Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans.

BACKGROUND: Treatment and preventative advances for chronic obstructive pulmonary disease (COPD) have been slow due, in part, to limited subphenotypes. We tested if unsupervised machine learning on CT images would discover CT emphysema subtypes with distinct characteristics, prognoses and genetic associations. METHODS: New CT emphysema subtypes were identified by unsupervised machine learning on only the texture and location of emphysematous regions on CT scans from 2853 participants in the Subpopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS), a COPD case-control study, followed by data reduction. Subtypes were compared with symptoms and physiology among 2949 participants in the population-based Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study and with prognosis among 6658 MESA participants. Associations with genome-wide single-nucleotide-polymorphisms were examined. RESULTS: The algorithm discovered six reproducible (interlearner intraclass correlation coefficient, 0.91-1.00) CT emphysema subtypes. The most common subtype in SPIROMICS, the combined bronchitis-apical subtype, was associated with chronic bronchitis, accelerated lung function decline, hospitalisations, deaths, incident airflow limitation and a gene variant near DRD1, which is implicated in mucin hypersecretion (p=1.1 ×10-8). The second, the diffuse subtype was associated with lower weight, respiratory hospitalisations and deaths, and incident airflow limitation. The third was associated with age only. The fourth and fifth visually resembled combined pulmonary fibrosis emphysema and had distinct symptoms, physiology, prognosis and genetic associations. The sixth visually resembled vanishing lung syndrome. CONCLUSION: Large-scale unsupervised machine learning on CT scans defined six reproducible, familiar CT emphysema subtypes that suggest paths to specific diagnosis and personalised therapies in COPD and pre-COPD.

Associations of hiatus hernia with CT-based interstitial lung changes: the MESA Lung Study.

BACKGROUND: Hiatus hernia (HH) is prevalent in adults with pulmonary fibrosis. We hypothesised that HH would be associated with markers of lung inflammation and fibrosis among community-dwelling adults and stronger among MUC5B (rs35705950) risk allele carriers. METHODS: In the Multi-Ethnic Study of Atherosclerosis, HH was assessed from cardiac and full-lung computed tomography (CT) scans performed at Exam 1 (2000-2002, n=3342) and Exam 5 (2010-2012, n=3091), respectively. Percentage of high attenuation areas (HAAs; percentage of voxels with attenuation between -600 and -250 HU) was measured from cardiac and lung scans. Interstitial lung abnormalities (ILAs) were examined from Exam 5 scans (n=2380). Regression models were used to examine the associations of HH with HAAs, ILAs and serum matrix metalloproteinase-7 (MMP-7), and adjusted for age, sex, race/ethnicity, educational attainment, smoking, height, weight and scanner parameters for HAA analysis. RESULTS: HH detected from Exam 5 scans was associated with a mean percentage difference in HAAs of 2.23% (95% CI 0.57-3.93%) and an increase of 0.48% (95% CI 0.07-0.89%) per year, particularly in MUC5B risk allele carriers (p-value for interaction=0.02). HH was associated with ILAs among those <80 years of age (OR for ILAs 1.78, 95% CI 1.14-2.80) and higher serum MMP-7 level among smokers (p-value for smoking interaction=0.04). CONCLUSIONS: HH was associated with more HAAs over time, particularly among MUC5B risk allele carriers, and ILAs in younger adults, and may be a risk factor in the early stages of interstitial lung disease.

QSM Throughout the Body.

Magnetic materials in tissue, such as iron, calcium, or collagen, can be studied using quantitative susceptibility mapping (QSM). To date, QSM has been overwhelmingly applied in the brain, but is increasingly utilized outside the brain. QSM relies on the effect of tissue magnetic susceptibility sources on the MR signal phase obtained with gradient echo sequence. However, in the body, the chemical shift of fat present within the region of interest contributes to the MR signal phase as well. Therefore, correcting for the chemical shift effect by means of water-fat separation is essential for body QSM. By employing techniques to compensate for cardiac and respiratory motion artifacts, body QSM has been applied to study liver iron and fibrosis, heart chamber blood and placenta oxygenation, myocardial hemorrhage, atherosclerotic plaque, cartilage, bone, prostate, breast calcification, and kidney stone.

Effect of Averaging Measurements From Multiple MRI Pulse Sequences on Kidney Volume Reproducibility in Autosomal Dominant Polycystic Kidney Disease.

BACKGROUND: Total kidney volume (TKV) is an important biomarker for assessing kidney function, especially for autosomal dominant polycystic kidney disease (ADPKD). However, TKV measurements from a single MRI pulse sequence have limited reproducibility, ± ~5%, similar to ADPKD annual kidney growth rates. PURPOSE: To improve TKV measurement reproducibility on MRI by extending artificial intelligence algorithms to automatically segment kidneys on T1-weighted, T2-weighted, and steady state free precession (SSFP) sequences in axial and coronal planes and averaging measurements. STUDY TYPE: Retrospective training, prospective testing. SUBJECTS: Three hundred ninety-seven patients (356 with ADPKD, 41 without), 75% for training and 25% for validation, 40 ADPKD patients for testing and 17 ADPKD patients for assessing reproducibility. FIELD STRENGTH/SEQUENCE: T2-weighted single-shot fast spin echo (T2), SSFP, and T1-weighted 3D spoiled gradient echo (T1) at 1.5 and 3T. ASSESSMENT: 2D U-net segmentation algorithm was trained on images from all sequences. Five observers independently measured each kidney volume manually on axial T2 and using model-assisted segmentations on all sequences and image plane orientations for two MRI exams in two sessions separated by 1-3 weeks to assess reproducibility. Manual and model-assisted segmentation times were recorded. STATISTICAL TESTS: Bland-Altman, Schapiro-Wilk (normality assessment), Pearson's chi-squared (categorical variables); Dice similarity coefficient, interclass correlation coefficient, and concordance correlation coefficient for analyzing TKV reproducibility. P-value < 0.05 was considered statistically significant. RESULTS: In 17 ADPKD subjects, model-assisted segmentations of axial T2 images were significantly faster than manual segmentations (2:49 minute vs. 11:34 minute), with no significant absolute percent difference in TKV (5.9% vs. 5.3%, P = 0.88) between scans 1 and 2. Absolute percent differences between the two scans for model-assisted segmentations on other sequences were 5.5% (axial T1), 4.5% (axial SSFP), 4.1% (coronal SSFP), and 3.2% (coronal T2). Averaging measurements from all five model-assisted segmentations significantly reduced absolute percent difference to 2.5%, further improving to 2.1% after excluding an outlier. DATA CONCLUSION: Measuring TKV on multiple MRI pulse sequences in coronal and axial planes is practical with deep learning model-assisted segmentations and can improve TKV measurement reproducibility more than 2-fold in ADPKD. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 1.

Axillary Lymphadenopathy After a COVID-19 Vaccine Booster Dose: Time to Resolution on Ultrasound Follow-Up and Associated Factors.

BACKGROUND. Because administration of booster doses of COVID-19 vaccines is ongoing, radiologists are continuing to encounter COVID-19 vaccine-related axillary lymphadenopathy on imaging. OBJECTIVE. The purposes of this study were to assess time to resolution of COVID-19 vaccine-related axillary lymphadenopathy identified on breast ultrasound after administration of a booster dose and to assess factors potentially associated with time to resolution. METHODS. This retrospective single-institution study included 54 patients (mean age, 57 years) with unilateral axillary lymphadenopathy ipsilateral to the site of injection of a booster dose of messenger RNA COVID-19 vaccine visualized on ultrasound (whether an initial breast imaging examination or follow-up to prior screening or diagnostic breast imaging) performed between September 1, 2021, and December 31, 2022, and who underwent follow-up ultrasound examinations until resolution of lymphadenopathy. Patient information was extracted from the EMR. Univariable and multivariable linear regression analyses were used to identify predictors of time to resolution. Time to resolution was compared with that in a previously described sample of 64 patients from the study institution that was used to evaluate time to resolution of axillary lymphadenopathy after the initial vaccination series. RESULTS. Six of the 54 patients had a history of breast cancer, and two had symptoms related to axillary lymphadenopathy (axillary pain in both patients). Among the 54 initial ultrasound examinations showing lymphadenopathy, 33 were screening examinations and 21 were diagnostic examinations. Lymphadenopathy had resolved a mean of 102 ± 56 (SD) days after administration of the booster dose and 84 ± 49 days after the initial ultrasound showing lymphadenopathy. Age, vaccine booster type (Moderna vs Pfizer-BioNTech), and history of breast cancer were not significantly associated with time to resolution in univariable or multivariable analyses (all p > .05). Time to resolution after administration of a booster dose was significantly shorter than time to resolution after administration of the first dose in the initial series (mean, 129 ± 37 days) (p = .01). CONCLUSION. Axillary lymphadenopathy after administration of a COVID-19 vaccine booster dose has a mean time to resolution of 102 days, shorter than the time to resolution after the initial vaccination series. CLINICAL IMPACT. The time to resolution after administration of a booster dose supports the current recommendation for a follow-up interval of at least 12 weeks when vaccine-related lymphadenopathy is suspected.

Imaging modalities for confirming pulmonary embolism during pregnancy: results from a multicenter international study.

OBJECTIVES: We explored the variations in use of imaging modalities for confirming pulmonary embolism (PE) according to the trimester of pregnancy. METHODS: We included all pregnant patients with confirmed acute PE from RIETE, a prospective registry of patients with PE (03/2001-02/2020). Imaging modalities included computed tomography pulmonary angiography (CTPA), ventilation-perfusion (V/Q) scan, or presence of signs of acute PE along with imaging-confirmed proximal deep vein thrombosis (pDVT) without pulmonary vascular imaging. We compared the imaging modalities to postpartum patients with PE, and other non-pregnant women with PE. RESULTS: There were 157 pregnant patients (age: 32.7 ± 0.5), 228 postpartum patients (age: 33.9 ± 0.5), and 23,937 non-pregnant non-postpartum women (age: 69.5 ± 0.1). CTPA was the most common modality for confirming PE, from 55.7% in first trimester to 58.3% in second trimester, and 70.0% in third trimester. From first trimester to third trimester, V/Q scanning was used in 21.3%, 16.7%, and 18.3% of cases, respectively. Confirmed pDVT along with the presence of signs/symptoms of PE was the confirmatory modality for PE in 21.3% of patients in first trimester, 19.4% in second trimester, and 6.7% in third trimester. The proportion of postpartum patients confirmed with CTPA (85.5%) was comparable to that of non-pregnant non-postpartum women (83.2%). From the first trimester of pregnancy to postpartum period, there was a linear increase in the proportion of patients with PE diagnosed with CTPA (p = 0.039). CONCLUSION: CTPA was the primary modality for confirming PE in all trimesters of pregnancy, although its proportional use was higher in later stages of pregnancy. KEY POINTS: • Computed tomography pulmonary angiography (CTPA) was the primary modality of diagnosis in all trimesters of pregnancy among patients with confirmed pulmonary embolism, even in the first trimester. • From the first trimester of pregnancy to postpartum period, there was a linear increase in the proportion of patients with pulmonary embolism who were diagnosed based on CTPA. • In the postpartum period, use of CTPA as the modality to confirm pulmonary embolism was comparable to non-pregnant patients.

Time for Resolution of COVID-19 Vaccine-Related Axillary Lymphadenopathy and Associated Factors.

BACKGROUND. The variable clinical course of subclinical lymphadenopathy detected on breast imaging after COVID-19 vaccination creates management challenges and has led to evolving practice recommendations. OBJECTIVE. The purpose of this study was to assess the duration of axillary lymphadenopathy ipsilateral to COVID-19 vaccination detected by breast imaging and to assess factors associated with the time until resolution. METHODS. This retrospective single-center study included 111 patients (mean age, 52 ± 12 years) with unilateral axillary lymphadenopathy ipsilateral to mRNA COVID-19 vaccine administration performed within the prior 8 weeks that was detected on breast ultrasound performed between January 1, 2021, and October 1, 2021, and who underwent follow-up ultrasound examinations at 4- to 12-week intervals until resolution of the lymphadenopathy. Patient information was extracted from medical records. Cortical thickness of the largest axillary lymph node on ultrasound was retrospectively measured and was considered enlarged when greater than 3 mm. Multivariable linear regression analysis was used to identify independent predictors of time until resolution. RESULTS. The mean cortical thickness at the initial ultrasound examination was 4.7 ± 1.2 mm. The lymphadenopathy resolved a mean of 97 ± 44 days after the initial ultrasound examination, 127 ± 43 days after the first vaccine dose, and 2.4 ± 0.6 follow-up ultrasound examinations. A significant independent predictor of shorter time to resolution was Pfizer-BioNTech (rather than Moderna) vaccination (ß = -18.0 [95% CI, -34.3 to -1.7]; p = .03]. Significant independent predictors of longer time to resolution were receipt of the second dose after the initial ultrasound examination (ß = 19.2 [95% CI, 3.1-35.2]; p = .02) and greater cortical thickness at the initial ultrasound examination (ß = 8.0 [95% CI, 1.5-14.5]; p = .02). Patient age, history of breast cancer, and axillary symptoms were not significantly associated with time to resolution (all p > .05). CONCLUSION. Axillary lymphadenopathy detected with breast ultrasound after COVID-19 mRNA vaccination lasts longer than reported in initial vaccine clinical trials. CLINICAL IMPACT. The prolonged time to resolution supports not delaying screening mammography because of recent COVID-19 vaccination. It also supports the professional society recommendation of a follow-up interval of at least 12 weeks when vaccine-related lymphadenopathy is suspected.

MR Angiography Series: Abdominal and Pelvic MR Angiography.

This review guides readers through the selection and setup of standardized MR angiography (MRA) protocols for the abdomen and pelvis for common clinical applications. Topics covered include renovascular MRA in potential kidney donors and in patients with hypertension; hepatic and mesenteric MRA in potential liver donors, patients with portal hypertension, and patients with chronic mesenteric ischemia; pelvic MRA for pretreatment planning before uterine fibroid embolization and in patients with pelvic congestion syndrome; and abdominal wall MRA for planning of breast reconstructive surgery. This module is the fifth in a series created on behalf of the Society for Magnetic Resonance Angiography (SMRA), a group of researchers and clinicians who are passionate about the benefits of MRA but understand its challenges. The full digital presentation is available online. ©RSNA, 2022.

Major hemorrhage and mortality in COVID-19 patients on therapeutic anticoagulation for venous thromboembolism.

We observed multiple fatal intracranial hemorrhages shortly after initiating therapeutic anticoagulation for treatment of venous thromboembolism (VTE) in COVID-19 patients suggesting increased anticoagulation risk associated with COVID-19. The objective of this study is to quantify risk of major hemorrhage in hospitalized COVID-19 patients on therapeutic anticoagulation for deep venous thrombosis (DVT) or pulmonary embolism (PE). Hospitalized patients with COVID-19 receiving therapeutic anticoagulation for DVT, PE or both at four New York City hospitals were evaluated for hemorrhagic complications. These were categorized as major (including fatal) or clinically relevant non-major according to the criteria of the International Society of Thrombosis and Haemostasis. Hemorrhagic complications were correlated with clinical and laboratory data, ICD-10 code diagnoses and type of anticoagulation treatment. Minor hemorrhages were excluded. Major/clinically relevant hemorrhages occurred in 36 of 170 (21%) hospitalized COVID-19 patients being treated with therapeutic anticoagulation for VTE including 4 (2.4%) fatal hemorrhages. Hemorrhage was 3.4 times more likely with unfractionated heparin 27/76 (36%) compared to 8/81 (10%) with low molecular weight heparin (p = 0.002). Multivariate analysis showed that major hemorrhage was associated with intubation (p = 0.04) and elevated serum LDH (p < 0.001) and low fibrinogen (p = 0.05). Increased risk of hemorrhagic complications in treating VTE in hospitalized COVID-19 patients should be considered especially when using unfractionated heparin, in intubated patients, with low fibrinogen and/or elevated LDH. Checking serum fibrinogen and LDH before initiating therapeutic anticoagulation and monitoring coagulation parameters frequently may reduce bleeding complications.

Machine Learning Based Prediction Model for Closed-Loop Small Bowel Obstruction Using Computed Tomography and Clinical Findings.

PURPOSE: The aim of the study was to develop a prediction model for closed-loop small bowel obstruction integrating computed tomography (CT) and clinical findings. METHODS: The radiology database and surgical reports from 2 suburban teaching hospitals were retrospectively reviewed for patients undergoing surgery for suspected closed-loop small bowel obstruction (CLSBO). Two observers independently reviewed the CT scans for the presence of imaging features of CLSBO, blinded to the surgically confirmed diagnosis and clinical parameters. Random forest analysis was used to train and validate a prediction model for CLSBO, by combining CT and clinical findings, after randomly splitting the sample into 80% training and 20% test subsets. RESULTS: Surgery confirmed CLSBO in 185 of 223 patients with clinically suspected CLSBO. Age greater than 52 years showed 2.82 (95% confidence interval = 1.13-4.77) times higher risk for CLSBO (P = 0.021). Sensitivity/specificity of CT findings included proximal dilatation (97/5%), distal collapse (96/2%), mesenteric edema (94/5%), pneumatosis (1/100%), free air (1/98%), and portal venous gas (0/100%). The random forest model combining imaging/clinical findings yielded an area under receiver operating curve of 0.73 (95% confidence interval = 0.58-0.94), sensitivity of 0.72 (0.55-0.85), specificity of 0.8 (0.28-0.99), and accuracy of 0.73 (0.57-0.85). Prior surgery, age, lactate, whirl sign, U/C-shaped bowel configuration, and fecalization were the most important variables in predicting CLSBO. CONCLUSIONS: A random forest model found clinical factors including prior surgery, age, lactate, and imaging factors including whirl sign, fecalization, and U/C-shaped bowel configuration are helpful in improving the prediction of CLSBO. Individual CT findings in CLSBO had either high sensitivity or specificity, suggesting that accurate diagnosis requires systematic assessment of all CT signs.

Pulmonary Embolism in Hospitalized Patients with COVID-19: A Multicenter Study.

Background Pulmonary embolism (PE) commonly complicates SARS-CoV-2 infection, but incidence and mortality reported in single-center studies, along with risk factors, vary. Purpose To determine the incidence of PE in patients with COVID-19 and its associations with clinical and laboratory parameters. Materials and Methods In this HIPAA-compliant study, electronic medical records were searched retrospectively for demographic, clinical, and laboratory data and outcomes among patients with COVID-19 admitted at four hospitals from March through June 2020. PE found at CT pulmonary angiography and perfusion scintigraphy was correlated with clinical and laboratory parameters. The d-dimer level was used to predict PE, and the obtained threshold was externally validated among 85 hospitalized patients with COVID-19 at a fifth hospital. The association between right-sided heart strain and embolic burden was evaluated in patients with PE undergoing echocardiography. Results A total of 413 patients with COVID-19 (mean age, 60 years ± 16 [standard deviation]; age range, 20-98 years; 230 men) were evaluated. PE was diagnosed in 102 (25%; 95% CI: 21, 29) of 413 hospitalized patients with COVID-19 who underwent CT pulmonary angiography or perfusion scintigraphy. PE was observed in 21 (29%; 95% CI: 19, 41) of 73 patients in the intensive care unit (ICU) versus 81 (24%; 95% CI: 20, 29) of 340 patients who were not in the ICU (P = .37). PE was associated with male sex (odds ratio [OR], 1.74; 95% CI: 1.1, 2.8; P = .02); smoking (OR, 1.86; 95% CI: 1.0, 3.4; P = .04); and increased d-dimer (P < .001), lactate dehydrogenase (P < .001), ferritin (P = .001), and interleukin-6 (P = .02) levels. Mortality in hospitalized patients was similar between patients with PE and those without PE (14% [13 of 102]; 95% CI: 8, 22] vs 13% [40 of 311]; 95% CI: 9, 17; P = .98), suggesting that diagnosis and treatment of PE were not associated with excess mortality. The d-dimer levels greater than 1600 ng/mL [8.761 nmol/L] helped predict PE with 100% sensitivity and 62% specificity in an external validation cohort. Embolic burden was higher in patients with right-sided heart strain among the patients with PE undergoing echocardiography (P = .03). Conclusion Pulmonary embolism (PE) incidence was 25% in patients hospitalized with COVID-19 suspected of having PE. A d-dimer level greater than 1600 ng/mL [8.761 nmol/L] was sensitive for identification of patients who needed CT pulmonary angiography. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Ketai in this issue.

Deep neural network for water/fat separation: Supervised training, unsupervised training, and no training.

PURPOSE: To use a deep neural network (DNN) for solving the optimization problem of water/fat separation and to compare supervised and unsupervised training. METHODS: The current T2∗ -IDEAL algorithm for solving water/fat separation is dependent on initialization. Recently, DNN has been proposed to solve water/fat separation without the need for suitable initialization. However, this approach requires supervised training of DNN using the reference water/fat separation images. Here we propose 2 novel DNN water/fat separation methods: 1) unsupervised training of DNN (UTD) using the physical forward problem as the cost function during training, and 2) no training of DNN using physical cost and backpropagation to directly reconstruct a single dataset. The supervised training of DNN, unsupervised training of DNN, and no training of DNN methods were compared with the reference T2∗ -IDEAL. RESULTS: All DNN methods generated consistent water/fat separation results that agreed well with T2∗ -IDEAL under proper initialization. CONCLUSION: The water/fat separation problem can be solved using unsupervised deep neural networks.

Quantitative transport mapping (QTM) of the kidney with an approximate microvascular network.

PURPOSE: Proof-of-concept study of mapping renal blood flow vector field according to the inverse solution to a mass transport model of time resolved tracer-labeled MRI data. THEORY AND METHODS: To determine tissue perfusion according to the underlying physics of spatiotemporal tracer concentration variation, the mass transport equation is integrated over a voxel with an approximate microvascular network for fitting time-resolved tracer imaging data. The inverse solution to the voxelized transport equation provides the blood flow vector field, which is referred to as quantitative transport mapping (QTM). A numerical microvascular network modeling the kidney with computational fluid dynamics reference was used to verify the accuracy of QTM and the current Kety's method that uses a global arterial input function. Multiple post-label delay arterial spin labeling (ASL) of the kidney on seven subjects was used to assess QTM in vivo feasibility. RESULTS: Against the ground truth in the numerical model, the error in flow estimated by QTM (18.6%) was smaller than that in Kety's method (45.7%, 2.5-fold reduction). The in vivo kidney perfusion quantification by QTM (cortex: 443 ± 58 mL/100 g/min and medulla: 190 ± 90 mL/100 g/min) was in the range of that by Kety's method (482 ± 51 mL/100 g/min in the cortex and 242 ± 73 mL/100 g/min in the medulla), and QTM provided better flow homogeneity in the cortex region. CONCLUSIONS: QTM flow velocity mapping is feasible from multi-delay ASL MRI data based on inverting the transport equation. In a numerical simulation, QTM with deconvolution in space and time provided more accurate perfusion quantification than Kety's method with deconvolution in time only.

Integrated quantitative susceptibility and R2 * mapping for evaluation of liver fibrosis: An ex vivo feasibility study.

To develop a method for noninvasive evaluation of liver fibrosis, we investigated the differential sensitivities of quantitative susceptibility mapping (QSM) and R2 * mapping using corrections for the effects of liver iron. Liver fibrosis is characterized by excessive accumulation of collagen and other extracellular matrix proteins. While collagen increases R2 * relaxation, measures of R2 * for fibrosis are confounded by liver iron, which may be present in the liver over a wide range of concentrations. The diamagnetic collagen contribution to susceptibility values measured by QSM is much less than the contribution of highly paramagnetic iron. In 19 ex vivo liver explants with and without fibrosis, QSM (χ), R2 * and proton density fat fraction (PDFF) maps were constructed from multiecho gradient-recalled echo (mGRE) sequence acquisition at 3 T. Median parameter values were recorded and differences between the MRI parameters in nonfibrotic vs. advanced fibrotic/cirrhotic samples were evaluated using Mann-Whitney U tests and receiver operating characteristic analyses. Logistic regression with stepwise feature selection was employed to evaluate the utility of combined MRI measurements for detection of fibrosis. Median R2 * increased in fibrotic vs. nonfibrotic liver samples (P = .041), while differences in χ and PDFF were nonsignificant (P = .545 and P = .395, respectively). Logistic regression identified the combination of χ and R2 * significant for fibrosis detection (logit [prediction] = -8.45 + 0.23 R2 * - 28.8 χ). For this classifier, a highly significant difference between nonfibrotic vs. advanced fibrotic/cirrhotic samples was observed (P = .002). The model exhibited an AUC of 0.909 (P = .003) for detection of advanced fibrosis/cirrhosis, which was substantially higher compared with AUCs of the individual parameters (AUC 0.591-0.784). An integrated QSM and R2 * analysis of mGRE 3 T imaging data is promising for noninvasive diagnostic assessment of liver fibrosis.

Hemorrhagic Cysts and Other MR Biomarkers for Predicting Renal Dysfunction Progression in Autosomal Dominant Polycystic Kidney Disease.

BACKGROUND: Screening for rapidly progressing autosomal dominant polycystic kidney disease (ADPKD) is necessary for assigning and monitoring therapies. Height-adjusted total kidney volume (ht-TKV) is an accepted biomarker for clinical prognostication, but represents only a small fraction of information on abdominal MRI. PURPOSE: To investigate the utility of other MR features of ADPKD to predict progression. STUDY TYPE: Single-center retrospective. POPULATION: Longitudinal data from 186 ADPKD subjects with baseline serum creatinine, PKD gene testing, abdominal MRI measurements, and ≥2 follow-up serum creatinine were reviewed. FIELD STRENGTH/SEQUENCE: 1.5T, T2 -weighted single-shot fast spin echo, T1 -weighted 3D spoiled gradient echo (liver accelerated volume acquisition) and 2D cine velocity encoded gradient echo (phase contrast MRA). ASSESSMENT: Ht-TKV, renal blood flow (RBF), number and fraction of renal and hepatic cysts, bright T1 hemorrhagic renal cysts, and liver and spleen volumes were independently assessed by three observers blinded to estimated glomerular filtration rate (eGFR) data. STATISTICAL TESTS: Linear mixed-effect models were applied to predict eGFR over time using MRI features at baseline adjusted for confounders. Validation was performed in 158 patients who had follow-up MRI using receiver operator characteristic, sensitivity, and specificity. RESULTS: Hemorrhagic cysts, fraction of renal and hepatic cysts, height-adjusted liver and spleen volumes were significant independent predictors of future eGFR (final prediction model R2 = 0.88 P < 0.05). The number of hemorrhagic cysts significantly improved the prediction compared to ht-TKV in predicting future eGFR (area under the curve [AUC] = 0.94, 95% confidence interval [CI]: 0.9-0.94 vs. R2 = 0.9, 95% CI: 0.85-0.9, P = 0.045). For baseline eGFR ≥60 ml/min/1.73m2 , sensitivity for predicting eGFR<45 ml/min/1.73m2 by ht-TKV alone was 29%. Sensitivity increased to 72% with all MRI variables in the model (P < 0.05 = 0.019), whereas specificity was unchanged, 100% vs. 99%. DATA CONCLUSION: Combining multiple MR features including hemorrhagic renal cysts, renal cyst fraction, liver and spleen volume, hepatic cyst fraction, and renal blood flow enhanced sensitivity for predicting eGFR decline in ADPKD compared to the standard model including only ht-TKV. Level of Evidence 2 Technical Efficacy Stage 2 J. MAGN. RESON. IMAGING 2021;53:564-576.

Utilization of radiomics to predict long-term outcome of magnetic resonance-guided focused ultrasound ablation therapy in adenomyosis.

OBJECTIVE: To develop and evaluate a T2 MR-based radiomics prediction model incorporating radiomics features and clinical parameters to predict the response to magnetic resonance-guided focused ultrasound surgery (MRgFUS) in patients with adenomyosis. MATERIALS AND METHODS: Sixty-nine patients (mean age, 38.6 years; age range, 26-50 years) with adenomyosis treated by MRgFUS were reviewed and allocated to training (n = 48) and testing cohorts (n = 21). One thousand one hundred eighteen radiomics features were extracted from T2-weighted imaging before MRgFUS. The radiomics features' dimension was reduced by Pearson correlation coefficient after normalization. Analysis of variance and logistical regression were used for feature selection by fivefold cross-validation in the training cohort, and the machine learning model was constructed for comparing the clinical model, radiomics model, and radiomics-clinical model which combined survived radiomics features and clinical parameters. The discrimination result of the model was obtained by bootstrap; receiver operating characteristic curve, area under the curve (AUC), and decision curve analyses were performed to illustrate the model performance in both the training and testing cohorts. RESULTS: Good response was achieved in 47 patients (68.1%) and failed in 22 patients (38.9%). The radiomics model comprised four selected features and demonstrated a degree of prediction capability of patients' poor response to MRgFUS treatment. The radiomics-clinical model showed good discrimination, with an AUC of 0.81 (95% confidence interval, 0.592-0.975) in the testing cohort. The decision curve analysis also showed favorable performance of the radiomics-clinical model. CONCLUSIONS: A prediction model composed of T2WI-based radiomics features and clinical parameters could be applied to guide the radiologist to evaluate MRgFUS for patients with adenomyosis who will achieve good response. KEY POINTS: • Magnetic resonance imaging-guided focused ultrasound surgery represents an alternative treatment for adenomyosis, but nearly one third of patients remain symptomatic 6 months after MRgFUS. • Combining four radiomics features of T2-weighted MRI with eight clinical features further improves prediction of poor responders to MR-guided focused ultrasound treatment of uterine adenomyosis (AUC = 0.81 in the testing cohort). • The radiomics model based on T2-weighted imaging combined with clinical parameters can help predict which patients are likely to have a good response to MRgFUS for adenomyosis.

Human airway branch variation and chronic obstructive pulmonary disease.

Susceptibility to chronic obstructive pulmonary disease (COPD) beyond cigarette smoking is incompletely understood, although several genetic variants associated with COPD are known to regulate airway branch development. We demonstrate that in vivo central airway branch variants are present in 26.5% of the general population, are unchanged over 10 y, and exhibit strong familial aggregation. The most common airway branch variant is associated with COPD in two cohorts (n = 5,054), with greater central airway bifurcation density, and with emphysema throughout the lung. The second most common airway branch variant is associated with COPD among smokers, with narrower airway lumens in all lobes, and with genetic polymorphisms within the FGF10 gene. We conclude that central airway branch variation, readily detected by computed tomography, is a biomarker of widely altered lung structure with a genetic basis and represents a COPD susceptibility factor.

Dipole modeling of multispectral signal for detecting metallic biopsy markers during MRI-guided breast biopsy: a pilot study.

PURPOSE: During MRI-guided breast biopsy, a metallic biopsy marker is deployed at the biopsy site to guide future interventions. Conventional MRI during biopsy cannot distinguish such markers from biopsy site air, and a post-biopsy mammogram is therefore performed to localize marker placement. The purpose of this pilot study is to develop dipole modeling of multispectral signal (DIMMS) as an MRI alternative to eliminate the cost, inefficiency, inconvenience, and ionizing radiation of a mammogram for biopsy marker localization. METHODS: DIMMS detects and localizes the biopsy marker by fitting the measured multispectral imaging (MSI) signal to the MRI signal model and marker properties. MSI was performed on phantoms containing titanium biopsy markers and air to illustrate the clinical challenge that DIMMS addresses and on 20 patients undergoing MRI-guided breast biopsy to assess DIMMS feasibility for marker detection. DIMMS was compared to conventional MSI field map thresholding, using the post-procedure mammogram as the reference standard. RESULTS: Biopsy markers were detected and localized in 20 of 20 cases using MSI with automated DIMMS post-processing (using a threshold of 0.7) and in 18 of 20 cases using MSI field mapping (using a threshold of 0.65 kHz). CONCLUSION: MSI with DIMMS post-processing is a feasible technique for biopsy marker detection and localization during MRI-guided breast biopsy. With a 2-min MSI scan, DIMMS is a promising MRI alternative to the standard-of-care post-biopsy mammogram.

Deep semantic lung segmentation for tracking potential pulmonary perfusion biomarkers in chronic obstructive pulmonary disease (COPD): The multi-ethnic study of atherosclerosis COPD study.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is associated with high morbidity and mortality. Identification of imaging biomarkers for phenotyping is necessary for future treatment and therapy monitoring. However, translation of visual analytic pipelines into clinics or their use in large-scale studies is significantly slowed by time-consuming postprocessing steps. PURPOSE: To implement an automated tool chain for regional quantification of pulmonary microvascular blood flow in order to reduce analysis time and user variability. STUDY TYPE: Prospective. POPULATION: In all, 90 MRI scans of 63 patients, of which 31 had a COPD with a mean Global Initiative for Chronic Obstructive Lung Disease status of 1.9 ± 0.64 (µ ± σ). FIELD STRENGTH/SEQUENCE: 1.5T dynamic gadolinium-enhanced MRI measurement using 4D dynamic contrast material-enhanced (DCE) time-resolved angiography acquired in a single breath-hold in inspiration. [Correction added on August 20, 2019, after first online publication: The field strength in the preceding sentence was corrected.] ASSESSMENT: We built a 3D convolutional neural network for semantic segmentation using 29 manually segmented perfusion maps. All five lobes of the lung are denoted, including the middle lobe. Evaluation was performed on 61 independent cases from two sites of the Multi-Ethnic Study of Arteriosclerosis (MESA)-COPD study. We publish our implementation of a model-free deconvolution filter according to Sourbron et al for 4D DCE MRI scans as open source. STATISTICAL TEST: Cross-validation 29/61 (# training / # testing), intraclass correlation coefficient (ICC), Spearman ρ, Pearson r, Sørensen-Dice coefficient, and overlap. RESULTS: Segmentations and derived clinical parameters were processed in ~90 seconds per case on a Xeon E5-2637v4 workstation with Tesla P40 GPUs. Clinical parameters and predicted segmentations exhibit high concordance with the ground truth regarding median perfusion for all lobes with an ICC of 0.99 and a Sørensen-Dice coefficient of 93.4 ± 2.8 (µ ± σ). DATA CONCLUSION: We present a robust end-to-end pipeline that allows for the extraction of perfusion-based biomarkers for all lung lobes in 4D DCE MRI scans by combining model-free deconvolution with deep learning. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:571-579.

Cardiac structural changes after transcatheter aortic valve replacement: systematic review and meta-analysis of cardiovascular magnetic resonance studies.

BACKGROUND: Transcatheter aortic valve replacement (TAVR) is increasingly used to treat patients with severe aortic stenosis (AS). Cardiovascular magnetic resonance imaging (CMR) provides reliable and reproducible estimates for assessment of cardiac structure and function after TAVR. The goal of this study was to conduct a systematic review and meta-analysis of the literature to assess left ventricular (LV) volumes, mass and function by CMR after TAVR. METHODS: Using Meta-analysis of Observational Studies in Epidemiology (MOOSE) guidelines, we searched PubMed and Embase for studies reporting CMR findings before and at least 1 month after TAVR. Main factors of interest were LV end-diastolic volume index (LVEDVi), LV end-systolic volume index (LVESVi), LV mass index (LVMi), and left ventricular ejection fraction (LVEF). Standardized mean differences (SMD) were pooled by random effects meta-analytic techniques. RESULTS: Of 453 screened publications, 10 studies (published between 2012 and 2018) were included. A total of 305 patients completed pre- and post-TAVR follow-up CMR (mean age range 78.6-85.0 years, follow-up range 6-15 months). Random effects analysis showed TAVR resulted in reduced LVEDVi (SMD: -0.25, 95% CI: - 0.43 to - 0.07, P = 0.006), LVESVi (SMD: -0.24, 95% CI: - 0.44 to - 0.05, P = 0.01), LVMi (SMD: -0.82, 95% CI: - 1.0 to - 0.63, P < 0.001) and increased LVEF (SMD: 22, 95% CI: 6 to 38%, P = 0.006). Heterogeneity across studies was low (I2: 0%, Pheterogeneity > 0.05 for all). The median reduction was 4 ml/m2 (IQR: 3.1 to 8.2) for LVEDVi, 5 ml/m2 (IQR: 3.0 to 6.0) for LVESVi, and 15.1 g/m2 (IQR: 11.8 to 18.3) for LVMi. The median increase for LVEF was 3.4% (IQR 1.0 to 4.6%). CONCLUSIONS: CMR demonstrates reverse LV remodeling occurrs within 6-15 months after TAVR, with reductions in LVEDVi, LVESVi and LVMi, and increased LVEF.