Purpose
To assess the performance of a machine learning model trained with contrast-enhanced CT-based radiomics features in distinguishing benign from malignant solid renal masses and to compare ...model performance with three abdominal radiologists.
Methods
Patients who underwent intra-operative ultrasound during a partial nephrectomy were identified within our institutional database, and those who had pre-operative contrast-enhanced CT examinations were selected. The renal masses were segmented from the CT images and radiomics features were derived from the segmentations. The pathology of each mass was identified; masses were labeled as either benign oncocytoma or angiomyolipoma (AML) or malignant clear cell, papillary, or chromophobe renal cell carcinoma (RCC) depending on the pathology. The data were parsed into a 70/30 train/test split and a random forest machine learning model was developed to distinguish benign from malignant lesions. Three radiologists assessed the cohort of masses and labeled cases as benign or malignant.
Results
148 masses were identified from the cohort, including 50 benign lesions (23 AMLs, 27 oncocytomas) and 98 malignant lesions (23 clear cell RCC, 44 papillary RCC, and 31 chromophobe RCCs). The machine learning algorithm yielded an overall accuracy of 0.82 for distinguishing benign from malignant lesions, with an area under the receiver operating curve of 0.80. In comparison, the three radiologists had significantly lower accuracies (
p
= 0.02) ranging from 0.67 to 0.75.
Conclusion
A machine learning model trained with CT-based radiomics features can provide superior accuracy for distinguishing benign from malignant solid renal masses compared to abdominal radiologists.
The purpose of this study was to compare a navigator gated free breathing 3D Phase Sensitive Inversion Recovery (PSIR) TurboFLASH to an established 2D PSIR TurboFLASH method for detecting myocardial ...late gadolinium hyperenhanced lesions caused by infiltrative and non-ischemic cardiomyopathy. Under an IRB approved protocol; patients with suspected non-ischemic infiltrative myocardial heart disease were examined on a 1.5T MR scanner for late enhancement after the administration of gadolinium using a segmented 2D PSIR TurboFLASH sequence followed by a navigator-gated 3D PSIR TurboFLASH sequence. Two independent readers analyzed image quality using a four point Likert scale for qualitative analysis (0 = poor, non diagnostic; 1 = fair, diagnostic may be impaired; 2 = good, some artifacts but not interfering in diagnostics, 3 = excellent, no artifacts) and also reported presence or absence of scar. Detected scars were classified based on area and location and also compared quantitatively in volume. Twenty-seven patients were scanned using both protocols. Image quality score did not differ significantly (
p
= 0.358, Wilcoxon signed rank test) for both technique. Scars were detected in 24 patients. Larger numbers of hyperenhanced scars were detected with 3D PSIR (200) compared to 2D PSIR (167) and scar volume were significant larger in 3D PSIR (
p
= 0.004). The mean scar volume over all cases was 49.95 cm
3
for 2D PSIR and 70.02 cm
3
for 3D PSIR. The navigator gated free breathing 3D PSIR approach is a suitable method for detecting myocardial late gadolinium hyperenhanced lesions caused by non-ischemic cardiomyopathy due to its complete isotropic coverage of the left ventricle, improving detection of scar lesions compared to 2D PSIR imaging.
Background
General anesthesia (GA) or sedation has been used to obtain good-quality motion-free breath-hold chest CT scans in young children; however pulmonary atelectasis is a common and problematic ...accompaniment that can confound diagnostic utility. Dual-source multidetector CT permits ultrafast high-pitch sub-second examinations, minimizing motion artifact and potentially eliminating the need for a breath-hold.
Objective
The purpose of this study was to evaluate the feasibility of free-breathing ultrafast pediatric chest CT without GA and to compare it with breath-hold and non-breath-hold CT with GA.
Materials and methods
Young (≤3 years old) pediatric outpatients scheduled for chest CT under GA were recruited into the study and scanned using one of three protocols: GA with intubation, lung recruitment and breath-hold; GA without breath-hold; and free-breathing CT without anesthesia. In all three protocols an ultrafast high-pitch CT technique was used. We evaluated CT images for overall image quality, presence of atelectasis and motion artifacts.
Results
We included 101 scans in the study. However the GA non-breath-hold technique was discontinued after 15 scans, when it became clear that atelectasis was a major issue despite diligent attempts to mitigate it. This technique was therefore not included in statistical evaluation (86 remaining patients). Overall image quality was higher (
P
=0.001) and motion artifacts were fewer (
P
<.001) for scans using the GA with intubation and recruitment technique compared to scans in the non-GA free-breathing group. However no significant differences were observed regarding the presence of atelectasis between these groups.
Conclusion
We demonstrated that although overall image quality was best and motion artifact least with a GA-breath-hold intubation and recruitment technique, free-breathing ultrafast pediatric chest CT without anesthesia provides sufficient image quality for diagnostic purposes and can be successfully performed both without and with contrast agent in young infants.
Meeting abstractsEMPTY Summary The purpose of this study is to evaluate semi quantitative perfusion parameter maps generated based on a fully automated non-rigid motion correction during a first pass ...myocardial perfusion (FPMP) MRI in patients with suspected coronary artery disease (CAD) or coronary micro vascular disease (CMVD). Subendocardial defect is seen on stress FPMP images (top) and corresponding semi quantitative perfusion parameter maps (stress in the middle and rest in the botton) in a 67 years old woman with history of scleroderma and normal coronary angiography. figure omitted; refer to PDF Conclusions Semi quantitative perfusion parameter maps obtained by a fully automated non-rigid motion correction during a FPMP MRI correlated both qualitatively and quantitatively with the free breathing images in patients with epicardial CAD and CMVD.
From: 15th Annual SCMR Scientific Sessions Orlando, FL, USA 2-5 February 2012 Author details1-Division of Cardiology, Department of Medicine, Northwestern University, Feinberg School of Medicine, ...Chicago, IL, USAEMPTY2-Feinberg Cardiovascular Research Institute, Northwestern University, Feinberg School of Medicine, Chicago, IL, USAEMPTY3-Division of Cardiology, Department of Medicine, Washington University Medical School, St. Louis, MO, USAEMPTY4-Division of Cardiology, Department of Medicine, Hospital Universitario de Canarias, Tenerife, SpainEMPTY5-Division of Rheumatology, Department of Medicine, Northwestern University, Feinberg School of Medicine, Chicago, IL, USAEMPTY6-Department of Radiology, Northwestern University, Feinberg School of Medicine, Chicago, IL, USAEMPTY Supplemental Information: Myocardial extracellular volume fraction (Ve), derived from cardiac magnetic resonance (CMR) T1 mapping of the myocardium, has been shown to quantify diffuse myocardial fibrosis (DMF) - but its utility in SSc has not been studied.
Purpose
To compare the precision and interobserver agreement of ventricular volume, function, and mass quantification by 3D time‐resolved (4D) flow MRI relative to cine steady‐state free precession ...(SSFP).
Materials and Methods
With Institutional Research Board approval, informed consent, and HIPAA compliance, 22 consecutive patients with congenital heart disease (CHD) (10 males, 6.4 ± 4.8 years) referred for 3T ferumoxytol‐enhanced cardiac MRI were prospectively recruited. Complete ventricular coverage with standard 2D short‐axis cine SSFP and whole chest coverage with axial 4D flow were obtained. Two blinded radiologists independently segmented images for left ventricular (LV) and right ventricular (RV) myocardium at end systole (ES) and end diastole (ED). Statistical analysis included linear regression, analysis of variance (ANOVA), Bland–Altman (BA) analysis, and intraclass correlation (ICC).
Results
Significant positive correlations were found between 4D flow and SSFP for ventricular volumes (r = 0.808–0.972, P < 0.001), ejection fraction (EF) (r = 0.900–928, P < 0.001), and mass (r = 0.884–0.934, P < 0.001). BA relative limits of agreement for both ventricles were between –52% to 34% for volumes, –29% to 27% for EF, and –41% to 48% for mass, with wider limits of agreement for the RV compared to the LV. There was no significant difference between techniques with respect to mean square difference of ED‐ES mass for either LV (F = 2.05, P = 0.159) or RV (F = 0.625, P = 0.434). Interobserver agreement was moderate to good with both 4D flow (ICC 0.523–0.993) and SSFP (ICC 0.619–0.982), with overlapping confidence intervals.
Conclusion
Quantification of ventricular volume, function, and mass can be accomplished with 4D flow MRI with precision and interobserver agreement comparable to that of cine SSFP. J. Magn. Reson. Imaging 2016;44:383–392.
Patients with Loeys-Dietz syndrome demonstrate a heightened risk of distal thoracic aortic events after valve-sparing aortic root replacement. This study assesses the clinical risks and hemodynamic ...consequences of a prophylactic aortic arch replacement strategy in Loeys-Dietz syndrome and characterizes smooth muscle cell phenotype in Loeys-Dietz syndrome aneurysmal and normal-sized downstream aorta.
Patients with genetically confirmed Loeys-Dietz syndrome (n = 8) underwent prophylactic aortic arch replacement during valve-sparing aortic root replacement. Four-dimensional flow magnetic resonance imaging studies were performed in 4 patients with Loeys-Dietz syndrome (valve-sparing aortic root replacement + arch) and compared with patients with contemporary Marfan syndrome (valve-sparing aortic root replacement only, n = 5) and control patients (without aortopathy, n = 5). Aortic tissues from 4 patients with Loeys-Dietz syndrome and 2 organ donors were processed for anatomically segmented single-cell RNA sequencing and histologic assessment.
Patients with Loeys-Dietz syndrome valve-sparing aortic root replacement + arch had no deaths, major morbidity, or aortic events in a median of 2 years follow-up. Four-dimensional magnetic resonance imaging demonstrated altered flow parameters in patients with postoperative aortopathy relative to controls, but no clear deleterious changes due to arch replacement. Integrated analysis of aortic single-cell RNA sequencing data (>49,000 cells) identified a continuum of abnormal smooth muscle cell phenotypic modulation in Loeys-Dietz syndrome defined by reduced contractility and enriched extracellular matrix synthesis, adhesion receptors, and transforming growth factor-beta signaling. These modulated smooth muscle cells populated the Loeys-Dietz syndrome tunica media with gradually reduced density from the overtly aneurysmal root to the nondilated arch.
Patients with Loeys-Dietz syndrome demonstrated excellent surgical outcomes without overt downstream flow or shear stress disturbances after concomitant valve-sparing aortic root replacement + arch operations. Abnormal smooth muscle cell–mediated aortic remodeling occurs within the normal diameter, clinically at-risk Loeys-Dietz syndrome arch segment. These initial clinical and pathophysiologic findings support concomitant arch replacement in Loeys-Dietz syndrome.