Background There is a need for reliable noninvasive methods for diagnosing and monitoring nonalcoholic fatty liver disease (NAFLD). Thus, the multidisciplinary Non-invasive Biomarkers of Metabolic Liver disease (NIMBLE) consortium was formed to identify and advance the regulatory qualification of NAFLD imaging biomarkers. Purpose To determine the different-day same-scanner repeatability coefficient of liver MRI biomarkers in patients with NAFLD at risk for steatohepatitis. Materials and Methods NIMBLE 1.2 is a prospective, observational, single-center short-term cross-sectional study (October 2021 to June 2022) in adults with NAFLD across a spectrum of low, intermediate, and high likelihood of advanced fibrosis as determined according to the fibrosis based on four factors (FIB-4) index. Participants underwent up to seven MRI examinations across two visits less than or equal to 7 days apart. Standardized imaging protocols were implemented with six MRI scanners from three vendors at both 1.5 T and 3 T, with central analysis of the data performed by an independent reading center (University of California, San Diego). Trained analysts, who were blinded to clinical data, measured the MRI proton density fat fraction (PDFF), liver stiffness at MR elastography (MRE), and visceral adipose tissue (VAT) for each participant. Point estimates and CIs were calculated using χ2 distribution and statistical modeling for pooled repeatability measures. Results A total of 17 participants (mean age, 58 years ± 8.5 [SD]; 10 female) were included, of which seven (41.2%), six (35.3%), and four (23.5%) participants had a low, intermediate, or high likelihood of advanced fibrosis, respectively. The different-day same-scanner mean measurements were 13%-14% for PDFF, 6.6 L for VAT, and 3.15 kPa for two-dimensional MRE stiffness. The different-day same-scanner repeatability coefficients were 0.22 L (95% CI: 0.17, 0.29) for VAT, 0.75 kPa (95% CI: 0.6, 0.99) for MRE stiffness, 1.19% (95% CI: 0.96, 1.61) for MRI PDFF using magnitude reconstruction, 1.56% (95% CI: 1.26, 2.07) for MRI PDFF using complex reconstruction, and 19.7% (95% CI: 15.8, 26.2) for three-dimensional MRE shear modulus. Conclusion This preliminary study suggests that thresholds of 1.2%-1.6%, 0.22 L, and 0.75 kPa for MRI PDFF, VAT, and MRE, respectively, should be used to discern measurement error from real change in patients with NAFLD. ClinicalTrials.gov registration no. NCT05081427 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Kozaka and Matsui in this issue.

Background Contrast-enhanced (CE) US has been studied for use in the detection of residual viable hepatocellular carcinoma (HCC) after locoregional therapy, but multicenter data are lacking. Purpose To compare two-dimensional (2D) and three-dimensional (3D) CE US diagnostic performance with that of CE MRI or CT, the current clinical standard, in the detection of residual viable HCC after transarterial chemoembolization (TACE) in a prospective multicenter trial. Materials and Methods Participants aged at least 21 years with US-visible HCC scheduled for TACE were consecutively enrolled at one of three participating academic medical centers from May 2016 to March 2022. Each underwent baseline 2D and 3D CE US before TACE, 2D and 3D CE US 1-2 weeks and/or 4-6 weeks after TACE, and CE MRI or CT 4-6 weeks after TACE. CE US and CE MRI or CT were evaluated by three fellowship-trained radiologists for the presence or absence of viable tumors and were compared with reference standards of pathology (18%), angiography on re-treatment after identification of residual disease at 1-2-month follow-up imaging (31%), 4-8-month CE MRI or CT (42%), or short-term (approximately 1-2 months) CE MRI or CT if clinically decompensated and estimated viability was greater than 50% at imaging (9%). Diagnostic performance criteria, including sensitivity and specificity, were obtained for each modality and time point with generalized estimating equation analysis. Results A total of 132 participants were included (mean age, 64 years ± 7 [SD], 87 male). Sensitivity of 2D CE US 4-6 weeks after TACE was 91% (95% CI: 84, 95), which was higher than that of CE MRI or CT (68%; 95% CI: 58, 76; P < .001). Sensitivity of 3D CE US 4-6 weeks after TACE was 89% (95% CI: 81, 94), which was higher than that of CE MRI or CT (P < .001), with no evidence of a difference from 2D CE US (P = .22). CE MRI or CT had 85% (95% CI: 76, 91) specificity, higher than that of 4-6-week 2D and 3D CE US (70% [95% CI: 56, 80] and 67% [95% CI: 53, 78], respectively; P = .046 and P = .023, respectively). No evidence of differences in any diagnostic criteria were observed between 1-2-week and 4-6-week 2D CE US (P > .21). Conclusion The 2D and 3D CE US examinations 4-6 weeks after TACE revealed higher sensitivity in the detection of residual HCC than CE MRI or CT, albeit with lower specificity. Importantly, CE US performance was independent of follow-up time. Clinical trial registration no. NCT02764801 © RSNA, 2023 Supplemental material is available for this article.

Background Screening for nonalcoholic fatty liver disease (NAFLD) is suboptimal due to the subjective interpretation of US images. Purpose To evaluate the agreement and diagnostic performance of radiologists and a deep learning model in grading hepatic steatosis in NAFLD at US, with biopsy as the reference standard. Materials and Methods This retrospective study included patients with NAFLD and control patients without hepatic steatosis who underwent abdominal US and contemporaneous liver biopsy from September 2010 to October 2019. Six readers visually graded steatosis on US images twice, 2 weeks apart. Reader agreement was assessed with use of κ statistics. Three deep learning techniques applied to B-mode US images were used to classify dichotomized steatosis grades. Classification performance of human radiologists and the deep learning model for dichotomized steatosis grades (S0, S1, S2, and S3) was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. Results The study included 199 patients (mean age, 53 years ± 13 [SD]; 101 men). On the test set (n = 52), radiologists had fair interreader agreement (0.34 [95% CI: 0.31, 0.37]) for classifying steatosis grades S0 versus S1 or higher, while AUCs were between 0.49 and 0.84 for radiologists and 0.85 (95% CI: 0.83, 0.87) for the deep learning model. For S0 or S1 versus S2 or S3, radiologists had fair interreader agreement (0.30 [95% CI: 0.27, 0.33]), while AUCs were between 0.57 and 0.76 for radiologists and 0.73 (95% CI: 0.71, 0.75) for the deep learning model. For S2 or lower versus S3, radiologists had fair interreader agreement (0.37 [95% CI: 0.33, 0.40]), while AUCs were between 0.52 and 0.81 for radiologists and 0.67 (95% CI: 0.64, 0.69) for the deep learning model. Conclusion Deep learning approaches applied to B-mode US images provided comparable performance with human readers for detection and grading of hepatic steatosis. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Tuthill in this issue.

Background Because of the global increase in the incidence of nonalcoholic fatty liver disease, the development of noninvasive, widely available, and highly accurate methods for assessing hepatic steatosis is necessary. Purpose To evaluate the performance of models with different combinations of quantitative US parameters for their ability to predict at least 5% steatosis in patients with chronic liver disease (CLD) as defined using MRI proton density fat fraction (PDFF). Materials and Methods Patients with CLD were enrolled in this prospective multicenter study between February 2020 and April 2021. Integrated backscatter coefficient (IBSC), signal-to-noise ratio (SNR), and US-guided attenuation parameter (UGAP) were measured in all participants. Participant MRI PDFF value was used to define at least 5% steatosis. Four models based on different combinations of US parameters were created: model 1 (UGAP alone), model 2 (UGAP with IBSC), model 3 (UGAP with SNR), and model 4 (UGAP with IBSC and SNR). Diagnostic performance of all models was assessed using area under the receiver operating characteristic curve (AUC). The model was internally validated using 1000 bootstrap samples. Results A total of 582 participants were included in this study (median age, 64 years; IQR, 52-72 years; 274 female participants). There were 364 participants in the steatosis group and 218 in the nonsteatosis group. The AUC values for steatosis diagnosis in models 1-4 were 0.92, 0.93, 0.95, and 0.96, respectively. The C-indexes of models adjusted by the bootstrap method were 0.92, 0.93, 0.95, and 0.96, respectively. Compared with other models, models 3 and 4 demonstrated improved discrimination of at least 5% steatosis (P < .01). Conclusion A model built using the quantitative US parameters UGAP, IBSC, and SNR could accurately discriminate at least 5% steatosis in patients with CLD. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Han in this issue.

The implementation of low-dose chest CT for lung screening presents a crucial opportunity to advance lung cancer care through early detection and interception. In addition, millions of pulmonary nodules are incidentally detected annually in the United States, increasing the opportunity for early lung cancer diagnosis. Yet, realization of the full potential of these opportunities is dependent on the ability to accurately analyze image data for purposes of nodule classification and early lung cancer characterization. This review presents an overview of traditional image analysis approaches in chest CT using semantic characterization as well as more recent advances in the technology and application of machine learning models using CT-derived radiomic features and deep learning architectures to characterize lung nodules and early cancers. Methodological challenges currently faced in translating these decision aids to clinical practice, as well as the technical obstacles of heterogeneous imaging parameters, optimal feature selection, choice of model, and the need for well-annotated image data sets for the purposes of training and validation, will be reviewed, with a view toward the ultimate incorporation of these potentially powerful decision aids into routine clinical practice.

Background Few studies have evaluated the role of artificial intelligence (AI) in prior screening mammography. Purpose To examine AI risk scores assigned to screening mammography in women who were later diagnosed with breast cancer. Materials and Methods Image data and screening information of examinations performed from January 2004 to December 2019 as part of BreastScreen Norway were used in this retrospective study. Prior screening examinations from women who were later diagnosed with cancer were assigned an AI risk score by a commercially available AI system (scores of 1-7, low risk of malignancy; 8-9, intermediate risk; and 10, high risk of malignancy). Mammographic features of the cancers based on the AI score were also assessed. The association between AI score and mammographic features was tested with a bivariate test. Results A total of 2787 prior screening examinations from 1602 women (mean age, 59 years ± 5.1 [SD]) with screen-detected (n = 1016) or interval (n = 586) cancers showed an AI risk score of 10 for 389 (38.3%) and 231 (39.4%) cancers, respectively, on the mammograms in the screening round prior to diagnosis. Among the screen-detected cancers with AI scores available two screening rounds (4 years) before diagnosis, 23.0% (122 of 531) had a score of 10. Mammographic features were associated with AI score for invasive screen-detected cancers (P < .001). Density with calcifications was registered for 13.6% (43 of 317) of screen-detected cases with a score of 10 and 4.6% (15 of 322) for those with a score of 1-7. Conclusion More than one in three cases of screen-detected and interval cancers had the highest AI risk score at prior screening, suggesting that the use of AI in mammography screening may lead to earlier detection of breast cancers. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Mehta in this issue.

Background The benefits of using low-field-strength fetal MRI to evaluate antenatal development include reduced image artifacts, increased comfort, larger bore size, and potentially reduced costs, but studies about fetal low-field-strength MRI are lacking. Purpose To evaluate the reliability and feasibility of low-field-strength fetal MRI to assess anatomic and functional measures in pregnant participants using a commercially available 0.55-T MRI scanner and a comprehensive 20-minute protocol. Materials and Methods This prospective study was performed at a large teaching hospital (St Thomas' Hospital; London, England) from May to November 2022 in healthy pregnant participants and participants with pregnancy-related abnormalities using a commercially available 0.55-T MRI scanner. A 20-minute protocol was acquired including anatomic T2-weighted fast-spin-echo, quantitative T2*, and diffusion sequences. Key measures like biparietal diameter, transcerebellar diameter, lung volume, and cervical length were evaluated by two radiologists and an MRI-experienced obstetrician. Functional organ-specific mean values were given. Comparison was performed with existing published values and higher-field MRI using linear regression, interobserver correlation, and Bland-Altman plots. Results A total of 79 fetal MRI examinations were performed (mean gestational age, 29.4 weeks ± 5.5 [SD] [age range, 17.6-39.3 weeks]; maternal age, 34.4 years ± 5.3 [age range, 18.4-45.5 years]) in 47 healthy pregnant participants (control participants) and in 32 participants with pregnancy-related abnormalities. The key anatomic two-dimensional measures for the 47 healthy participants agreed with large cross-sectional 1.5-T and 3-T control studies. The interobserver correlations for the biparietal diameter in the first 40 consecutive scans were 0.96 (95% CI: 0.7, 0.99; P = .002) for abnormalities and 0.93 (95% CI: 0.86, 0.97; P < .001) for control participants. Functional features, including placental and brain T2* and placental apparent diffusion coefficient values, strongly correlated with gestational age (mean placental T2* in the control participants: 5.2 msec of decay per week; R2 = 0.66; mean T2* at 30 weeks, 176.6 msec; P < .001). Conclusion The 20-minute low-field-strength fetal MRI examination protocol was capable of producing reliable structural and functional measures of the fetus and placenta in pregnancy. Clinical trial registration no. REC 21/LO/0742 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Gowland in this issue.

In 1971, the first patient CT examination by Ambrose and Hounsfield paved the way for not only volumetric imaging of the brain but of the entire body. From the initial 5-minute scan for a 180° rotation to today's 0.24-second scan for a 360° rotation, CT technology continues to reinvent itself. This article describes key historical milestones in CT technology from the earliest days of CT to the present, with a look toward the future of this essential imaging modality. After a review of the beginnings of CT and its early adoption, the technical steps taken to decrease scan times-both per image and per examination-are reviewed. Novel geometries such as electron-beam CT and dual-source CT have also been developed in the quest for ever-faster scans and better in-plane temporal resolution. The focus of the past 2 decades on radiation dose optimization and management led to changes in how exposure parameters such as tube current and tube potential are prescribed such that today, examinations are more customized to the specific patient and diagnostic task than ever before. In the mid-2000s, CT expanded its reach from gray-scale to color with the clinical introduction of dual-energy CT. Today's most recent technical innovation-photon-counting CT-offers greater capabilities in multienergy CT as well as spatial resolution as good as 125 μm. Finally, artificial intelligence is poised to impact both the creation and processing of CT images, as well as automating many tasks to provide greater accuracy and reproducibility in quantitative applications.

Background Artificial intelligence (AI) algorithms have shown high accuracy for detection of pulmonary embolism (PE) on CT pulmonary angiography (CTPA) studies in academic studies. Purpose To determine whether use of an AI triage system to detect PE on CTPA studies improves radiologist performance or examination and report turnaround times in a clinical setting. Materials and Methods This prospective single-center study included adult participants who underwent CTPA for suspected PE in a clinical practice setting. Consecutive CTPA studies were evaluated in two phases, first by radiologists alone (n = 31) (May 2021 to June 2021) and then by radiologists aided by a commercially available AI triage system (n = 37) (September 2021 to December 2021). Sixty-two percent of radiologists (26 of 42 radiologists) interpreted studies in both phases. The reference standard was determined by an independent re-review of studies by thoracic radiologists and was used to calculate performance metrics. Diagnostic accuracy and turnaround times were compared using Pearson χ2 and Wilcoxon rank sum tests. Results Phases 1 and 2 included 503 studies (participant mean age, 54.0 years ± 17.8 [SD]; 275 female, 228 male) and 1023 studies (participant mean age, 55.1 years ± 17.5; 583 female, 440 male), respectively. In phases 1 and 2, 14.5% (73 of 503) and 15.9% (163 of 1023) of CTPA studies were positive for PE (P = .47). Mean wait time for positive PE studies decreased from 21.5 minutes without AI to 11.3 minutes with AI (P < .001). The accuracy and miss rate, respectively, for radiologist detection of any PE on CTPA studies was 97.6% and 12.3% without AI and 98.6% and 6.1% with AI, which was not significantly different (P = .15 and P = .11, respectively). Conclusion The use of an AI triage system to detect any PE on CTPA studies improved wait times but did not improve radiologist accuracy, miss rate, or examination and report turnaround times. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Murphy and Tee in this issue.

CT systems equipped with photon-counting detectors (PCDs), referred to as photon-counting CT (PCCT), are beginning to change imaging in several subspecialties, such as cardiac, vascular, thoracic, and musculoskeletal radiology. Evidence has been building in the literature underpinning the many advantages of PCCT for different clinical applications. These benefits derive from the distinct features of PCDs, which are made of semiconductor materials capable of converting photons directly into electric signal. PCCT advancements include, among the most important, improved spatial resolution, noise reduction, and spectral properties. PCCT spatial resolution on the order of 0.25 mm allows for the improved visualization of small structures (eg, small vessels, arterial walls, distal bronchi, and bone trabeculations) and their pathologies, as well as the identification of previously undetectable anomalies. In addition, blooming artifacts from calcifications, stents, and other dense structures are reduced. The benefits of the spectral capabilities of PCCT are broad and include reducing radiation and contrast material dose for patients. In addition, multiple types of information can be extracted from a single data set (ie, multiparametric imaging), including quantitative data often regarded as surrogates of functional information (eg, lung perfusion). PCCT also allows for a novel type of CT imaging, K-edge imaging. This technique, combined with new contrast materials specifically designed for this modality, opens the door to new applications for imaging in the future.