The 50 most-cited articles in Radiology, 2022

Background Patients with fractures are a common emergency presentation and may be misdiagnosed at radiologic imaging. An increasing number of studies apply artificial intelligence (AI) techniques to fracture detection as an adjunct to clinician diagnosis. Purpose To perform a systematic review and meta-analysis comparing the diagnostic performance in fracture detection between AI and clinicians in peer-reviewed publications and the gray literature (ie, articles published on preprint repositories). Materials and Methods A search of multiple electronic databases between January 2018 and July 2020 (updated June 2021) was performed that included any primary research studies that developed and/or validated AI for the purposes of fracture detection at any imaging modality and excluded studies that evaluated image segmentation algorithms. Meta-analysis with a hierarchical model to calculate pooled sensitivity and specificity was used. Risk of bias was assessed by using a modified Prediction Model Study Risk of Bias Assessment Tool, or PROBAST, checklist. Results Included for analysis were…

Background Spatial resolution, soft-tissue contrast, and dose-efficient capabilities of photon-counting CT (PCCT) potentially allow a better quality and diagnostic confidence of coronary CT angiography (CCTA) in comparison to conventional CT. Purpose To compare the quality of CCTA scans obtained with a clinical prototype PCCT system and an energy-integrating detector (EID) dual-layer CT (DLCT) system. Materials and Methods In this prospective board-approved study with informed consent, participants with coronary artery disease underwent retrospective electrocardiographically gated CCTA with both systems after injection of 65–75 mL of 400 mg/mL iodinated contrast agent at 5 mL/sec. A prior phantom task-based quality assessment of the detectability index of coronary lesions was performed. Ultra-high-resolution parameters were used for PCCT (1024 matrix, 0.25-mm section thickness) and EID DLCT (512 matrix, 0.67-mm section thickness). Three cardiac radiologists independently performed a blinded analysis using a five-point quality score (1 = insufficient, 5 = excellent) for overall image…

Background Mounting evidence suggests that the choroid plexus (CP) plays an important role in the pathophysiology of Alzheimer disease (AD), but its imaging profile in cognitive impairment remains unclear. Purpose To evaluate CP volume, permeability, and susceptibility by using MRI in patients at various stages of cognitive impairment. Materials and Methods This retrospective study evaluated patients with cognitive symptoms who underwent 3.0-T MRI of the brain, including dynamic contrast-enhanced (DCE) imaging and quantitative susceptibility mapping (QSM), between January 2013 and May 2020. CP volume was automatically segmented using three-dimensional T1-weighted sequences; the volume transfer constant (ie, Ktrans) and fractional plasma volume (ie, Vp) were determined using DCE MRI, and susceptibility was assessed using QSM. The effects of CP volume, expressed as the ratio to intracranial volume, on cognition were evaluated using multivariable linear regression adjusted for age, sex, education, apolipoprotein E ε4 allele status, and volumetric measures. Results A total of 532…

Background Preoperative assessment of pathologic complete response (pCR) in locally advanced rectal cancer (LARC) after neoadjuvant chemoradiotherapy (nCRT) is increasingly needed for organ preservation, but large-scale validation of an MRI radiomics model remains lacking. Purpose To evaluate radiomics models based on T2-weighted imaging and diffusion-weighted MRI for predicting pCR after nCRT in LARC and compare their performance with visual assessment by radiologists. Materials and Methods This retrospective study included patients with LARC (clinical stage T3 or higher, positive nodal status, or both) who underwent post-nCRT MRI and elective resection between January 2009 and December 2018. Surgical histopathologic analysis was the reference standard for pCR. Radiomic features were extracted from the volume of interest on T2-weighted images and apparent diffusion coefficient (ADC) maps from post-nCRT MRI to generate three models: T2 weighted, ADC, and both T2 weighted and ADC (merged). Radiomics signatures were generated using the least absolute shrinkage and selection operator…

Opportunistic CT screening leverages robust imaging data embedded within abdominal and thoracic scans that are generally unrelated to the specific clinical indication and have heretofore gone largely unused. This incidental imaging information may prove beneficial to patients in terms of wellness, prevention, risk profiling, and presymptomatic detection of relevant disease. The growing interest in CT-based opportunistic screening relates to a confluence of factors: the objective and generalizable nature of CT-based body composition measures, the emergence of fully automated explainable AI solutions, the sheer volume of body CT scans performed, and the increasing emphasis on precision medicine and value-added initiatives. With a systematic approach to body composition and other useful CT markers, initial evidence suggests that their ability to help radiologists assess biologic age and predict future adverse cardiometabolic events rivals even the best available clinical reference standards. Emerging data suggest that standalone "intended" CT screening over an unorganized opportunistic…

MRI plays an important role as a secondary test or problem-solving modality in the evaluation of adnexal lesions depicted at US. MRI has increased specificity compared with US, decreasing the number of false-positive diagnoses for malignancy and thereby avoiding unnecessary or over-extensive surgery in patients with benign lesions or borderline tumors, while women with possible malignancies can be expeditiously referred for oncologic surgical evaluation. The Ovarian-Adnexal Reporting and Data System (O-RADS) MRI Committee is an international collaborative effort formed under the direction of the American College of Radiology and includes a diverse group of experts on adnexal imaging and management who developed the O-RADS MRI risk stratification system. This scoring system assigns a probability of malignancy based on the MRI features of an adnexal lesion and provides information to facilitate optimal patient management. The widespread implementation of a codified reporting system will lead to improved interpretation agreement and standardized communication between radiologists and…

Background Transarterial chemoembolization (TACE) is the recommended treatment for intermediate hepatocellular carcinoma (HCC) according to the Barcelona Clinic Liver Cancer guidelines. Prospective uncontrolled studies suggest that yttrium 90 (90Y) transarterial radioembolization (TARE) is a safe and effective alternative. Purpose To compare the efficacy and safety of TARE with TACE for unresectable HCC. Materials and Methods In this single-center prospective randomized controlled trial (TRACE), 90Y glass TARE was compared with doxorubicin drug-eluting bead (DEB) TACE in participants with intermediate-stage HCC, extended to Eastern Cooperative Oncology Group performance status 1 and those with early-stage HCC not eligible for surgery or thermoablation. Participants were recruited between September 2011 and March 2018. The primary end point was time to overall tumor progression (TTP) (Kaplan-Meier analysis) in the intention-to-treat (ITT) and per-protocol (PP) groups. Results At interim analysis, 38 participants (median age, 67 years; IQR, 63–72 years; 33 men) were randomized to the…

Background Ultra–low-dose (ULD) CT could facilitate the clinical implementation of large-scale lung cancer screening while minimizing the radiation dose. However, traditional image reconstruction methods are associated with image noise in low-dose acquisitions. Purpose To compare the image quality and lung nodule detectability of deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-V (ASIR-V) in ULD CT. Materials and Methods Patients who underwent noncontrast ULD CT (performed at 0.07 or 0.14 mSv, similar to a single chest radiograph) and contrast-enhanced chest CT (CECT) from April to June 2020 were included in this prospective study. ULD CT images were reconstructed with filtered back projection (FBP), ASIR-V, and DLIR. Three-dimensional segmentation of lung tissue was performed to evaluate image noise. Radiologists detected and measured nodules with use of a deep learning–based nodule assessment system and recognized malignancy-related imaging features. Bland-Altman analysis and repeated-measures analysis of variance were used to evaluate…

Background Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT. Purpose To develop and to validate a deep learning (DL)–based tool able to detect pancreatic cancer at CT. Materials and Methods Retrospectively collected contrast-enhanced CT studies in patients diagnosed with pancreatic cancer between January 2006 and July 2018 were compared with CT studies of individuals with a normal pancreas (control group) obtained between January 2004 and December 2019. An end-to-end tool comprising a segmentation convolutional neural network (CNN) and a classifier ensembling five CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation were compared using the McNemar test. Results A total of 546 patients with pancreatic cancer (mean age, 65 years ± 12 [SD], 297 men) and 733 control subjects were randomly divided into training, validation, and test sets. In the internal test set, the DL tool achieved 89.9% (98 of 109; 95% CI:…

Vascular imaging with color and power Doppler is a useful tool in the assessment of various disease processes. Assessment of blood flow, from infarction and ischemia to hyperemia, in organs, neoplasms, and vessels, is used in nearly every US investigation. Recent developments in this area are sensitive to small-vessel low velocity flow without use of intravenous contrast agents, known as microvascular flow imaging (MVFI). MVFI is more sensitive in detection of small vessels than color, power, and spectral Doppler, reducing the need for follow-up contrast-enhanced US (CEUS), CT, and MRI, except when arterial and venous wash-in and washout characteristics would be helpful in diagnosis. Varying clinical applications of MVFI are reviewed in adult and pediatric populations, including its technical underpinnings. MVFI shows promise in assessment of several conditions including benign and malignant lesions in the liver and kidney, acute pathologic abnormalities in the gallbladder and testes, and superficial lymph nodes. Future potential of MVFI in different conditions (eg, endovascular…

Background Macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC) is an aggressive variant associated with angiogenesis and immunosuppressive tumor microenvironment, which is expected to be noninvasively identified using radiomics approaches. Purpose To construct a CT radiomics model to predict the MTM subtype and to investigate the underlying immune infiltration patterns. Materials and Methods This study included five retrospective data sets and one prospective data set from three academic medical centers between January 2015 and December 2021. The preoperative liver contrast-enhanced CT studies of 365 adult patients with resected HCC were evaluated. The Third Xiangya Hospital of Central South University provided the training set and internal test set, while Yueyang Central Hospital and Hunan Cancer Hospital provided the external test sets. Radiomic features were extracted and used to develop a radiomics model with machine learning in the training set, and the performance was verified in the two test sets. The outcomes cohort, including 58 adult patients with…

Background Gallium 68 (68Ga)–labeled fibroblast-activation protein inhibitor (FAPI) has recently been introduced as a promising tumor imaging agent. Purpose To compare 68Ga-FAPI PET/CT with fluorine 18 (18F)–labeled fluorodeoxyglucose (FDG) PET/CT in evaluating lung cancer. Materials and Methods In this prospective study conducted from September 2020 to February 2021, images from participants with lung cancer who underwent both 68Ga-FAPI and 18F-FDG PET/CT examinations were analyzed. The tracer uptakes, quantified by maximum standardized uptake value (SUVmax) and target-to-background ratio (TBR), were compared for paired positive lesions between both modalities using the paired t test or Wilcoxon signed-rank test. Results Thirty-four participants (median age, 64 years [interquartile range: 46–80 years]; 20 men) were evaluated. From visual evaluation, 68Ga-FAPI PET/CT and 18F-FDG PET/CT showed similar performance in the delineation of primary tumors and detection of suspected metastases in the lungs, liver, and adrenal glands. The metabolic tumor volume in primary and recurrent lung…

Background Developments in artificial intelligence (AI) systems to assist radiologists in reading mammograms could improve breast cancer screening efficiency. Purpose To investigate whether an AI system could detect normal, moderate-risk, and suspicious mammograms in a screening sample to safely reduce radiologist workload and evaluate across Breast Imaging Reporting and Data System (BI-RADS) densities. Materials and Methods This retrospective simulation study analyzed mammographic examination data consecutively collected from January 2014 to December 2015 in the Danish Capital Region breast cancer screening program. All mammograms were scored from 0 to 10, representing the risk of malignancy, using an AI tool. During simulation, normal mammograms (score < 5) would be excluded from radiologist reading and suspicious mammograms (score > recall threshold [RT]) would be recalled. Two radiologists read the remaining mammograms. The RT was fitted using another independent cohort (same institution) by matching to the radiologist sensitivity. This protocol was further applied to each…

Background Contrast-enhanced mammography (CEM) is a more accessible alternative to contrast-enhanced MRI (CE-MRI) in breast imaging, but a summary comparison of published studies is lacking. Purpose To directly compare the performance of CEM and CE-MRI regarding sensitivity, specificity, and negative predictive value in detecting breast cancer, involving all publicly available studies in the English language. Materials and Methods Two readers extracted characteristics of studies investigating the comparative diagnostic performance of CEM and CE-MRI in detecting breast cancer. Studies published until April 2021 were eligible. Sensitivity, specificity, negative predictive value, and positive and negative likelihood ratios were calculated using bivariate random effects models. A Fagan nomogram was used to identify the maximum pretest probability at which posttest probabilities of a negative CEM or CE-MRI examination were in line with the 2% malignancy rate benchmark for downgrading a Breast Imaging Reporting and Data System (BI-RADS) category 4 to a BI-RADS category 3 result. I 2…

Adequate clinical evaluation of artificial intelligence (AI) algorithms before adoption in practice is critical. Clinical evaluation aims to confirm acceptable AI performance through adequate external testing and confirm the benefits of AI-assisted care compared with conventional care through appropriately designed and conducted studies, for which prospective studies are desirable. This article explains some of the fundamental methodological points that should be considered when designing and appraising the clinical evaluation of AI algorithms for medical diagnosis. The specific topics addressed include the following: (a) the importance of external testing of AI algorithms and strategies for conducting the external testing effectively, (b) the various metrics and graphical methods for evaluating the AI performance as well as essential methodological points to note in using and interpreting them, (c) paired study designs primarily for comparative performance evaluation of conventional and AI-assisted diagnoses, (d) parallel study designs primarily for evaluating the effect of AI…

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease worldwide, with an estimated prevalence of up to 30% in the general population and higher in people with type 2 diabetes. The assessment of liver fat content is essential to help identify patients with or who are at risk for NAFLD and to follow their disease over time. The American Institute of Ultrasound in Medicine-RSNA Quantitative Imaging Biomarkers Alliance Pulse-Echo Quantitative Ultrasound Initiative was formed to help develop and standardize acquisition protocols and to better understand confounding factors of US-based fat quantification. The three quantitative US parameters explored by the initiative are attenuation, backscatter coefficient, and speed of sound. The purpose of this review is to present the current state of attenuation imaging for fat quantification and to provide expert opinion on examination performance and interpretation. US attenuation methods that need further study are outlined.

Background The prognosis of hepatocellular carcinoma (HCC) with major portal vein tumor thrombosis (PVTT) is dismal after standard treatment with sorafenib. Hepatic arterial infusion chemotherapy (HAIC) has been suggested for patients with HCC and major PVTT. Purpose To compare the efficacy and safety of sorafenib plus 3cir-OFF HAIC versus sorafenib alone for advanced HCC with major PVTT. Materials and Methods This phase II trial recruited systemic treatment-naïve patients with HCC and major PVTT (portal vein invasion grade Vp3 [first branch] and Vp4 [main trunk]) between June 2017 and November 2019. Patients were randomly assigned (1:1 ratio) to receive sorafenib (400 mg twice daily) plus 3cir-OFF HAIC (35 mg/m2 oxaliplatin [hours 0–2] followed by 600 mg/m2 5-fluorouracil [hours 2–24], days 1–3) with a standardized percutaneous port catheter system or sorafenib alone (400 mg twice daily) every 4 weeks. The primary end point was overall survival (OS). The secondary end points were objective response rate, progression-free survival (PFS), and safety. OS and PFS were assessed using…

Background Deep learning reconstruction (DLR) may improve image quality. However, its impact on diffusion-weighted imaging (DWI) of the prostate has yet to be assessed. Purpose To determine whether DLR can improve image quality of diffusion-weighted MRI at b values ranging from 1000 sec/mm2 to 5000 sec/mm2 in patients with prostate cancer. Materials and Methods In this retrospective study, images of the prostate obtained at DWI with a b value of 0 sec/mm2, DWI with a b value of 1000 sec/mm2 (DWI1000), DWI with a b value of 3000 sec/mm2 (DWI3000), and DWI with a b value of 5000 sec/mm2 (DWI5000) from consecutive patients with biopsy-proven cancer from January to June 2020 were reconstructed with and without DLR. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) from region-of-interest analysis and qualitatively assessed using a five-point visual scoring system (1 [very poor] to 5 [excellent]) for each high-b-value DWI sequence with and without DLR. The SNR, CNR, and visual score for DWI with and without DLR were compared with the paired t…

Abstract Magnetoencephalography (MEG) is an established method to investigate epilepsy. Current MEG systems house hundreds of cryogenic sensors in a rigid, one-size-fits-all helmet, which results in several limitations, particularly in children. On-scalp MEG based on optically-pumped magnetometers (OPMs) may alleviate these limitations. We report on five children (5–11 years old) with self-limited focal (n=3) or structural (n=2) epilepsy who underwent cryogenic (102 magnetometers) and on-scalp (32 OPMs) MEG. We compared the two modalities for the detection and localization of interictal epileptiform discharges (IEDs). We identified IEDs in all children with comparable sensor topographies for both MEG devices. IED amplitudes were 2.3-4.8 times higher with on-scalp MEG and signal-to-noise ratio (SNR) was also 27-60% higher with on-scalp MEG in all but one patient with large head movement artifacts. The neural source of averaged IEDs was located at about 5 mm (n=3) or higher (8.3 mm, n=1; 15.6 mm, n=1) between on-scalp and cryogenic MEG. Despite limited number of sensors and scalp…

Research has not yet quantified the effects of workload or duty hours on the accuracy of radiologists. With the exception of a brief reduction in imaging studies during the 2020 peak of the COVID-19 pandemic, the workload of radiologists in the United States has seen relentless growth in recent years. One concern is that this increased demand could lead to reduced accuracy. Behavioral studies in species ranging from insects to humans have shown that decision speed is inversely correlated to decision accuracy. A potential solution is to institute workload and duty limits to optimize radiologist performance and patient safety. The concern, however, is that any prescribed mandated limits would be arbitrary and thus no more advantageous than allowing radiologists to self-regulate. Specific studies have been proposed to determine whether limits reduce error, and if so, to provide a principled basis for such limits. This could determine the precise susceptibility of individual radiologists to medical error as a function of speed during image viewing, the maximum number of studies that…

As the role of artificial intelligence (AI) in clinical practice evolves, governance structures oversee the implementation, maintenance, and monitoring of clinical AI algorithms to enhance quality, manage resources, and ensure patient safety. In this article, a framework is established for the infrastructure required for clinical AI implementation and presents a road map for governance. The road map answers four key questions: Who decides which tools to implement? What factors should be considered when assessing an application for implementation? How should applications be implemented in clinical practice? Finally, how should tools be monitored and maintained after clinical implementation? Among the many challenges for the implementation of AI in clinical practice, devising flexible governance structures that can quickly adapt to a changing environment will be essential to ensure quality patient care and practice improvement objectives.

Background Although deep learning has brought revolutionary changes in health care, reliance on manually selected cross-sectional images and segmentation remain methodological barriers. Purpose To develop and validate an automated preoperative artificial intelligence (AI) algorithm for tumor and lymph node (LN) segmentation with CT imaging for prediction of LN metastasis in patients with pancreatic ductal adenocarcinoma (PDAC). Materials and Methods In this retrospective study, patients with surgically resected, pathologically confirmed PDAC underwent multidetector CT from January 2015 to April 2020. Three models were developed, including an AI model, a clinical model, and a radiomics model. CT-determined LN metastasis was diagnosed by radiologists. Multivariable logistic regression analysis was conducted to develop the clinical and radiomics models. The performance of the models was determined on the basis of their discrimination and clinical utility. Kaplan-Meier curves, the log-rank test, or Cox regression were used for survival analysis. Results Overall, 734 patients (mean age,…

The U.S. National Council on Radiation Protection and Measurements (NCRP) conducted a retrospective assessment of the U.S. data, and the United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR) performed a similar worldwide assessment for 2009-2018 (with most data from 2014 to 2017). Using the data from those reports, the frequency of radiologic and nuclear medicine studies, annual collective, and per capita effective dose in the United States for 2016 were compared with worldwide estimates from 2009 to 2018. There were an estimated 691 million radiologic, CT, dental, and nuclear medicine studies performed in the United States in 2016, which represented 16.5% of the 4.2 billion performed worldwide. The United States also accounted for 74 million CT procedures (18% of the world's estimated total), 275 million conventional radiology procedures (11% of the world's total), 8.1 million interventional radiologic procedures (34% of the world's total), 320 million dental radiography procedures (29% of the world's total), and 13.5 million nuclear medicine procedures…

Abstract Background Long-COVID is an umbrella term used to describe ongoing symptoms following COVID-19 infection after four weeks. Symptoms are wide-ranging but breathlessness is one of the most common and can persist for months after the initial infection. Investigations including Computed Tomography (CT), and physiological measurements (lung function tests) are usually unremarkable. The mechanisms driving breathlessness remain unclear, and this may be hindering the development of effective treatments. Methods Eleven non-hospitalised Long-COVID (NHLC, 4 male), 12 post-hospitalised COVID-19 (PHC, 10 male) patients were recruited from a Post-COVID Assessment clinic, and thirteen healthy controls (6 female) were recruited to undergo Hyperpolarized Xenon Magnetic Resonance Imaging (Hp-XeMRI). NHLC and PHC participants underwent contemporaneous CT, Hp-XeMRI, lung function tests, 1-minute sit-to-stand test and breathlessness questionnaires. Statistical analysis included group and pair-wise comparisons between patients and controls, and correlations between patient clinical and imaging…

Background Recently developed time-dependent diffusion MRI has potential in characterizing cellular tissue microstructures; however, its value in imaging prostate cancer (PCa) remains unknown. Purpose To investigate the feasibility of time-dependent diffusion MRI–based microstructural mapping for noninvasively characterizing cellular properties of PCa and for discriminating between clinically significant PCa and clinically insignificant disease. Materials and Methods Men with a clinical suspicion of PCa were enrolled prospectively between October 2019 and August 2020. Time-dependent diffusion MRI data were acquired with pulsed and oscillating gradient diffusion MRI sequences at an equivalent diffusion time of 7.5–30 msec on a 3.0-T scanner. Time-dependent diffusion MRI–based microstructural parameters, including cell diameter, intracellular volume fraction, cellularity, and diffusivities, were estimated with a two-compartment model. These were compared for different International Society of Urological Pathology grade groups (GGs), and their performance in discriminating clinically…

Background An iterative reconstruction (IR) algorithm was introduced for clinical photon-counting detector (PCD) CT. Purpose To investigate the image quality and the optimal strength level of a quantum IR algorithm (QIR; Siemens Healthcare) for virtual monoenergetic images and polychromatic images (T3D) in a phantom and in patients undergoing portal venous abdominal PCD CT. Materials and Methods In this retrospective study, noise power spectrum (NPS) was measured in a water-filled phantom. Consecutive oncologic patients who underwent portal venous abdominal PCD CT between March and April 2021 were included. Virtual monoenergetic images at 60 keV and T3D were reconstructed without QIR (QIR-off; reference standard) and with QIR at four levels (QIR 1–4; index tests). Global noise index, contrast-to-noise ratio (CNR), and voxel-wise CT attenuation differences were measured. Noise and texture, artifacts, diagnostic confidence, and overall quality were assessed qualitatively. Conspicuity of hypodense liver lesions was rated by four readers. Parametric (analyses of variance, paired t…

Abstract Background The sequelae of SARS-CoV-2 infection on pulmonary structure and function remain incompletely characterized. Methods Adults with confirmed COVID-19 who remained symptomatic more than thirty days following diagnosis were enrolled and classified as ambulatory, hospitalized or requiring the intensive care unit (ICU) based on the highest level of care received during acute infection. Symptoms, pulmonary function tests and chest computed tomography (CT) findings were compared across groups and to healthy controls. CT images were quantitatively analyzed using supervised machine-learning to measure regional ground glass opacities (GGO) and image-matching to measure regional air trapping. Comparisons were performed using univariate analyses and multivariate linear regression. Results Of the 100 patients enrolled, 67 were in the ambulatory group. All groups commonly reported cough and dyspnea. Pulmonary function testing revealed restrictive physiology in the hospitalized and ICU groups but was normal in the ambulatory group. Among hospitalized and ICU patients, the mean…

Gallbladder polyps (also known as polypoid lesions of the gallbladder) are a common incidental finding. The vast majority of gallbladder polyps smaller than 10 mm are not true neoplastic polyps but are benign cholesterol polyps with no inherent risk of malignancy. In addition, recent studies have shown that the overall risk of gallbladder cancer is not increased in patients with small gallbladder polyps, calling into question the rationale for frequent and prolonged follow-up of these common lesions. In 2021, a Society of Radiologists in Ultrasound, or SRU, consensus conference was convened to provide recommendations for the management of incidentally detected gallbladder polyps at US. See also the editorial by Sidhu and Rafailidis in this issue.

Background Artificial intelligence (AI) has shown promising results for cancer detection with mammographic screening. However, evidence related to the use of AI in real screening settings remain sparse. Purpose To compare the performance of a commercially available AI system with routine, independent double reading with consensus as performed in a population-based screening program. Furthermore, the histopathologic characteristics of tumors with different AI scores were explored. Materials and Methods In this retrospective study, 122 969 screening examinations from 47 877 women performed at four screening units in BreastScreen Norway from October 2009 to December 2018 were included. The data set included 752 screen-detected cancers (6.1 per 1000 examinations) and 205 interval cancers (1.7 per 1000 examinations). Each examination had an AI score between 1 and 10, where 1 indicated low risk of breast cancer and 10 indicated high risk. Threshold 1, threshold 2, and threshold 3 were used to assess the performance of the AI system as a binary decision tool (selected vs not selected).…

Background Stratifying high-risk histopathologic features in endometrial carcinoma is important for treatment planning. Radiomics analysis at preoperative MRI holds potential to identify high-risk phenotypes. Purpose To evaluate the performance of multiparametric MRI three-dimensional radiomics-based machine learning models for differentiating low- from high-risk histopathologic markers—deep myometrial invasion (MI), lymphovascular space invasion (LVSI), and high-grade status—and advanced-stage endometrial carcinoma. Materials and Methods This dual-center retrospective study included women with histologically proven endometrial carcinoma who underwent 1.5-T MRI before hysterectomy between January 2011 and July 2015. Exclusion criteria were tumor diameter less than 1 cm, missing MRI sequences or histopathology reports, neoadjuvant therapy, and malignant neoplasms other than endometrial carcinoma. Three-dimensional radiomics features were extracted after tumor segmentation at MRI (T2-weighted, diffusion-weighted, and dynamic contrast-enhanced MRI). Predictive features were selected in…

Background Monitoring the microcirculation in human feet is crucial in assessing peripheral vascular diseases, such as diabetic foot. However, conventional imaging modalities are more focused on diagnosis in major arteries, and there are limited methods to provide microvascular information in early stages of the disease. Purpose To investigate a three-dimensional (3D) noncontrast bimodal photoacoustic (PA)/US imaging system that visualizes the human foot morphologically and also reliably quantifies podiatric vascular parameters noninvasively. Materials and Methods A clinically relevant PA/US imaging system was combined with a foot scanner to obtain 3D PA and US images of the human foot in vivo. Healthy participants were recruited from September 2020 to June 2021. The collected 3D PA and US images were postprocessed to present structural information about the foot. The quantitative reliability was evaluated in five repeated scans of 10 healthy feet by calculating the intraclass correlation coefficient and minimal detectable change, and the detectability of microvascular changes was…

Background Deep learning (DL) algorithms could improve the classification of ovarian tumors assessed with multimodal US. Purpose To develop DL algorithms for the automated classification of benign versus malignant ovarian tumors assessed with US and to compare algorithm performance to Ovarian-Adnexal Reporting and Data System (O-RADS) and subjective expert assessment for malignancy. Materials and Methods This retrospective study included consecutive women with ovarian tumors undergoing gray scale and color Doppler US from January 2019 to November 2019. Histopathologic analysis was the reference standard. The data set was divided into training (70%), validation (10%), and test (20%) sets. Algorithms modified from residual network (ResNet) with two fusion strategies (feature fusion [hereafter, DLfeature] or decision fusion [hereafter, DLdecision]) were developed. DL prediction of malignancy was compared with O-RADS risk categorization and expert assessment by area under the receiver operating characteristic curve (AUC) analysis in the test set. Results A total of 422 women (mean age,…

Background Assessment of liver lesions is constrained as CT radiation doses are lowered; evidence suggests deep learning reconstructions mitigate such effects. Purpose To evaluate liver metastases and image quality between reduced-dose deep learning image reconstruction (DLIR) and standard-dose filtered back projection (FBP) contrast-enhanced abdominal CT. Materials and Methods In this prospective Health Insurance Portability and Accountability Act–compliant study (September 2019 through April 2021), participants with biopsy-proven colorectal cancer and liver metastases at baseline CT underwent standard-dose and reduced-dose portal venous abdominal CT in the same breath hold. Three radiologists detected and characterized lesions at standard-dose FBP and reduced-dose DLIR, reported confidence, and scored image quality. Contrast-to-noise ratios for liver metastases were recorded. Summary statistics were reported, and a generalized linear mixed model was used. Results Fifty-one participants (mean age ± standard deviation, 57 years ± 13; 31 men) were evaluated. The mean volume CT dose…

Background Portable, low-field-strength (0.064-T) MRI has the potential to transform neuroimaging but is limited by low spatial resolution and low signal-to-noise ratio. Purpose To implement a machine learning super-resolution algorithm that synthesizes higher spatial resolution images (1-mm isotropic) from lower resolution T1-weighted and T2-weighted portable brain MRI scans, making them amenable to automated quantitative morphometry. Materials and Methods An external high-field-strength MRI data set (1-mm isotropic scans from the Open Access Series of Imaging Studies data set) and segmentations for 39 regions of interest (ROIs) in the brain were used to train a super-resolution convolutional neural network (CNN). Secondary analysis of an internal test set of 24 paired low- and high-field-strength clinical MRI scans in participants with neurologic symptoms was performed. These were part of a prospective observational study (August 2020 to December 2021) at Massachusetts General Hospital (exclusion criteria: inability to lay flat, body habitus preventing low-field-strength MRI,…

Background After severe traumatic brain injury (sTBI), physicians use long-term prognostication to guide acute clinical care yet struggle to predict outcomes in comatose patients. Purpose To develop and evaluate a prognostic model combining deep learning of head CT scans and clinical information to predict long-term outcomes after sTBI. Materials and Methods This was a retrospective analysis of two prospectively collected databases. The model-building set included 537 patients (mean age, 40 years ± 17 [SD]; 422 men) from one institution from November 2002 to December 2018. Transfer learning and curriculum learning were applied to a convolutional neural network using admission head CT to predict mortality and unfavorable outcomes (Glasgow Outcomes Scale scores 1–3) at 6 months. This was combined with clinical input for a holistic fusion model. The models were evaluated using an independent internal test set and an external cohort of 220 patients with sTBI (mean age, 39 years ± 17; 166 men) from 18 institutions in the Transforming Research and Clinical Knowledge in Traumatic Brain…

Background The long-term pulmonary sequelae of COVID-19 is not well known. Purpose To characterize patterns and rates of improvement of chest CT abnormalities 1 year after COVID-19 pneumonia. Materials and Methods This was a secondary analysis of a prospective, multicenter observational cohort study conducted from April 29 to August 12, 2020, to assess pulmonary abnormalities at chest CT approximately 2, 3, and 6 months and 1 year after onset of COVID-19 symptoms. Pulmonary findings were graded for each lung lobe using a qualitative CT severity score (CTSS) ranging from 0 (normal) to 25 (all lobes involved). The association of demographic and clinical factors with CT abnormalities after 1 year was assessed with logistic regression. The rate of change of the CTSS at follow-up CT was investigated by using the Friedmann test. Results Of 142 enrolled participants, 91 underwent a 1-year follow-up CT examination and were included in the analysis (mean age, 59 years ± 13 [SD]; 35 women [38%]). In 49 of 91 (54%) participants, CT abnormalities were observed: 31 of 91 (34%) participants…

Background There is limited consensus regarding the relative diagnostic performance of cardiac MRI and fluorodeoxyglucose (FDG) PET for cardiac sarcoidosis. Purpose To perform a systematic review and meta-analysis to compare the diagnostic accuracy of cardiac MRI and FDG PET for cardiac sarcoidosis. Materials and Methods Medline, Ovid Epub, Cochrane Central Register of Controlled Trials, Embase, Emcare, and Scopus were searched from inception until January 2022. Inclusion criteria included studies that evaluated the diagnostic accuracy of cardiac MRI or FDG PET for cardiac sarcoidosis in adults. Data were independently extracted by two investigators. Summary accuracy metrics were obtained by using bivariate random-effects meta-analysis. Meta-regression was used to assess the effect of different covariates. Risk of bias was assessed using the Quality Assessment Tool for Diagnostic Accuracy Studies‐2 tool. The study protocol was registered a priori in the International Prospective Register of Systematic Reviews (Prospero protocol CRD42021214776). Results Thirty-three studies were…

Background Sarcopenia is frequently found in patients with cirrhosis and is associated with liver dysfunction, cirrhosis-related complications, and poorer quality of life. Purpose To evaluate changes in skeletal muscle and fat mass at CT and to evaluate the relationship of sarcopenia to mortality in patients with cirrhosis after transjugular intrahepatic portosystemic shunt (TIPS) placement. Materials and Methods Patients who underwent TIPS between August 2016 and May 2020 were included in this retrospective study. Skeletal muscle and fat mass were evaluated at CT at the L3 vertebra at baseline and at 2 months, 5 months, and 1 year after TIPS. Sarcopenia was defined as L3 skeletal muscle index (SMI) less than 50 cm2/m2 for men and less than 39 cm2/m2 for women. The primary end point was change in skeletal muscle and fat mass, and secondary end points included survival and the predictive factors for survival. Changes in skeletal muscle and fat mass over time were analyzed by generalized estimating equations. Results A total of 224 patients (159 men [113 with and 46 without…

Background There are limited data on the pattern and severity of myocardial injury in patients with COVID-19 vaccination–associated myocarditis. Purpose To describe myocardial injury following COVID-19 vaccination and to compare these findings to other causes of myocarditis. Materials and Methods In this retrospective cohort study, consecutive adult patients with myocarditis with at least one T1-based and at least one T2-based abnormality at cardiac MRI performed at a tertiary referral hospital from December 2019 to November 2021 were included. Patients were classified into one of three groups: myocarditis following COVID-19 vaccination, myocarditis following COVID-19 illness, and other myocarditis not associated with COVID-19 vaccination or illness. Results Of the 92 included patients, 21 (23%) had myocarditis following COVID-19 vaccination (mean age, 31 years ± 14 [SD]; 17 men; messenger RNA–1273 in 12 [57%] and BNT162b2 in nine [43%]). Ten of 92 (11%) patients had myocarditis following COVID-19 illness (mean age, 51 years ± 14; three men) and 61 of 92 (66%) patients had other…

Background Deep learning (DL)–based MRI reconstructions can reduce examination times for turbo spin-echo (TSE) acquisitions. Studies that prospectively employ DL-based reconstructions of rapidly acquired, undersampled spine MRI are needed. Purpose To investigate the diagnostic interchangeability of an unrolled DL-reconstructed TSE (hereafter, TSEDL) T1- and T2-weighted acquisition method with standard TSE and to test their impact on acquisition time, image quality, and diagnostic confidence. Materials and Methods This prospective single-center study included participants with various spinal abnormalities who gave written consent from November 2020 to July 2021. Each participant underwent two MRI examinations: standard fully sampled T1- and T2-weighted TSE acquisitions (reference standard) and prospectively undersampled TSEDL acquisitions with threefold and fourfold acceleration. Image evaluation was performed by five readers. Interchangeability analysis and an image quality–based analysis were used to compare the TSE and TSEDL images. Acquisition time and diagnostic confidence were…

Background Patients with mitral valve prolapse (MVP) may develop adverse outcomes even in the absence of mitral regurgitation or left ventricular (LV) dysfunction. Purpose To investigate the prognostic value of mitral annulus disjunction (MAD) and myocardial fibrosis at late gadolinium enhancement (LGE) cardiac MRI in patients with MVP without moderate-to-severe mitral regurgitation or LV dysfunction. Materials and Methods In this longitudinal retrospective study, 118 144 cardiac MRI studies were evaluated between October 2007 and June 2020 at 15 European tertiary medical centers. Follow-up was from the date of cardiac MRI examination to June 2020; the minimum and maximum follow-up intervals were 6 months and 156 months, respectively. Patients were excluded if at least one of the following conditions was present: cardiomyopathy, LV ejection fraction less than 40%, ischemic heart disease, congenital heart disease, inflammatory heart disease, moderate or worse mitral regurgitation, participation in competitive sport, or electrocardiogram suggestive of channelopathies. In the…

The Society of Radiologists in Ultrasound convened a panel of specialists from radiology, orthopedic surgery, and pathology to arrive at a consensus regarding the management of superficial soft-tissue masses imaged with US. The recommendations in this statement are based on analysis of current literature and common practice strategies. This statement reviews and illustrates the US features of common superficial soft-tissue lesions that may manifest as a soft-tissue mass and suggests guidelines for subsequent management.

Background A preoperative predictive model is needed that can be used to identify patients with lung adenocarcinoma (LUAD) who have a higher risk of recurrence or metastasis. Purpose To investigate associations between CT-based radiomic consensus clustering of stage I LUAD and clinical-pathologic features, genomic data, and patient outcomes. Materials and Methods Patients who underwent complete surgical resection for LUAD from April 2014 to December 2017 with preoperative CT and next-generation sequencing data were retrospectively identified. Comprehensive radiomic analysis was performed on preoperative CT images; tumors were classified as solid, ground glass, or mixed. Patients were clustered into groups based on their radiomics features using consensus clustering, and clusters were compared with tumor genomic alterations, histopathologic features, and recurrence-specific survival (Kruskal-Wallis test for continuous data, χ2 or Fisher exact test for categorical data, and log-rank test for recurrence-specific survival). Cluster analysis was performed on the entire cohort and on the…

Laparoscopic myomectomy, a common gynecologic operation in premenopausal women, has become heavily regulated since 2014 following the dissemination of unsuspected uterine leiomyosarcoma (LMS) throughout the pelvis of a physician treated for symptomatic leiomyoma. Research since that time suggests a higher prevalence than previously suspected of uterine LMS in resected masses presumed to represent leiomyoma, as high as one in 770 women (0.13%). Though rare, the dissemination of an aggressive malignant neoplasm due to noncontained electromechanical morcellation in laparoscopic myomectomy is a devastating outcome. Gynecologic surgeons' desire for an evidence-based, noninvasive evaluation for LMS is driven by a clear need to avoid such harms while maintaining the availability of minimally invasive surgery for symptomatic leiomyoma. Laparoscopic gynecologists could rely upon the distinction of higher-risk uterine masses preoperatively to plan oncologic surgery (ie, potential hysterectomy) for patients with elevated risk for LMS and, conversely, to safely offer women with no or minimal…

Background Infrapatellar fat pad (IPFP) quality has been implicated as a marker for predicting knee osteoarthritis (KOA); however, no valid quantification for subtle IPFP abnormalities has been established. Purpose To investigate whether MRI-based three-dimensional texture analysis of IPFP abnormalities could help predict incident radiographic KOA. Materials and Methods In this prospective nested case-control study, 690 participants whose knees were at risk for KOA were included from the Pivotal Osteoarthritis Initiative MRI Analyses incident osteoarthritis cohort. All knees had a Kellgren-Lawrence grade of 1 or less at baseline. During the 4-year follow-up, case participants were matched 1:1 to control participants, with incident radiographic KOA as the outcome. MRI scans were segmented at the incident time point of KOA (hereafter, P0), 1 year before P0 (hereafter, P-1), and baseline. MRI-based three-dimensional texture analysis was performed to extract IPFP texture features. Least absolute shrinkage and selection operator and multivariable logistic regressions were applied in the…

The design and analysis of multireader multicase (MRMC) studies are quite challenging. These studies differ from most medical studies because they need a reference standard and sampling from two populations (ie, reader and patient populations). They are quite expensive to conduct, requiring a good deal of readers' time for image interpretation. One common problem is the use of imperfect reference standards, often correlated with the test or tests being evaluated. Another common issue is oversimplification of the multidimensional MRMC data. In this study, the fundamentals of MRMC study design and analysis are reviewed. The goal is to provide investigators with a guide to the fundamentals of MRMC design and analysis, with references to more detailed discussions. In addition, readers are updated on newer areas of research, including correction for studies with multiple diagnostic accuracy end points and adjustment for location bias.

Abstract The frequency and extent of persistent sequelae in children and adolescents after infection with SARS-CoV-2 still needs to be comprehensively determined. In this cross-sectional clinical trial, we used non-invasive, label-free morphologic and free-breathing phase-resolved functional low-field magnetic resonance imaging (LF-MRI) to identify pulmonary changes in children and adolescents from 5 to <18 years after previously PCR-confirmed SARS-CoV-2 infection. While morphological pathologies were less frequent in children, functional LF-MRI visualized widespread ventilation, perfusion and combined ventilation/perfusion defects compared to healthy controls. The loss of functional lung parenchyma was more pronounced in long Covid than recovered patients. While pulmonary dysfunction was persistent even month after primary infection, LF-MRI demonstrated high capability to visualize and detect these changes in children and adolescents. ( Clinicaltrials.org ID NCT04990531 )

Background Microwave ablation (MWA) has attracted interest as a minimally invasive treatment for papillary thyroid carcinoma (PTC). However, comparisons between MWA and surgical resection (SR) in the management of T1N0M0 PTC are rare. Purpose To compare the technical effectiveness, disease progression, and complications of MWA and SR for solitary T1N0M0 PTC. Materials and Methods This retrospective study was conducted in a single center. A total of 1029 patients with T1N0M0 PTC treated with either MWA or SR from January 2015 to May 2021 were studied and divided into two groups according to treatment modality. Propensity score matching and inverse probability of treatment weighting were used to control for confounding factors. Disease progression was analyzed in T1N0M0 PTCs as well as T1a and T1b subgroups by using Kaplan-Meier curves and Cox proportional hazards regression models. Results A total of 404 patients (mean age, 43 years ± 12 [SD]; 289 women; 337 with T1a PTC) underwent MWA, and 625 (mean age, 46 years ± 12; 495 women; 521 with T1a PTC) underwent SR. During the follow-up…

Background The World Health Organization (WHO) recommends chest radiography to facilitate tuberculosis (TB) screening. However, chest radiograph interpretation expertise remains limited in many regions. Purpose To develop a deep learning system (DLS) to detect active pulmonary TB on chest radiographs and compare its performance to that of radiologists. Materials and Methods A DLS was trained and tested using retrospective chest radiographs (acquired between 1996 and 2020) from 10 countries. To improve generalization, large-scale chest radiograph pretraining, attention pooling, and semisupervised learning (“noisy-student”) were incorporated. The DLS was evaluated in a four-country test set (China, India, the United States, and Zambia) and in a mining population in South Africa, with positive TB confirmed with microbiological tests or nucleic acid amplification testing (NAAT). The performance of the DLS was compared with that of 14 radiologists. The authors studied the efficacy of the DLS compared with that of nine radiologists using the Obuchowski-Rockette-Hillis procedure. Given WHO…

Background Longitudinal data on the association of quantitative thigh muscle MRI markers with knee osteoarthritis (KOA) outcomes are scarce. These associations are of clinical importance, with potential use for thigh muscle–directed disease-modifying interventions. Purpose To measure KOA-associated longitudinal changes in MRI-derived muscle cross-sectional area (CSA) and adipose tissue and their association with downstream symptom worsening and knee replacement (KR). Materials and Methods In a secondary analysis of the Osteoarthritis Initiative multicenter prospective cohort (February 2004 through October 2015), knees of participants with available good-quality thigh MRI scans at baseline and at least one follow-up visit were included and classified as with and without KOA according to baseline radiographic Kellgren-Lawrence grade of 2 or higher and matched for confounders with use of propensity score matching. An automated deep learning model for thigh MRI two-dimensional segmentation was developed and tested. Markers of muscle CSA and intramuscular adipose tissue (intra-MAT) were…