scholarly journals Applying Deep Learning to Accelerated Clinical Brain Magnetic Resonance Imaging for Multiple Sclerosis

2021 ◽  
Vol 12 ◽  
Author(s):  
Ashika Mani ◽  
Tales Santini ◽  
Radhika Puppala ◽  
Megan Dahl ◽  
Shruthi Venkatesh ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Image Quality ◽  
Repeated Measures ◽  
Financial Burden ◽  
Brain Magnetic Resonance Imaging ◽  
Lesion Volume ◽  
Patient Reported

Background: Magnetic resonance (MR) scans are routine clinical procedures for monitoring people with multiple sclerosis (PwMS). Patient discomfort, timely scheduling, and financial burden motivate the need to accelerate MR scan time. We examined the clinical application of a deep learning (DL) model in restoring the image quality of accelerated routine clinical brain MR scans for PwMS.Methods: We acquired fast 3D T1w BRAVO and fast 3D T2w FLAIR MRI sequences (half the phase encodes and half the number of slices) in parallel to conventional parameters. Using a subset of the scans, we trained a DL model to generate images from fast scans with quality similar to the conventional scans and then applied the model to the remaining scans. We calculated clinically relevant T1w volumetrics (normalized whole brain, thalamic, gray matter, and white matter volume) for all scans and T2 lesion volume in a sub-analysis. We performed paired t-tests comparing conventional, fast, and fast with DL for these volumetrics, and fit repeated measures mixed-effects models to test for differences in correlations between volumetrics and clinically relevant patient-reported outcomes (PRO).Results: We found statistically significant but small differences between conventional and fast scans with DL for all T1w volumetrics. There was no difference in the extent to which the key T1w volumetrics correlated with clinically relevant PROs of MS symptom burden and neurological disability.Conclusion: A deep learning model that improves the image quality of the accelerated routine clinical brain MR scans has the potential to inform clinically relevant outcomes in MS.

scholarly journals “No evident disease activity”: The use of combined assessments in the management of patients with multiple sclerosis

2017 ◽  
Vol 23 (9) ◽  
pp. 1179-1187 ◽  
Author(s):  
Gavin Giovannoni ◽  
Davorka Tomic ◽  
Jeremy R Bright ◽  
Eva Havrdová
Keyword(s):  
Multiple Sclerosis ◽  
Disease Activity ◽  
Brain Magnetic Resonance Imaging ◽  
Individual Patient Level ◽  
Patient Reported ◽  
Magnetic Resonance Imaging Mri ◽  
The Individual ◽  
The Brain

Using combined endpoints to define no evident disease activity (NEDA) is becoming increasingly common when setting targets for treatment outcomes in multiple sclerosis (MS). Historically, NEDA has taken account of the occurrence of relapses, brain magnetic resonance imaging (MRI) lesions and disability worsening, but this approach places emphasis on inflammatory activity in the brain and mostly overlooks ongoing neurodegenerative damage. Combined assessments of NEDA which take account of changes in brain volume or neuropsychological outcomes such as cognitive function may begin to address this imbalance, and such assessments may also consider blood or spinal-fluid neurofilament levels or patient-reported outcomes and quality of life measures. If a combined NEDA assessment can be validated in prospective studies as indicative of long-term disease remission at the individual patient level, treating to achieve NEDA could become the goal of clinical practice and achieving NEDA may become the “new normal” state of disease control for patients with MS.

scholarly journals Radial self-navigated native magnetic resonance angiography in comparison to navigator-gated contrast-enhanced MRA of the entire thoracic aorta in an aortic patient collective

2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Martina Correa Londono ◽  
Nino Trussardi ◽  
Verena C. Obmann ◽  
Davide Piccini ◽  
Michael Ith ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Image Quality ◽  
Magnetic Resonance Angiography ◽  
Thoracic Aorta ◽  
Aortic Root ◽  
Aortic Disease ◽  
Ascending Aorta ◽  
Scan Time ◽  
Contrast Enhanced

Abstract Background The native balanced steady state with free precession (bSSFP) magnetic resonance angiography (MRA) technique has been shown to provide high diagnostic image quality for thoracic aortic disease. This study compares a 3D radial respiratory self-navigated native MRA (native-SN-MRA) based on a bSSFP sequence with conventional Cartesian, 3D, contrast-enhanced MRA (CE-MRA) with navigator-gated respiration control for image quality of the entire thoracic aorta. Methods Thirty-one aortic native-SN-MRA were compared retrospectively (63.9 ± 10.3 years) to 61 CE-MRA (63.1 ± 11.7 years) serving as a reference standard. Image quality was evaluated at the aortic root/ascending aorta, aortic arch and descending aorta. Scan time was recorded. In 10 patients with both MRA sequences, aortic pathologies were evaluated and normal and pathologic aortic diameters were measured. The influence of artifacts on image quality was analyzed. Results Compared to the overall image quality of CE-MRA, the overall image quality of native-SN-MRA was superior for all segments analyzed (aortic root/ascending, p < 0.001; arch, p < 0.001, and descending, p = 0.005). Regarding artifacts, the image quality of native-SN-MRA remained superior at the aortic root/ascending aorta and aortic arch before and after correction for confounders of surgical material (i.e., susceptibility-related artifacts) (p = 0.008 both) suggesting a benefit in terms of motion artifacts. Native-SN-MRA showed a trend towards superior intraindividual image quality, but without statistical significance. Intraindividually, the sensitivity and specificity for the detection of aortic disease were 100% for native-SN-MRA. Aortic diameters did not show a significant difference (p = 0.899). The scan time of the native-SN-MRA was significantly reduced, with a mean of 05:56 ± 01:32 min vs. 08:51 ± 02:57 min in the CE-MRA (p < 0.001). Conclusions Superior image quality of the entire thoracic aorta, also regarding artifacts, can be achieved with native-SN-MRA, especially in motion prone segments, in addition to a shorter acquisition time.

Improving Image Quality of Single Plane Wave Ultrasound via Deep Learning Based Channel Compounding

2020 ◽  
Author(s):  
Sven Rothlubbers ◽  
Hannah Strohm ◽  
Klaus Eickel ◽  
Jurgen Jenne ◽  
Vincent Kuhlen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Plane Wave ◽  
Single Plane

scholarly journals Long-Term Patient Satisfaction and Quality of Life After Breast-Conserving Therapy: A Prospective Study Using the BREAST-Q

2021 ◽  
Author(s):  
Ilona Stolpner ◽  
Jörg Heil ◽  
Fabian Riedel ◽  
Markus Wallwiener ◽  
Benedikt Schäfgen ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Risk Factors ◽  
Patient Satisfaction ◽  
Repeated Measures ◽  
Aesthetic Surgery ◽  
Well Being ◽  
Breast Conserving Therapy ◽  
Patient Reported

Abstract Background Poor patient-reported satisfaction after breast-conserving therapy (BCT) has been associated with impaired health-related quality of life (HRQOL) and subsequent depression in retrospective analysis. This prospective cohort study aimed to assess the HRQOL of patients who have undergone BCT using the BREAST-Q, and to identify clinical risk factors for lower patient satisfaction. Methods Patients with primary breast cancer undergoing BCT were asked to complete the BREAST-Q preoperatively (T1) for baseline evaluation, then 3 to 4 weeks postoperatively (T2), and finally 1 year after surgery (T3). Clinicopathologic data were extracted from the patients’ charts. Repeated measures analysis of variance (ANOVA) was used to determine significant differences in mean satisfaction and well-being levels among the test intervals. Multiple linear regression was used to evaluate risk factors for lower satisfaction. Results The study enrolled 250 patients. The lowest baseline BREAST-Q score was reported for “satisfaction with breast” (mean, 61 ± 19), but this increased postoperatively (mean, 66 ± 18) and was maintained at the 1 year follow-up evaluation (mean, 67 ± 21). “Physical well-being” decreased from T1 (mean, 82 ± 17) to T2 (mean, 28 ± 13) and did not recover much by T3 (mean, 33 ± 13), being the lowest BREAST-Q score postoperatively and in the 1-year follow-up evaluation. In multiple regression, baseline psychosocial well-being, body mass index (BMI), and type of incision were risk factors for lower “satisfaction with breasts.” Conclusion Both the aesthetic/surgery-related and psychological aspects are equally important with regard to “satisfaction with breasts” after BCT. The data could serve as the benchmark for future studies.

scholarly journals Real-Time Automated Classification of Sky Conditions Using Deep Learning and Edge Computing

2021 ◽  
Vol 13 (19) ◽  
pp. 3859
Author(s):  
Joby M. Prince Czarnecki ◽  
Sathishkumar Samiappan ◽  
Meilun Zhou ◽  
Cary Daniel McCraine ◽  
Louis L. Wasson
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Quality ◽  
Convolutional Neural Network ◽  
Precision Agriculture ◽  
Edge Computing ◽  
Training Data ◽  
Learning Approaches ◽  
Sky Conditions

The radiometric quality of remotely sensed imagery is crucial for precision agriculture applications because estimations of plant health rely on the underlying quality. Sky conditions, and specifically shadowing from clouds, are critical determinants in the quality of images that can be obtained from low-altitude sensing platforms. In this work, we first compare common deep learning approaches to classify sky conditions with regard to cloud shadows in agricultural fields using a visible spectrum camera. We then develop an artificial-intelligence-based edge computing system to fully automate the classification process. Training data consisting of 100 oblique angle images of the sky were provided to a convolutional neural network and two deep residual neural networks (ResNet18 and ResNet34) to facilitate learning two classes, namely (1) good image quality expected, and (2) degraded image quality expected. The expectation of quality stemmed from the sky condition (i.e., density, coverage, and thickness of clouds) present at the time of the image capture. These networks were tested using a set of 13,000 images. Our results demonstrated that ResNet18 and ResNet34 classifiers produced better classification accuracy when compared to a convolutional neural network classifier. The best overall accuracy was obtained by ResNet34, which was 92% accurate, with a Kappa statistic of 0.77. These results demonstrate a low-cost solution to quality control for future autonomous farming systems that will operate without human intervention and supervision.

scholarly journals Impact of Medium Cut-Off Dialyzers on Patient-Reported Outcomes: COREXH Registry

2020 ◽  
pp. 1-9
Author(s):  
Juan Carlos Alarcon ◽  
Alfonso Bunch ◽  
Freddy Ardila ◽  
Eduardo Zuñiga ◽  
Jasmin I. Vesga ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Kidney Disease ◽  
Repeated Measures ◽  
Patient Reported Outcomes ◽  
Short Form ◽  
High Flux ◽  
Middle Molecules ◽  
Patient Reported ◽  
The Impact

<b><i>Introduction:</i></b> A new generation of hemodialysis (HD) membranes called medium cut-off (MCO) membranes possesses enhanced capacities for middle molecule clearance, which have been associated with adverse outcomes in this population. These improvements could potentially positively impact patient-reported outcomes (PROs). <b><i>Objective:</i></b> The objective of this study was to evaluate the impact of MCO membranes on PROs in a cohort of HD patients in Colombia. <b><i>Methods:</i></b> This was a prospective, multicenter, observational cohort study of 992 patients from 12 renal clinics in Colombia who were switched from high-flux HD to MCO therapy and observed for 12 months. Changes in Kidney Disease Quality of Life 36-Item Short Form Survey (KDQoL-SF36) domains, Dialysis Symptom Index (DSI), and restless legs syndrome (RLS) 12 months after switching to MCO membranes were compared with time on high-flux membranes. Repeated measures of ANOVA were used to evaluate changes in KDQoL-SF36 scores; severity scoring was used to assess DSI changes over time; Cochran’s Q test was used to evaluate changes in frequency of diagnostic criteria of RLS. <b><i>Results:</i></b> During 12 months of follow-up, 3 of 5 KDQoL-SF36 domains improved compared with baseline: symptoms (<i>p</i> &#x3c; 0.0001), effects of kidney disease (<i>p</i> &#x3c; 0.0001), and burden of kidney disease (<i>p</i> &#x3c; 0.001). The proportion of patients diagnosed with RLS significantly decreased from 22.1% at baseline to 10% at 12 months (<i>p</i> &#x3c; 0.0001). No significant differences in the number of symptoms (DSI, <i>p =</i> 0.1) were observed, although their severity decreased (<i>p</i> = 0.009). <b><i>Conclusions:</i></b> In conventional HD patients, the expanded clearance of large middle molecules with MCO-HD membranes was associated with higher health-related quality of life scores and a decrease in the prevalence of RLS.

Sign in / Sign up

Export Citation Format

Share Document