Try a new search

Format these results:

Searched for:



Total Results:


Deep Learning Reconstruction Enables Highly Accelerated Biparametric MR Imaging of the Prostate

Johnson, Patricia M; Tong, Angela; Donthireddy, Awani; Melamud, Kira; Petrocelli, Robert; Smereka, Paul; Qian, Kun; Keerthivasan, Mahesh B; Chandarana, Hersh; Knoll, Florian
BACKGROUND:Early diagnosis and treatment of prostate cancer (PCa) can be curative; however, prostate-specific antigen is a suboptimal screening test for clinically significant PCa. While prostate magnetic resonance imaging (MRI) has demonstrated value for the diagnosis of PCa, the acquisition time is too long for a first-line screening modality. PURPOSE/OBJECTIVE:To accelerate prostate MRI exams, utilizing a variational network (VN) for image reconstruction. STUDY TYPE/METHODS:Retrospective. SUBJECTS/METHODS:One hundred and thirteen subjects (train/val/test: 70/13/30) undergoing prostate MRI. FIELD STRENGTH/SEQUENCE/UNASSIGNED:3.0 T; a T2 turbo spin echo (TSE) T2-weighted image (T2WI) sequence in axial and coronal planes, and axial echo-planar diffusion-weighted imaging (DWI). ASSESSMENT/RESULTS:, and apparent diffusion coefficient map-according to the Prostate Imaging Reporting and Data System (PI-RADS v2.1), for both VN and standard reconstructions. Accuracy of PI-RADS ≥3 for clinically significant cancer was computed. Projected scan time of the retrospectively under-sampled biparametric exam was also computed. STATISTICAL TESTS/UNASSIGNED:One-sided Wilcoxon signed-rank test was used for comparison of image quality. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for lesion detection and grading. Generalized estimating equation with cluster effect was used to compare differences between standard and VN bp-MRI. A P-value of <0.05 was considered statistically significant. RESULTS:(Reader 1: 3.20 ± 0.70 (Standard), 3.40 ± 0.75 (VN) P = 0.98; Reader 2: 2.85 ± 0.81 (Standard), 3.00 ± 0.79 (VN) P = 0.93; Reader 3: 4.45 ± 0.72 (Standard), 4.05 ± 0.69 (VN) P = 0.02; Reader 4: 4.50 ± 0.69 (Standard), 4.45 ± 0.76 (VN) P = 0.50). In the lesion evaluation study, there was no significant difference in the number of PI-RADS ≥3 lesions identified on standard vs. VN bp-MRI (P = 0.92, 0.59, 0.87) with similar sensitivity and specificity for clinically significant cancer. The average scan time of the standard clinical biparametric exam was 11.8 minutes, and this was projected to be 3.2 minutes for the accelerated exam. DATA CONCLUSION/UNASSIGNED:Diagnostic accelerated biparametric prostate MRI exams can be performed using deep learning methods in <4 minutes, potentially enabling rapid screening prostate MRI. LEVEL OF EVIDENCE/METHODS:3 TECHNICAL EFFICACY: Stage 5.
PMID: 34877735
ISSN: 1522-2586
CID: 5110242

Diagnostic abdominal MR imaging on a prototype low-field 0.55 T scanner operating at two different gradient strengths

Chandarana, Hersh; Bagga, Barun; Huang, Chenchan; Dane, Bari; Petrocelli, Robert; Bruno, Mary; Keerthivasan, Mahesh; Grodzki, David; Block, Kai Tobias; Stoffel, David; Sodickson, Daniel K
PURPOSE:To develop a protocol for abdominal imaging on a prototype 0.55 T scanner and to benchmark the image quality against conventional 1.5 T exam. METHODS:In this prospective IRB-approved HIPAA-compliant study, 10 healthy volunteers were recruited and imaged. A commercial MRI system was modified to operate at 0.55 T (LF) with two different gradient performance levels. Each subject underwent non-contrast abdominal examinations on the 0.55 T scanner utilizing higher gradients (LF-High), lower adjusted gradients (LF-Adjusted), and a conventional 1.5 T scanner. The following pulse sequences were optimized: fat-saturated T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and Dixon T1-weighted imaging (T1WI). Three readers independently evaluated image quality in a blinded fashion on a 5-point Likert scale, with a score of 1 being non-diagnostic and 5 being excellent. An exact paired sample Wilcoxon signed-rank test was used to compare the image quality. RESULTS:Diagnostic image quality (overall image quality score ≥ 3) was achieved at LF in all subjects for T2WI, DWI, and T1WI with no more than one unit lower score than 1.5 T. The mean difference in overall image quality score was not significantly different between LF-High and LF-Adjusted for T2WI (95% CI - 0.44 to 0.44; p = 0.98), DWI (95% CI - 0.43 to 0.36; p = 0.92), and for T1 in- and out-of-phase imaging (95%C I - 0.36 to 0.27; p = 0.91) or T1 fat-sat (water only) images (95% CI - 0.24 to 0.18; p = 1.0). CONCLUSION:Diagnostic abdominal MRI can be performed on a prototype 0.55 T scanner, either with conventional or with reduced gradient performance, within an acquisition time of 10 min or less.
PMID: 34415411
ISSN: 2366-0058
CID: 5048652

Multi-Center Follow-up Study to Develop a Classification System Which Differentiates Mucinous Cystic Neoplasm of the Liver and Benign Hepatic Cyst Using Machine Learning

Hardie, Andrew D; Chamberlin, Jordan H; Boyum, James H; Sharbidre, Kedar G; Petrocelli, Robert; Flemming, Brian P; Zahid, Mohd; Venkatesh, Sudhakar K; Mruthyunjayappa, Smitha; Hajdu, Cristina H; Kovacs, Mark D
RATIONALE AND OBJECTIVES/OBJECTIVE:To date, no clinically useful classification system has been developed for reliably differentiating mucinous cystic neoplasm (MCN) from a benign hepatic cyst (BHC) in the liver. The objective was to use machine learning and a multi-center study design to develop and assess the performance of a novel classification system for predicting whether a hepatic cystic lesion represents MCN or BHC. MATERIALS AND METHODS/METHODS:A multi-center cohort study identified 154 surgically resected hepatic cystic lesions in 154 subjects which were pathologic confirmed as MCN (43) or BHC (111). Readers at each institution recorded seven pre-determined imaging features previously identified as potential differentiating features from prior publications. The contribution of each of these features to differentiating MCN from BHC was assessed by machine learning to develop an optimal classification system. RESULTS:Although several of the assessed imaging features demonstrated statistical significance, only 3 imaging features were found by machine learning to significantly contribute to a potential classification system: (1) solid enhancing nodule (2) all septations arising from an external macro-lobulation (3) whether the lesion was solitary or one of multiple cystic liver lesions. The optimal classification system had only four categories and correctly identified 144/154 lesion (93.5%). CONCLUSION/CONCLUSIONS:This multi-center follow-up study was able to use machine learning to develop a highly accurate classification system for differentiation of hepatic MCN from BHC, which could be readily applied to clinical practice.
PMID: 34598868
ISSN: 1878-4046
CID: 5067612

Computed Tomography Enterography

Petrocelli, Robert; Dane, Bari
Computed tomography enterography (CTE) is an abdominopelvic computed tomography (CT) tailored for evaluation of the small bowel. This multidetector CT examination uses neutral oral contrast to optimally distend small bowel. Patients are scanned after the rapid injection of intravenous contrast during peak bowel wall enhancement. CTE is excellent for the evaluation of many small bowel disorders, particularly Crohn's disease. The purpose of this article is to review CTE indications, contraindications, technique, safety considerations, and imaging findings of common small bowel diseases.
ISSN: 1546-0843
CID: 5009252

Neuro-invasion by a zoonotic arbovirus [Case Report]

Iluyomade, Adedapo; Wander, Praneet; Gupta, Akriti; Petrocelli, Robert; Jones, James
PMID: 27681554
ISSN: 0972-9062
CID: 4507422

Nutrient Excess and AMPK Downregulation in Incubated Skeletal Muscle and Muscle of Glucose Infused Rats

Coughlan, Kimberly A; Balon, Thomas W; Valentine, Rudy J; Petrocelli, Robert; Schultz, Vera; Brandon, Amanda; Cooney, Gregory J; Kraegen, Edward W; Ruderman, Neil B; Saha, Asish K
We have previously shown that incubation for 1h with excess glucose or leucine causes insulin resistance in rat extensor digitorum longus (EDL) muscle by inhibiting AMP-activated protein kinase (AMPK). To examine the events that precede and follow these changes, studies were performed in rat EDL incubated with elevated levels of glucose or leucine for 30min-2h. Incubation in high glucose (25mM) or leucine (100μM) significantly diminished AMPK activity by 50% within 30min, with further decreases occurring at 1 and 2h. The initial decrease in activity at 30min coincided with a significant increase in muscle glycogen. The subsequent decreases at 1h were accompanied by phosphorylation of αAMPK at Ser485/491, and at 2h by decreased SIRT1 expression and increased PP2A activity, all of which have previously been shown to diminish AMPK activity. Glucose infusion in vivo, which caused several fold increases in plasma glucose and insulin, produced similar changes but with different timing. Thus, the initial decrease in AMPK activity observed at 3h was associated with changes in Ser485/491 phosphorylation and SIRT1 expression and increased PP2A activity was a later event. These findings suggest that both ex vivo and in vivo, multiple factors contribute to fuel-induced decreases in AMPK activity in skeletal muscle and the insulin resistance that accompanies it.
PMID: 25996822
ISSN: 1932-6203
CID: 4507412

Plasma Branch Chain and Aromatic Amino Acid Levels are Associated with Insulin Resistance in Nonalcoholic Fatty Liver Disease (NAFLD) [Meeting Abstract]

Sunny, Nishanth E.; Lomonaco, Romina; Petrocelli, Robert; Bashir, Usman; Egan, Austin; Cusi, Kenneth
ISSN: 0892-6638
CID: 4507432