-free survival was 88.8%. Overall and major complication rates were 21.2% (13/61) and 8.2% (5/61), with 3 mortalities. Gradient reduction < 12 mm Hg correlated with clinical success (P < .01). CONCLUSIONS: TIPS creation in pediatric patients is technically feasible and clinically efficacious for treatment and prevention of esophageal and gastroesophageal variceal hemorrhage. High 2-year clinical success, patency, and survival rates should encourage providers to consider portosystemic shunts as a bridge to liver transplantation.

Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists.

BACKGROUND: Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists. METHODS AND FINDINGS: We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4-28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863-0.910), 0.911 (95% CI 0.866-0.947), and 0.985 (95% CI 0.974-0.991), respectively, whereas CheXNeXt's AUCs were 0.831 (95% CI 0.790-0.870), 0.704 (95% CI 0.567-0.833), and 0.851 (95% CI 0.785-0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825-0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777-0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution. CONCLUSIONS: In this study, we developed and validated a deep learning algorithm that classified clinically important abnormalities in chest radiographs at a performance level comparable to practicing radiologists. Once tested prospectively in clinical settings, the algorithm could have the potential to expand patient access to chest radiograph diagnostics.

Albumin-Bilirubin Score: An Accurate Predictor of Hepatic Decompensation in High-Risk Patients Undergoing Transarterial Chemoembolization for Hepatocellular Carcinoma.

PURPOSE: To evaluate validity of albumin-bilirubin (ALBI) grade as a predictor of acute-on-chronic liver failure (ACLF) after transarterial chemoembolization for hepatocellular carcinoma (HCC) in patients with baseline moderate to severe liver dysfunction. MATERIALS AND METHODS: In this retrospective study, serum albumin and bilirubin levels measured before chemoembolization were used to calculate ALBI score in 123 patients treated with 187 high-risk chemoembolizations. Procedures were considered high risk if Child-Turcotte-Pugh score before chemoembolization was ≥ 8. ACLF was objectively measured using chronic liver failure-sequential organ failure assessment score at 30 and 90 d. The 30-day mortality and morbidity from new or worsening ascites and/or hepatic encephalopathy (HE) were assessed. Univariate and multivariate analyses were used to identify clinical and procedural predictors of ACLF in this high-risk population. RESULTS: ACLF occurred after 15 (8%) high-risk chemoembolizations within 30 days and an additional 9 (5%) procedures between 30 and 90 days. Overall 30-day mortality was 2.7%. New or worsened ascites and/or HE occurred after 52 (28%) procedures within 30 days. Significant prognosticators of ACLF at 90 days revealed by univariate analysis were bilirubin (P = .004), albumin (P = .007), and ALBI score (P = .002), with ALBI score remaining statistically significant on multivariate regression analysis (OR = 3.99; 95% CI, 1.70-9.40; P = .002). CONCLUSIONS: Chemoembolization for HCC can be performed safely in patients with moderate to severe liver dysfunction. ALBI score before chemoembolization provides objective prognostication for ACLF after chemoembolization in this cohort and may be used for risk stratification.

Transarterial chemoembolization in children to treat unresectable hepatocellular carcinoma.

Children with unresectable HCC have a dismal prognosis and few approved treatment options. TACE is an effective treatment option for adults with HCC, but experience in children is very limited. Retrospective analysis was performed of 8 patients aged 4-17 years (4 male, mean 12.5 years) who underwent TACE for unresectable HCC. Response to TACE was evaluated by change in AFP, RECIST and tumor volume, PRETEXT, and transplantation eligibility by UCSF and Milan criteria. Post-procedure mean follow-up was 8.2 years. Mean overall change in tumor volume for the 8 patients was 51%. Percent change in AFP ranged from a decrease of 100% to an increase of 89.3%, with a mean change of -49.6%. Two patients did not undergo resection or transplantation and died of progressive disease. Six patients underwent orthotopic liver transplantation with mean first TACE-to-transplant interval of 141 days (range 11-514). Following transplantation, 5 patients were alive at the end of the follow-up period and one died of recurrent disease. Based on our initial experience, TACE for children with unresectable HCC appears to be a safe and effective method for managing hepatic tumor burden and for downstaging and bridging to liver transplantation.

Comparison of Transjugular Liver Biopsy and Percutaneous Liver Biopsy With Tract Embolization in Pediatric Patients.

PURPOSE: The aim of the study was to compare safety and efficacy of transjugular liver biopsy (TJLB) and percutaneous liver biopsy (PLB) with tract embolization in pediatric patients with liver disease. MATERIALS AND METHODS: TJLB and PLB between December 2009 and October 2015 were retrospectively reviewed. Primary endpoints were adequate sampling and complication rate. Patient age, weight, coagulation factors, ascites, blood transfusions, adequacy of biopsy sample, number of biopsy samples, and complications were compared. RESULTS: There were 39 TJLB (average age 10.6 years) and 120 PLB (average age 7.1 years) (P value <0.05). Average weight was 40.2 kg for TJLB and 26.8 kg for PLB (P value <0.05). Average platelets were 155 for TJLB and 252 for PLB (P value <0.05). Average international normalized ratio was 1.7 for TJLB and 1.3 for PLB (P value <0.05). Mean postbiopsy hematocrit decrease was 0.8 and 0.9, for TJLB and PLB, respectively. Mean postbiopsy hemoglobin decrease was 0.3 in both groups. Number of core biopsy samples was 4.5 and 4.3, for TJLB and PLB, respectively. There was 1 biopsy yielding insufficient sample in each group. TJLB had 1 (2.6%) complication of supraventricular tachycardia. PLB had 4 (3.3%) complications, with 1 hemoperitoneum, 1 hypotension, 1 patient with decreased hemoglobin, and 1 patient with bilious drainage from the biopsy site. CONCLUSIONS: TJLB and PLB with gelatin sponge pledget tract embolization are both safe and effective for the diagnosis of hepatic disease in pediatric patients. To avoid radiation, PLB may be considered as first-line approach in the pediatric population, even in the setting of coagulopathy.

Role of interventional radiology in managing pediatric liver tumors : Part 2: percutaneous interventions.

Hepatoblastoma and hepatocellular carcinoma (HCC) are the most common pediatric liver malignancies, with hepatoblastoma occurring more commonly in younger children and HCC occurring more commonly in older children and adolescents. Although surgical resection (including transplant when necessary) and systemic chemotherapy have improved overall survival rate for hepatoblastoma to approximately 80% from 30%, a number of children with this tumor type are not eligible for operative treatment. In contradistinction, pediatric HCC continues to carry a dismal prognosis with an overall 5-year survival rate of 30%. The Paediatric Hepatic International Tumour Trial (PHITT) is an international trial aimed at evaluating both existing and emerging oncologic therapies for primary pediatric liver tumors. Interventional radiology offers a number of minimally invasive procedures that aid in diagnosis and therapy of pediatric liver tumors. For diagnosis, the PHITT biopsy guidelines emphasize and recommend percutaneous image-guided tumor biopsy. Additionally, both percutaneous and endovascular procedures provide therapeutic alternatives that have been, to this point, only minimally utilized in the pediatric population. Specifically, percutaneous ablation offers a number of cytotoxic technologies that can potentially eradicate disease or downstage children with unresectable disease. Percutaneous portal vein embolization is an additional minimally invasive procedure that might be useful to induce remnant liver hypertrophy prior to extended liver resection in the setting of a primary liver tumor. PHITT offers an opportunity to collect data from children treated with these emerging therapeutic options across the world. The purpose of this manuscript is to describe the potential role of minimally invasive percutaneous transhepatic procedures, as well as review the existing data largely stemming from the adult HCC experience.

Role of interventional radiology in managing pediatric liver tumors : Part 1: Endovascular interventions.

Primary liver malignancies are rare in children. Hepatoblastoma and hepatocellular carcinoma (HCC) together represent the overwhelming majority of cases. Overall survival of hepatoblastoma approaches 80% with multimodal treatment approaches that include chemotherapy, surgery and transplantation. However, there remains a subset of children with hepatoblastoma in whom resection or transplantation is not possible. The 5-year survival for children diagnosed with HCC is less than 30% and remains a significant therapeutic challenge. The poor outcomes for children with primary liver tumors motivate investigation of new therapeutic alternatives. Interventional oncology offers a broad scope of percutaneous and transcatheter endovascular cancer therapies that might provide clinical benefits. Minimally invasive approaches are distinct from medical, surgical and radiation oncologic treatments, and in adults these approaches have been established as the fourth pillar of cancer care. Transarterial chemoembolization is a minimally invasive locoregional treatment option performed by interventional radiologists with level-I evidence as standard of care in adults with advanced liver malignancy; transarterial chemoembolization in adults has served to prolong disease-free progression, downstage and bridge patients for surgical and transplant interventions, and improve overall survival. However, while several groups have reported that transarterial chemoembolization is feasible in children, the published experience is limited primarily to small retrospective case series. The lack of prospective trial evidence has in part limited the utilization of transarterial chemoembolization in the pediatric patient population. The purpose of this article is to provide an overview of the role of interventional radiology in the diagnosis and endovascular management of hepatic malignancies in children.

Stereotactic body radiotherapy for pediatric hepatocellular carcinoma with central biliary obstruction.

Here, we present the case of a pediatric patient with newly diagnosed hepatocellular carcinoma causing central biliary obstruction and persistently elevated bilirubin of 3.0-4.3 mg/dl despite placement of bilateral internal-external biliary drains. The tumor was not resectable, and the patient was not a candidate for liver transplant due to nodal disease, for chemotherapy due to hyperbilirubinemia, or for local therapies aside from stereotactic body radiotherapy (SBRT). In this report, we discuss the successful use of SBRT in the management of this patient, and its role in allowing the patient to become a candidate for additional therapies.

Ultrasound-Guided Liver Biopsy With Gelatin Sponge Pledget Tract Embolization in Infants Weighing Less Than 10 kg.

OBJECTIVES: The aim of the study was to describe and assess the technical success and safety of ultrasound-guided liver biopsy with gelatin sponge pledget tract embolization technique in infants <10 kg across 3 tertiary pediatric hospitals. MATERIALS AND METHODS: There were 67 pediatric patients weighing <10 kg (36 boys; 31 girls; average age 202 days; average weight 6 kg, range 1.5-9.9 kg) referred for liver biopsy performed with ultrasound guidance and gelatin sponge pledget tract embolization during a 2-year period. Patient history, procedural records, and clinical follow-up documents were retrospectively reviewed. RESULTS: A total of 67 procedures were included. There was 100% technical success rate and all samples obtained provided adequate tissue for histological assessment. Average number of 18 G biopsy passes was 3 (range 1-6). There were no procedure-related deaths. There was 1 complication (1%) in a 5-kg infant who was readmitted 36 hours after biopsy with a fever and fully recovered after antibiotics were administered. Biliary atresia was the most common underlying diagnosis (20%), whereas others included acute rejection (16%) and biliary obstruction (7%). CONCLUSIONS: Ultrasound-guided percutaneous liver biopsy with gelatin sponge pledget tract embolization technique in children weighing <10 kg is safe, effective, and use of this technique may lead to a reduction in rates of adverse events reported in other pediatric series.

Assessing the Risk of Hemorrhagic Complication following Transjugular Liver Biopsy in Bone Marrow Transplantation Recipients.

PURPOSE: To determine if recipients of bone marrow transplants (BMTs) are at increased risk of hemorrhagic complications following transjugular liver biopsy (TJLB). MATERIALS AND METHODS: TJLBs in BMT and non-BMT patients between January 2007 and July 2014 were reviewed. Patient demographic and pre- and postprocedural laboratory data were reviewed. Mean platelet count and International Normalized Ratio were 174,300 × 10(3)/µL ± 107.3 (standard deviation) and 1.2 ± 0.4, respectively, for BMT recipients, compared with 88,100 × 10(3)/µL ± 70.9 and 1.2 ± 0.5, respectively, for non-BMT. Patients in whom hemoglobin level decreased by > 1 g/dL and/or required transfusion within 15 days of TJLB were reviewed to determine the presence of a biopsy-related hemorrhagic complication. RESULTS: A total of 1,600 TJLBs in 1,120 patients were analyzed. Of these, 183 TJLBs in 159 BMT recipients and 1,417 TJLBs in 961 patients non-BMT patients were performed. Thirteen TJLBs were complicated by hemorrhage: five in BMT (2.9%) and eight in the non-BMT cohorts (0.6%; P < .01). Preprocedural platelet counts were within normal range (57-268 × 10(3)/µL) in all but one patient (8 × 10(3)/µL). BMT recipients had an odds ratio of 4.9 (95% confidence interval, 1.25-17.3) for post-TJLB bleeding/hemorrhage compared with those without BMTs (P < .01). CONCLUSIONS: TJLB continues to be a safe procedure in the vast majority of patients. However, hemorrhagic complications occurred at a rate of 2.9% in BMT recipients, compared with 0.6% in patients without BMTs, and therefore caution should be exercised when performing TJLB in this group.

Isolated Upper Extremity Posttransplant Lymphoproliferative Disorder in a Child.

Posttransplant lymphoproliferative disorder (PTLD) is a well-described complication of solid organ and bone marrow transplants. The most common presentation is intra-abdominal lymphadenopathy or single or multiple intraparenchymal masses involving the liver, spleen, or kidneys. Here we describe the imaging and pathology findings of an unusual case of PTLD appearing as an intramuscular forearm lesion in a pediatric male. The manifestation of PTLD as an isolated upper extremity mass in a pediatric patient has to our knowledge not been described.