Impact of easing COVID-19 safety measures on trauma computed tomography imaging volumes.

PURPOSE: The coronavirus disease 2019 (COVID-19) pandemic has led to substantial disruptions in healthcare staffing and operations. Stay-at-home (SAH) orders and limitations in social gathering implemented in spring 2020 were followed by initial decreases in healthcare and imaging utilization. This study aims to evaluate the impact of subsequent easing of SAH on trauma volumes, demand for, and turnaround times for trauma computed tomography (CT) exams, hypothesizing that after initial decreases, trauma volumes have increased as COVID safety measures have been reduced. METHODS: Patient characteristics, CT imaging volumes, and turnaround time were analyzed for all adult activated emergency department trauma patients requiring CT imaging at a single Level-I trauma center (1/2018-2/2022) located in the sixth most populous county in the USA. Based on COVID safety measures in place in the state of California, three time periods were compared: baseline (PRE, 1/1/2018-3/19/2020), COVID safety measures (COVID, 3/20/2020-1/25/2021), and POST (1/26/2021-2/28/2022). RESULTS: There were 16,984 trauma patients across the study (PRE = 8289, COVID = 3139, POST = 5556). The average daily trauma patient volumes increased significantly in the POST period compared to the PRE and COVID periods (13.9 vs. 10.3 vs. 10.1, p < 0.001), with increases in both blunt (p < 0.001) and penetrating (p = 0.002) trauma. The average daily number of trauma CT examinations performed increased significantly in the POST period compared to the PRE and COVID periods (56.7 vs. 48.3 vs. 47.6, p < 0.001), with significant increases in average turnaround time (47 min vs. 31 and 37, p < 0.001). CONCLUSION: After initial decreases in trauma radiology volumes following stay-at-home orders, subsequent easing of safety measures has coincided with increases in trauma imaging volumes above pre-pandemic levels and longer exam turnaround times.

Use of enfortumab vedotin in an HIV-positive patient with urothelial carcinoma.

INTRODUCTION: Enfortumab vedotin is an antibody-drug conjugate used in patients with pretreated advanced urothelial carcinoma. Patients with human immunodeficiency virus were excluded from clinical trials conducted with this agent. Efficacy and safety of enfortumab vedotin has not been established in this patient population. CASE REPORT: A patient with a long-standing diagnosis of human immunodeficiency virus and an undetectable viral load on antiretroviral therapy was diagnosed with metastatic upper tract urothelial carcinoma. Following disease progression on platinum-based chemotherapy and pembrolizumab, he was initiated on therapy with enfortumab vedotin. MANAGEMENT & OUTCOME: The patient developed significant toxicity shortly after initiation of enfortumab vedotin. His treatment was subsequently changed to docetaxel chemotherapy and he developed similar significant toxicity. Upon changing his antiretroviral therapy regimen, he was rechallenged with enfortumab vedotin and was able to tolerate it without dose-limiting toxicity, ultimately achieving a partial treatment response. DISCUSSION: This case describes use of enfortumab vedotin in a patient with human immunodeficiency virus, which has not previously been reported. It also underscores the importance of careful medication reconciliation in patients receiving enfortumab vedotin and antiretroviral therapy.

Comparison of Conventional and Triple Bolus Computerized Tomographic Urography Protocols for Radiation Dose Reduction in Hematuria Evaluation: A Randomized Controlled Trial.

PURPOSE: Computerized tomographic urography is the diagnostic tool of choice for evaluating hematuria. In keeping with the ALARA (As Low As Reasonably Achievable) principle, we evaluated a triple bolus computerized tomography protocol designed to reduce radiation exposure. MATERIALS AND METHODS: Patients with macroscopic or microscopic hematuria were prospectively randomized to conventional computerized tomography (100) or triple bolus computerized tomography (100). The triple bolus computerized tomography protocol entails 2 scans: pre-contrast scan followed by 3 contrast injections at 40 seconds, 60 seconds and 20 minutes prior to the second scan to capture all 3 phases. The conventional computerized tomography protocol requires 4 scans: pre-contrast scan, and 3 post-contrast scans at the corticomedullary, nephrographic and excretory phases. Radiation exposure and the detection of urological pathology were recorded based on radiology reports. RESULTS: There were no differences in patient demographics or body mass index between the 2 groups. Triple bolus computerized tomography exposed patients to 33% less radiation (1,715 vs 1,145 mGy*cm for conventional vs triple bolus computerized tomography; p <0.001). For macroscopic hematuria, the pathology detection rates were 70% for triple bolus and 73% for conventional computerized tomography (p=0.72). For microscopic hematuria, the detection rates were 59% for triple bolus and 50% for conventional computerized tomography (p=0.68). In both groups, the rates of detection of urolithiasis, renal cysts, urological masses, bladder pathology and prostate pathology were no different between triple bolus and conventional computerized tomography. CONCLUSIONS: In both the settings of macroscopic and microscopic hematuria evaluation, triple bolus computerized tomography significantly reduces radiation exposure while providing equivalent detection of genitourinary pathology compared to conventional computerized tomography. The ability to detect upper tract filling defects was not specifically tested.

A 3D-2D Hybrid U-Net Convolutional Neural Network Approach to Prostate Organ Segmentation of Multiparametric MRI.

OBJECTIVE: Prostate cancer is the most commonly diagnosed cancer in men in the United States with more than 200,000 new cases in 2018. Multiparametric MRI (mpMRI) is increasingly used for prostate cancer evaluation. Prostate organ segmentation is an essential step of surgical planning for prostate fusion biopsies. Deep learning convolutional neural networks (CNNs) are the predominant method of machine learning for medical image recognition. In this study, we describe a deep learning approach, a subset of artificial intelligence, for automatic localization and segmentation of prostates from mpMRI. MATERIALS AND METHODS: This retrospective study included patients who underwent prostate MRI and ultrasound-MRI fusion transrectal biopsy between September 2014 and December 2016. Axial T2-weighted images were manually segmented by two abdominal radiologists, which served as ground truth. These manually segmented images were used for training on a customized hybrid 3D-2D U-Net CNN architecture in a fivefold cross-validation paradigm for neural network training and validation. The Dice score, a measure of overlap between manually segmented and automatically derived segmentations, and Pearson linear correlation coefficient of prostate volume were used for statistical evaluation. RESULTS: The CNN was trained on 299 MRI examinations (total number of MR images = 7774) of 287 patients. The customized hybrid 3D-2D U-Net had a mean Dice score of 0.898 (range, 0.890-0.908) and a Pearson correlation coefficient for prostate volume of 0.974. CONCLUSION: A deep learning CNN can automatically segment the prostate organ from clinical MR images. Further studies should examine developing pattern recognition for lesion localization and quantification.

Variability of the Positive Predictive Value of PI-RADS for Prostate MRI across 26 Centers: Experience of the Society of Abdominal Radiology Prostate Cancer Disease-focused Panel.

Background Prostate MRI is used widely in clinical care for guiding tissue sampling, active surveillance, and staging. The Prostate Imaging Reporting and Data System (PI-RADS) helps provide a standardized probabilistic approach for identifying clinically significant prostate cancer. Despite widespread use, the variability in performance of prostate MRI across practices remains unknown. Purpose To estimate the positive predictive value (PPV) of PI-RADS for the detection of high-grade prostate cancer across imaging centers. Materials and Methods This retrospective cross-sectional study was compliant with the HIPAA. Twenty-six centers with members in the Society of Abdominal Radiology Prostate Cancer Disease-focused Panel submitted data from men with suspected or biopsy-proven untreated prostate cancer. MRI scans were obtained between January 2015 and April 2018. This was followed with targeted biopsy. Only men with at least one MRI lesion assigned a PI-RADS score of 2-5 were included. Outcome was prostate cancer with Gleason score (GS) greater than or equal to 3+4 (International Society of Urological Pathology grade group ≥2). A mixed-model logistic regression with institution and individuals as random effects was used to estimate overall PPVs. The variability of observed PPV of PI-RADS across imaging centers was described by using the median and interquartile range. Results The authors evaluated 3449 men (mean age, 65 years ± 8 [standard deviation]) with 5082 lesions. Biopsy results showed 1698 cancers with GS greater than or equal to 3+4 (International Society of Urological Pathology grade group ≥2) in 2082 men. Across all centers, the estimated PPV was 35% (95% confidence interval [CI]: 27%, 43%) for a PI-RADS score greater than or equal to 3 and 49% (95% CI: 40%, 58%) for a PI-RADS score greater than or equal to 4. The interquartile ranges of PPV at these same PI-RADS score thresholds were 27%-44% and 27%-48%, respectively. Conclusion The positive predictive value of the Prostate Imaging and Reporting Data System was low and varied widely across centers. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Milot in this issue.

Effect of shelter-in-place on emergency department radiology volumes during the COVID-19 pandemic.

PURPOSE: The coronavirus disease 2019 (COVID-19) pandemic has led to significant disruptions in the healthcare system including surges of infected patients exceeding local capacity, closures of primary care offices, and delays of non-emergent medical care. Government-initiated measures to decrease healthcare utilization (i.e., "flattening the curve") have included shelter-in-place mandates and social distancing, which have taken effect across most of the USA. We evaluate the immediate impact of the Public Health Messaging and shelter-in-place mandates on Emergency Department (ED) demand for radiology services. METHODS: We analyzed ED radiology volumes from the five University of California health systems during a 2-week time period following the shelter-in-place mandate and compared those volumes with March 2019 and early April 2019 volumes. RESULTS: ED radiology volumes declined from the 2019 baseline by 32 to 40% (p < 0.001) across the five health systems with a total decrease in volumes across all 5 systems by 35% (p < 0.001). Stratifying by subspecialty, the smallest declines were seen in non-trauma thoracic imaging, which decreased 18% (p value < 0.001), while all other non-trauma studies decreased by 48% (p < 0.001). CONCLUSION: Total ED radiology demand may be a marker for public adherence to shelter-in-place mandates, though ED chest radiology demand may increase with an increase in COVID-19 cases.

Assessing the clinical utility of color Doppler ultrasound for ovarian torsion in the setting of a negative contrast-enhanced CT scan of the abdomen and pelvis.

PURPOSE: The purpose of this study is to evaluate the utility of color Doppler ultrasound (CDU) in the assessment of ovarian torsion following a negative contrast-enhanced computed tomography (CT) examination. METHODS: This is a retrospective study of women who presented to the ED with abdominal pain and received both a contrast-enhanced CT and CDU within a 24-h period. The abdominal/pelvic CT examinations were evaluated for findings specific to torsion, including ovarian size greater than 5 cm, the presence of free fluid, uterine deviation, fallopian tube thickening, ovarian fat stranding, smooth wall thickening, the presence of the "twisted pedicle" sign, and abnormal ovarian enhancement. The results were compared to the presence or absence of ovarian torsion on the concurrent US. RESULTS: The initial query yielded 834 cases among 789 women. Of those 834 cases, 283 cases in 261 women received both imaging modalities within a 24-h period. The CT examinations demonstrated 48 cases with an ovarian size greater than 5 cm. 84 cases showed the presence of free fluid. Three cases of fallopian tube thickening were identified. One case of smooth wall thickening and a "twisted pedicle" sign were noted. Fifteen cases demonstrated stranding of the peri-ovarian fat. Twenty nine cases showed abnormal ovarian enhancement. A total of 111 cases showed at least one positive finding. Fourteen positive cases were identified on the CDU studies. Of the 14 positive cases, 11 had ovarian size greater than 5 cm. Twelve cases demonstrated the presence of free fluid. There was no uterine deviation or smooth wall thickening. One twisted pedicle was noted. Seven cases showed peri-ovarian fat stranding. Ten cases showed abnormal enhancement. Abnormalities on CT were noted in all cases suspicious for ovarian torsion on CDU. No negative CT examinations were associated with a positive CDU. In this small sample size, the negative predictive value of a negative CT examination was 100%. CONCLUSION: A negative contrast-enhanced CT examination of the abdomen and pelvis is sufficient to rule out ovarian torsion. Therefore, there is no utility in the addition of CDU specifically to evaluate for ovarian torsion following a negative contrast-enhanced CT scan of the abdomen and pelvis.

Osteolytic mystery: A rare case of pathologic fracture from a phosphaturic mesenchymal tumor in hip and femur.

Phosphaturic mesenchymal tumor (PMT) is a rare tumor causing bone complications and myopathy. Histologically, PMT displays a mix of spindled cells, osteoclast-like giant cells, basophilic matrix, and flocculent or "grungy" calcification. Here we describe a case of PMT in the right hip and proximal femur, initially suspected to be multiple myeloma, presenting with osteolytic lesions and elevated alkaline phosphatase. Tests for malignancy were negative, but a subsequent biopsy confirmed PMT. The patient underwent hip biopsy, femur resection, and hemiarthroplasty, with follow-up MRI recommended.

Incidental solitary fibrous tumor involving the seminal vesicle: A case report.

Solitary fibrous tumors are rare mesenchymal neoplasms that can range from slow-growing to aggressive tumors. This report presents a unique case of a young male patient with a solitary fibrous tumor involving the seminal vesicle, a rare location, and reinforces incidental discovery of these tumors on imaging and physical exams. Detection of these tumors is imperative to identify and treat malignancy. In our case, a 39-year-old previously healthy Asian male presents to the emergency department as a trauma admission post bicycle crash and is incidentally found to have a pelvic mass on computed tomography imaging of the pelvis. The patient underwent trans-anal biopsy which showed spindle epithelioid cells positive for CD34 and STAT6 markers, with a morphological and immunohistochemical profile consistent with a solitary fibrous tumor. The patient underwent surgery with a robotic-assisted laparoscopic pelvic mass resection and now follows up annually with imaging for observation.

A case report of challenges in distinguishing gastroesophageal junction hepatoid adenocarcinoma from testicular germ cell tumor: Insights for improved diagnosis with gene expression profiling.

Gastroesophageal junction hepatoid adenocarcinoma is a rare form of gastroesophageal cancer. We present a case of a 38-year-old man with no significant medical history who was diagnosed with gastroesophageal junction hepatoid adenocarcinoma but initially misdiagnosed with a testicular germ cell tumor, given the elevated alpha-feto protein and poorly differentiated pathology. We will elaborate on the importance of gene expression profiling in modern oncology to better define the tumor of origin in patients with cancer of unknown primary origin, how it helped us to diagnose gastroesophageal junction hepatoid adenocarcinoma and how it can help identify potential additional therapeutic targets in some cases. Due to the rarity of this subtype of gastroesophageal junction cancer there is a lack of standard therapeutic options, and we will discuss the most commonly used treatment regimens. The patient underwent three lines of antineoplastic therapy and unfortunately passed after 51 weeks of follow-up.

Primary Adenosquamous Carcinoma of the Prostate.

Prostate cancer accounts for 29% of malignant diagnoses among men in the United States and is the second leading cause of death from cancer. Effective screening methods and improved treatment have decreased the mortality rate significantly. This decreased mortality rate, however, does not apply to all histologic variants. Adenosquamous carcinoma of the prostate is an extremely aggressive neoplasm with no current known curative therapy. It is often diagnosed after chemotherapy, radiation, or androgen deprivation therapy for traditional prostatic adenocarcinomas. Primary carcinomas of the prostate with squamous features include, but are not limited to, pure squamous cell carcinoma and adenocarcinoma mixed with squamous cell carcinoma (SCC). Important distinguishable clinical features of adenosquamous carcinoma include normal prostate-specific antigen (PSA) levels, even with advanced disease and osteolytic versus osteoblastic metastatic lesions in adenocarcinoma. Additional entities to consider in the differential diagnosis are squamous metaplasia of the prostate, secondary involvement of pure SCC, and urothelial carcinoma with squamous differentiation. Here, we present a de novo case of adenosquamous carcinoma in a 48-year-old man who rapidly developed extensive metastatic disease.

Work-related musculoskeletal disorders affecting diagnostic radiologists and prophylactic physical therapy regimen.

The shift from film to PACS in reading rooms, coupled with escalating case volumes, exposes radiologists to the issues of the modern computer workstation including computer work posture and work-related musculoskeletal disorders (WMSD). Common WMSDs affecting the neck and upper extremities include cervical myofascial pain, shoulder tendonitis, lateral epicondylitis, carpal tunnel syndrome, and cubital tunnel syndrome. This review examines each pathology along with its pathogenesis, clinical features, physical exam findings, and potential risk factors. Furthermore, a comprehensive 11-part physical therapy regimen that is both prophylactic and therapeutic is illustrated and described in detail. One of the objectives of this review is to advocate for the inclusion of a physical therapy regimen in the working routine of diagnostic radiologists to prevent WMSDs. A brief daily commitment to this regimen can help radiologists remain healthy and productive in order to deliver optimal patient care throughout their careers.

Utilization of Re-VASC, the Novel Retroperitoneal Neovascularity Scoring System, for Characterization of T1a Small Renal Masses.

Purpose: Early characterization of small (T1a, <4 cm) renal masses is imperative for patient care and treatment planning. Renal biopsy is a sensitive and specific procedure that can accurately differentiate small renal masses as malignant or benign. However, it is an invasive procedure with a nonnegligible complication rate and is not performed routinely at most institutions. In this study, we sought to apply the Retroperitoneal Vascularity Assessment and Scoring in Carcinoma (Re-VASC) scoring system to T1a renal masses and analyzed whether it could differentiate these masses as benign or malignant. Methods: We obtained Institutional Review Board approval to retrospectively examine the records of all patients who presented to our single, urban academic referral center for surgical treatment of renal cell carcinoma (RCC). For the malignant group, patients with a diagnosis of T1a RCC from pathologic evaluation were included. Additionally, patients with a histopathological diagnosis of a T1a nonmalignant renal mass (fat poor-angiomyolipoma or oncocytoma) were included in our benign group. Results: This study includes 57 benign and 69 malignant T1a renal tumors. Average size for benign and malignant masses were 2.47 and 2.63, respectively (p = 0.267). Analysis demonstrated no significant difference between both groups in terms of sex, laterality, or size. The average Re-VASC score of benign and malignant masses was 0.175 and malignant masses was 0.784, respectively (p < 0.001). Additionally, the Re-VASC score was independently associated with malignancy with an odds ratio of 2.223 (p = 0.0109). Conclusion: The Re-VASC scoring system exhibits significantly greater values for malignant T1a renal masses when compared to benign masses. As a result, it shows promise as an adjunctive tool to renal biopsy for clinical decision-making. Further assessment of Re-VASC's true efficacy as a diagnostic marker will include prospective evaluation of a larger multicenter population.

Undifferentiated carcinoma of the pancreas with osteoclast-like giant cells: a case report.

BACKGROUND: Undifferentiated carcinomas of the pancreas with osteoclast-like giant cells (UCPOGC) are rare pancreatic neoplasms that account for less than 1% of all pancreatic malignancies. This case report of a 54-year-old male with metastatic UCPOGC adds to the existing literature and further ascertains the clinical and imaging features, treatment options, and prognosis of this rare entity. CASE PRESENTATION: We present the detailed clinical course of a 54-year-old Asian male patient with UCPOGC, with focus on the relevant clinical features and imaging findings that are characteristic of this disease entity. CONCLUSIONS: UCPOGC is an extremely rare pancreatic tumor with a unique histopathology and clinical course. It is often difficult to distinguish UCPOGCs from other pancreatic tumors, such as traditional pancreatic ductal adenocarcinomas (PDAC), on imaging, and it therefore remains a pathological diagnosis. Surgery is generally regarded as the first-line treatment option, and the roles of chemotherapy and radiation are unclear. Due to the exceeding rarity of this tumor, large-scale clinical studies are not feasible. Therefore, it is important to share individual insights and experiences to improve our understanding and care for patients with this devastating disease.

Automated detection of IVC filters on radiographs with deep convolutional neural networks.

PURPOSE: To create an algorithm able to accurately detect IVC filters on radiographs without human assistance, capable of being used to screen radiographs to identify patients needing IVC filter retrieval. METHODS: A primary dataset of 5225 images, 30% of which included IVC filters, was assembled and annotated. 85% of the data was used to train a Cascade R-CNN (Region Based Convolutional Neural Network) object detection network incorporating a pre-trained ResNet-50 backbone. The remaining 15% of the data, independently annotated by three radiologists, was used as a test set to assess performance. The algorithm was also assessed on an independently constructed 1424-image dataset, drawn from a different institution than the primary dataset. RESULTS: On the primary test set, the algorithm achieved a sensitivity of 96.2% (95% CI 92.7-98.1%) and a specificity of 98.9% (95% CI 97.4-99.5%). Results were similar on the external test set: sensitivity 97.9% (95% CI 96.2-98.9%), specificity 99.6 (95% CI 98.9-99.9%). CONCLUSION: Fully automated detection of IVC filters on radiographs with high sensitivity and excellent specificity required for an automated screening system can be achieved using object detection neural networks. Further work will develop a system for identifying patients for IVC filter retrieval based on this algorithm.

Revenue and Cost Analysis of a System Utilizing Natural Language Processing and a Nurse Coordinator for Radiology Follow-up Recommendations.

Radiology reports often contain recommendations for follow-up imaging, Provider adherence to these radiology recommendations can be incomplete, which may result in patient harm, lost revenue, or litigation. This study sought to perform a revenue assessment of a hybrid natural language processing (NLP) and human follow-up system. Reports generated from January 2020 to April 2021 that were indexed as overdue from follow-up recommendations by mPower Follow-Up Recommendation Algorithm (Nuance Communications Inc., Burlington, MA), were assessed for follow up and revenue. Follow-up exams completed because of the hybrid system were tabulated and given revenue amounts based on Medicare national reimbursement rates. These rates were then summated. A total of n =3011 patients were flagged via the mPower algorithm as having not received a timely follow-up indicated for procedure. Of these, n = 427 required the quality nurse to contact their healthcare provider to place orders. The follow-up imaging of these patients accounted for $62,937.66 of revenue. This revenue was calculated as higher than personnel cost (based on national average quality and safety nurse salary and time allotted on follow-ups). Our results indicate that a hybrid human-artificial intelligence follow-up system can be profitable, while potentially adding to patient safety. Our revenue figure likely significantly underestimates the true revenue obtained at our institution. This was due to the use of Medicare national reimbursement rates to calculate revenue, for the purposes of generalizability.

Novel Retroperitoneal Neovascularity Scoring System in Renal Cell Carcinoma Tumor Staging.

Purpose: Renal cell carcinoma (RCC) is the most common type of kidney cancer worldwide. Although radiologists assess enhancement patterns of renal tumors to predict tumor pathology report, to our knowledge, no formal scoring system has been created and validated to assess the level of neovascularity in RCC, despite its critical role in cancer metastases. In this study, we characterized and analyzed the level of angiogenesis in tumor-burdened kidneys and their benign counterparts. We then created and validated a scoring scale for neovascularity that can help predict tumor staging for RCC. Methods: After Institutional Review Board approval, the charts of patients who had undergone operation for RCC between January 13, 2014 and February 4, 2020 were retrospectively reviewed for inclusion in this study. Inclusion criteria were a diagnosis of RCC, simple/radical nephrectomy, preoperative contrast-enhanced CT scans, and complete pathology reports. Neovascularity was scored on a scale of 0-4 where 0 = no neovascularity detected, 1 = a single vessel <3 mm wide, 2 = a single vessel ≥3 mm wide, 3 = multiple vessels <3 mm wide, and 4 = multiple vessels ≥3 mm wide. Results: A total of 227 patients were included in this study. Most of the tumor pathology reports were clear cell carcinoma, regardless of tumor staging. The average neovascularity score was 1.07 for pT1x tumors, 2.83 for pT2x tumors, and 3.04 for pT3x tumors. There was a significant difference in neovascularity score between pT1x and pT2x tumors (p = 0.0046), pT1x and pT3x tumors (p < 0.0001), and benign kidneys and kidneys with RCC (p < 0.0001). Conclusion: Our novel vascular scoring system for RCC demonstrates significant correlation with RCC pathological tumor staging. This scoring system may be utilized as part of a comprehensive radiological assessment of renal tumors, potentially improving tumor characterization and clinical decision making.

Imaging uterine lipoleiomyomas: A case series and review of the literature.

Background: Lipoleiomyomas are uncommon uterine lesions containing adipose and smooth muscle tissue. They have a variable presentation and are usually found incidentally on imaging or post-hysterectomy tissue analysis. Given their low prevalence, there is a dearth of literature describing imaging characteristics for uterine lipoleiomyomas. In this image-rich case series, we summarize an example of an initial presentation as well as present ultrasound, computed tomography (CT), and magnetic resonance imaging (MRI) findings for 36 patients. Case presentation: We present the detailed clinical course of a representative patient evaluated for uterine lipoleiomyoma and describe imaging findings seen in another 35 patients. This includes ultrasound findings from 16 patients, CT findings from 25 patients, and MRI findings from 5 patients. Among the 36 total patients, symptoms at the time of diagnosis were variable but often included abdominal or pelvic pain; however, most patients were asymptomatic, and the lipoleiomyomas were incidentally discovered on imaging. Conclusions: Uterine lipoleiomyomas are rare and benign tumors with variable presentations. Ultrasound, CT, and MRI findings can assist in diagnosis. Findings on ultrasound typically include well-circumscribed hyperechoic and septated lesions with minimal to no internal blood flow. CT shows fat-containing either homogeneous or heterogeneous circumscribed lesions depending on their ratio of fat and smooth muscle tissue. Lastly, on MRI, uterine lipoleiomyomas commonly appear heterogenous with loss of signal on fat-suppressed sequences. These imaging findings are highly specific for lipoleiomyomas, and familiarity with these findings may reduce unnecessary and potentially invasive procedures.

Artificial Intelligence for Improved Hepatosplenomegaly Diagnosis.

Hepatosplenomegaly is commonly diagnosed by radiologists based on single dimension measurements and heuristic cut-offs. Volumetric measurements may be more accurate for diagnosing organ enlargement. Artificial intelligence techniques may be able to automatically calculate liver and spleen volume and facilitate more accurate diagnosis. After IRB approval, 2 convolutional neural networks (CNN) were developed to automatically segment the liver and spleen on a training dataset comprised of 500 single-phase, contrast-enhanced CT abdomen and pelvis examinations. A separate dataset of ten thousand sequential examinations at a single institution was segmented with these CNNs. Performance was evaluated on a 1% subset and compared with manual segmentations using Sorensen-Dice coefficients and Pearson correlation coefficients. Radiologist reports were reviewed for diagnosis of hepatomegaly and splenomegaly and compared with calculated volumes. Abnormal enlargement was defined as greater than 2 standard deviations above the mean. Median Dice coefficients for liver and spleen segmentation were 0.988 and 0.981, respectively. Pearson correlation coefficients of CNN-derived estimates of organ volume against the gold-standard manual annotation were 0.999 for the liver and spleen (P < 0.001). Average liver volume was 1556.8 ± 498.7 cc and average spleen volume was 194.6 ± 123.0 cc. There were significant differences in average liver and spleen volumes between male and female patients. Thus, the volume thresholds for ground-truth determination of hepatomegaly and splenomegaly were determined separately for each sex. Radiologist classification of hepatomegaly was 65% sensitive, 91% specific, with a positive predictive value (PPV) of 23% and an negative predictive value (NPV) of 98%. Radiologist classification of splenomegaly was 68% sensitive, 97% specific, with a positive predictive value (PPV) of 50% and a negative predictive value (NPV) of 99%. Convolutional neural networks can accurately segment the liver and spleen and may be helpful to improve radiologist accuracy in the diagnosis of hepatomegaly and splenomegaly.

Emergent pediatric US: what every radiologist should know.

Appendicitis, intussusception, and hypertrophic pyloric stenosis (HPS) are three of the most common reasons for emergent abdominal imaging in pediatric patients. Although the use of computed tomography has risen dramatically over the past 2 decades, children are particularly at risk for the adverse effects of ionizing radiation, and even low-dose radiation is associated with a small but significant increase in lifetime risk of fatal cancer. In most emergency departments, the use of magnetic resonance (MR) imaging as a primary modality for the evaluation of a child with abdominal pain remains impractical due to its high cost, its limited availability, and the frequent need for sedation. Ultrasonography (US) does not involve ionizing radiation and, unlike MR imaging, is relatively inexpensive, is widely available, and does not require sedation. Another major advantage of US in abdominal imaging is that it allows dynamic assessment of bowel peristalsis and compressibility. Delayed diagnosis of any of the aforementioned disease processes can lead to serious morbidity and, in some cases, death. The ability to diagnose or exclude disease with US should be part of a core radiology skill set for any practice that includes a pediatric population.