Search

Your search keyword '"Hansen, Michael S."' showing total 342 results
Start Over Author "Hansen, Michael S."
342 results on '"Hansen, Michael S."'

2. A Path Towards Clinical Adaptation of Accelerated MRI

Author

Yao, Michael S. and Hansen, Michael S.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Accelerated MRI reconstructs images of clinical anatomies from sparsely sampled signal data to reduce patient scan times. While recent works have leveraged deep learning to accomplish this task, such approaches have often only been explored in simulated environments where there is no signal corruption or resource limitations. In this work, we explore augmentations to neural network MRI image reconstructors to enhance their clinical relevancy. Namely, we propose a ConvNet model for detecting sources of image artifacts that achieves a classifier $F_2$ score of 79.1%. We also demonstrate that training reconstructors on MR signal data with variable acceleration factors can improve their average performance during a clinical patient scan by up to 2%. We offer a loss function to overcome catastrophic forgetting when models learn to reconstruct MR images of multiple anatomies and orientations. Finally, we propose a method for using simulated phantom data to pre-train reconstructors in situations with limited clinically acquired datasets and compute capabilities. Our results provide a potential path forward for clinical adaptation of accelerated MRI., Comment: Accepted to ML4H 2022

Published
2022

3. End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction

Author

Zhao, Ruiyang, Zhang, Yuxin, Yaman, Burhaneddin, Lungren, Matthew P., and Hansen, Michael S.

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing, Physics - Medical Physics
Abstract

Deep learning techniques have emerged as a promising approach to highly accelerated MRI. However, recent reconstruction challenges have shown several drawbacks in current deep learning approaches, including the loss of fine image details even using models that perform well in terms of global quality metrics. In this study, we propose an end-to-end deep learning framework for image reconstruction and pathology detection, which enables a clinically aware evaluation of deep learning reconstruction quality. The solution is demonstrated for a use case in detecting meniscal tears on knee MRI studies, ultimately finding a loss of fine image details with common reconstruction methods expressed as a reduced ability to detect important pathology like meniscal tears. Despite the common practice of quantitative reconstruction methodology evaluation with metrics such as SSIM, impaired pathology detection as an automated pathology-based reconstruction evaluation approach suggests existing quantitative methods do not capture clinically important reconstruction outcomes.

Published
2021

4. fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Data

Author

Zhao, Ruiyang, Yaman, Burhaneddin, Zhang, Yuxin, Stewart, Russell, Dixon, Austin, Knoll, Florian, Huang, Zhengnan, Lui, Yvonne W., Hansen, Michael S., and Lungren, Matthew P.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Physics - Medical Physics
Abstract

Improving speed and image quality of Magnetic Resonance Imaging (MRI) via novel reconstruction approaches remains one of the highest impact applications for deep learning in medical imaging. The fastMRI dataset, unique in that it contains large volumes of raw MRI data, has enabled significant advances in accelerating MRI using deep learning-based reconstruction methods. While the impact of the fastMRI dataset on the field of medical imaging is unquestioned, the dataset currently lacks clinical expert pathology annotations, critical to addressing clinically relevant reconstruction frameworks and exploring important questions regarding rendering of specific pathology using such novel approaches. This work introduces fastMRI+, which consists of 16154 subspecialist expert bounding box annotations and 13 study-level labels for 22 different pathology categories on the fastMRI knee dataset, and 7570 subspecialist expert bounding box annotations and 643 study-level labels for 30 different pathology categories for the fastMRI brain dataset. The fastMRI+ dataset is open access and aims to support further research and advancement of medical imaging in MRI reconstruction and beyond.

Published
2021

6. Radiation-free CMR diagnostic heart catheterization in children

Author

Ratnayaka, Kanishka, Kanter, Joshua P, Faranesh, Anthony Z, Grant, Elena K, Olivieri, Laura J, Cross, Russell R, Cronin, Ileen F, Hamann, Karin S, Campbell-Washburn, Adrienne E, O’Brien, Kendall J, Rogers, Toby, Hansen, Michael S, and Lederman, Robert J

Subjects
Biomedical and Clinical Sciences, Cardiovascular Medicine and Haematology, Clinical Sciences, Pediatric Research Initiative, Heart Disease, Clinical Research, Patient Safety, Biomedical Imaging, Cardiovascular, Pediatric, Bioengineering, Adolescent, Age Factors, Cardiac Catheterization, Child, Feasibility Studies, Female, Heart Diseases, Hemodynamics, Humans, Magnetic Resonance Imaging, Interventional, Male, Predictive Value of Tests, Radiation Exposure, Time Factors, Catheterization, Magnetic Resonance Imaging, Interventional Cardiovascular MRI, Real-time MRI, MRI fluoroscopy, Cardiorespiratory Medicine and Haematology, Nuclear Medicine & Medical Imaging, Cardiovascular medicine and haematology
Abstract

BackgroundChildren with heart disease may require repeated X-Ray cardiac catheterization procedures, are more radiosensitive, and more likely to survive to experience oncologic risks of medical radiation. Cardiovascular magnetic resonance (CMR) is radiation-free and offers information about structure, function, and perfusion but not hemodynamics. We intend to perform complete radiation-free diagnostic right heart catheterization entirely using CMR fluoroscopy guidance in an unselected cohort of pediatric patients; we report the feasibility and safety.MethodsWe performed 50 CMR fluoroscopy guided comprehensive transfemoral right heart catheterizations in 39 pediatric (12.7 ± 4.7 years) subjects referred for clinically indicated cardiac catheterization. CMR guided catheterizations were assessed by completion (success/failure), procedure time, and safety events (catheterization, anesthesia). Pre and post CMR body temperature was recorded. Concurrent invasive hemodynamic and diagnostic CMR data were collected.ResultsDuring a twenty-two month period (3/2015 - 12/2016), enrolled subjects had the following clinical indications: post-heart transplant 33%, shunt 28%, pulmonary hypertension 18%, cardiomyopathy 15%, valvular heart disease 3%, and other 3%. Radiation-free CMR guided right heart catheterization attempts were all successful using passive catheters. In two subjects with septal defects, right and left heart catheterization were performed. There were no complications. One subject had six such procedures. Most subjects (51%) had undergone multiple (5.5 ± 5) previous X-Ray cardiac catheterizations. Retained thoracic surgical or transcatheter implants (36%) did not preclude successful CMR fluoroscopy heart catheterization. During the procedure, two subjects were receiving vasopressor infusions at baseline because of poor cardiac function, and in ten procedures, multiple hemodynamic conditions were tested.ConclusionsComprehensive CMR fluoroscopy guided right heart catheterization was feasible and safe in this small cohort of pediatric subjects. This includes subjects with previous metallic implants, those requiring continuous vasopressor medication infusions, and those requiring pharmacologic provocation. Children requiring multiple, serial X-Ray cardiac catheterizations may benefit most from radiation sparing. This is a step toward wholly CMR guided diagnostic (right and left heart) cardiac catheterization and future CMR guided cardiac intervention.Trial registrationClinicalTrials.gov NCT02739087 registered February 17, 2016.

Published
2017

7. CMR fluoroscopy right heart catheterization for cardiac output and pulmonary vascular resistance: results in 102 patients

Author

Rogers, Toby, Ratnayaka, Kanishka, Khan, Jaffar M, Stine, Annette, Schenke, William H, Grant, Laurie P, Mazal, Jonathan R, Grant, Elena K, Campbell-Washburn, Adrienne, Hansen, Michael S, Ramasawmy, Rajiv, Herzka, Daniel A, Xue, Hui, Kellman, Peter, Faranesh, Anthony Z, and Lederman, Robert J

Subjects
Biomedical and Clinical Sciences, Cardiovascular Medicine and Haematology, Clinical Sciences, Lung, Cardiovascular, Clinical Trials and Supportive Activities, Bioengineering, Heart Disease, Biomedical Imaging, Clinical Research, Administration, Inhalation, Adult, Aged, Cardiac Catheterization, Cardiac Output, Case-Control Studies, Female, Fluoroscopy, Humans, Hypertension, Pulmonary, Magnetic Resonance Imaging, Interventional, Male, Middle Aged, Models, Cardiovascular, Nitric Oxide, Oxygen, Predictive Value of Tests, Prospective Studies, Pulmonary Artery, Time Factors, Vascular Resistance, Interventional MRI catheterization, Right heart catheterization, Invasive hemodynamics, Phase contrast MRI flow, Real-time MRI, CMR, Cardiac MRI, Cardiorespiratory Medicine and Haematology, Nuclear Medicine & Medical Imaging, Cardiovascular medicine and haematology
Abstract

BackgroundQuantification of cardiac output and pulmonary vascular resistance (PVR) are critical components of invasive hemodynamic assessment, and can be measured concurrently with pressures using phase contrast CMR flow during real-time CMR guided cardiac catheterization.MethodsOne hundred two consecutive patients underwent CMR fluoroscopy guided right heart catheterization (RHC) with simultaneous measurement of pressure, cardiac output and pulmonary vascular resistance using CMR flow and the Fick principle for comparison. Procedural success, catheterization time and adverse events were prospectively collected.ResultsRHC was successfully completed in 97/102 (95.1%) patients without complication. Catheterization time was 20 ± 11 min. In patients with and without pulmonary hypertension, baseline mean pulmonary artery pressure was 39 ± 12 mmHg vs. 18 ± 4 mmHg (p

Published
2017

11. Real-Time Magnetic Resonance Imaging Technique for Determining Left Ventricle Pressure-Volume Loops

Author

Witschey, Walter RT, Contijoch, Francisco, McGarvey, Jeremy R, Ferrari, Victor A, Hansen, Michael S, Lee, Madonna E, Takebayashi, Satoshi, Aoki, Chikashi, Chirinos, Julio A, Yushkevich, Paul A, Gorman, Joseph H, Pilla, James J, and Gorman, Robert C

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Biomedical Imaging, Heart Disease, Cardiovascular, Bioengineering, Animals, Cardiac Output, Disease Models, Animal, Heart Rate, Heart Ventricles, Image Interpretation, Computer-Assisted, Magnetic Resonance Imaging, Cine, Male, Myocardial Contraction, Random Allocation, Sensitivity and Specificity, Stroke Volume, Swine, Ventricular Dysfunction, Left, Ventricular Function, Left, Ventricular Pressure, Cardiorespiratory Medicine and Haematology, Respiratory System, Cardiovascular medicine and haematology, Clinical sciences
Abstract

BackgroundRapid determination of the left ventricular (LV) pressure-volume (PV) relationship as loading conditions are varied is the gold standard for assessment of LV function. Cine magnetic resonance imaging (MRI) does not have sufficient spatiotemporal resolution to assess beat-to-beat changes of the LV PV relationship required to measure the LV end-systolic elastance (EES) or preload-recruitable stroke work (PRSW). Our aim was to investigate real-time MRI and semiautomated LV measurement of LV volume to measure PV relations in large animals under normal and inotropically stressed physiologic conditions.MethodsWe determined that PV relationships could be accurately measured using an image exposure time Tex less than 100 ms and frame rate Tfr less than 50 ms at elevated heart rates (∼140 beats per minute) using a golden angle radial MRI k-space trajectory and active contour segmentation.ResultsWith an optimized exposure time (Tex=95 ms and frame rate Tfr=2.8 ms), we found that there was no significant difference between cine and real-time MRI at rest in end-diastolic volume, end-systolic volume, ejection fraction, stroke volume, or cardiac output (n=5, p

Published
2014

23. Is Erythrocyte Sedimentation Rate Necessary for the Initial Diagnosis of Giant Cell Arteritis?

Author

Hansen, Michael S., Klefter, Oliver N., Terslev, Lene, Jensen, Mads R., Brittain, Jane M., Døhn, Uffe M., Faber, Carsten, Heegaard, Steffen, Wiencke, Anne K., Subhi, Yousif, Hamann, Steffen, Hansen, Michael S., Klefter, Oliver N., Terslev, Lene, Jensen, Mads R., Brittain, Jane M., Døhn, Uffe M., Faber, Carsten, Heegaard, Steffen, Wiencke, Anne K., Subhi, Yousif, and Hamann, Steffen

Abstract

Giant cell arteritis (GCA) is an ophthalmological emergency that can be difficult to diagnose and prompt treatment is vital. We investigated the sequential diagnostic value for patients with suspected GCA using three biochemical measures as they arrive to the clinician: first, platelet count, then C-reactive protein (CRP), and lastly, erythrocyte sedimentation rate (ESR). This retrospective cross-sectional study of consecutive patients with suspected GCA investigated platelet count, CRP, and ESR using diagnostic test accuracy statistics and odds ratios (ORs) in a sequential fashion. The diagnosis was established by experts at follow-up, considering clinical findings and tests including temporal artery biopsy. A total of 94 patients were included, of which 37 (40%) were diagnosed with GCA. Compared with those without GCA, patients with GCA had a higher platelet count (p < 0.001), CRP (p < 0.001), and ESR (p < 0.001). Platelet count demonstrated a low sensitivity (38%) and high specificity (88%); CRP, a high sensitivity (86%) and low specificity (56%); routine ESR, a high sensitivity (89%) and low specificity (47%); and age-adjusted ESR, a moderate sensitivity (65%) and moderate specificity (65%). Sequential analysis revealed that ESR did not provide additional value in evaluating risk of GCA. Initial biochemical evaluation can be based on platelet count and CRP, without waiting for ESR, which allows faster initial decision-making in GCA.

Published
2023

33. Optical Coherence Tomography of Peripapillary Vessels in Giant Cell Arteritis and Ischaemic Ocular Disease

Author

Klefter, Oliver N., Hansen, Michael S., Willerslev, Anne, Faber, Carsten, Terslev, Lene, Jensen, Mads R., Døhn, Uffe M., Wiencke, Anne, Heegaard, Steffen, Hamann, Steffen, Klefter, Oliver N., Hansen, Michael S., Willerslev, Anne, Faber, Carsten, Terslev, Lene, Jensen, Mads R., Døhn, Uffe M., Wiencke, Anne, Heegaard, Steffen, and Hamann, Steffen

Abstract

With normal retinal blood flow, cross-sectional optical coherence tomography (OCT) of retinal vessels shows a structured intravascular reflectivity profile, resembling a ‘figure-of-8’. Altered profiles have been reported in vascular occlusive and haematological diseases. Giant cell arteritis (GCA) can cause visual loss, usually due to anterior ischaemic optic neuropathy (AION) or retinal artery occlusion. Our aim was to extend the assessment of OCT vascular profiles to patients with suspected GCA and to determine if any abnormalities were related to GCA per se or to ischaemic ocular conditions. This nested retrospective study included 61 eyes of 31 patients (13 with GCA). Six eyes had arteritic and seven eyes non-arteritic AION, three eyes had non-arteritic retinal artery occlusion, 11 eyes had other ocular conditions and 34 were unaffected control eyes. For each eye the appearance of structured intravascular profiles on peripapillary OCT was graded as present, partial, absent or uncertain. Non-presence of structured intravascular profiles was more frequent in AION and retinal artery occlusion than in other ocular conditions or unaffected eyes (Fisher’s test, p =.0047). Based on follow-up of 25 eyes, reflectivity profiles normalised in three out of four eyes after 85 (35–245) days. Vessel profiles were not associated with GCA (p =.32) and were similar in arteritic and non-arteritic AION (p =.66). In conclusion, absence of structured intravascular reflectivity profiles may be a marker of acute ischaemia in the anterior optic nerve or inner retina. However, it did not seem specific for GCA. The prognostic value warrants further studies.

Published
2022

39. Effectiveness and drug adherence of biologic monotherapy in routine care of patients with rheumatoid arthritis: a cohort study of patients registered in the Danish biologics registry

Author

Jørgensen, Tanja Schjødt, Kristensen, Lars Erik, Christensen, Robin, Bliddal, Henning, Lorenzen, Tove, Hansen, Michael S., Østergaard, Mikkel, Jensen, Jørgen, Zanjani, Lida, Laursen, Toke, Butt, Sheraz, Dam, Mette Y., Lindegaard, Hanne M., Espesen, Jakob, Hendricks, Oliver, Kumar, Prabhat, Kincses, Anita, Larsen, Line H., Andersen, Marlene, Næser, Esben K., Jensen, Dorte V., Grydehøj, Jolanta, Unger, Barbara, Dufour, Ninna, Sørensen, Vibeke, Vildhøj, Sara, Jensen Hansen, Inger Marie, Raun, Johnny, Krogh, Niels Steen, and Lund Hetland, Merete

Published
2015
Full Text
View/download PDF

44. Pachychoroid Spectrum Diseases in Patients with Cushing's Syndrome: A Systematic Review with Meta-Analyses.

Author

Holtz, Jeppe K., Larsson, Janni M. E., Hansen, Michael S., van Dijk, Elon H. C., and Subhi, Yousif

Subjects
CUSHING'S syndrome, CHOROID, OPTICAL coherence tomography, POLYPOIDAL choroidal vasculopathy
Abstract

Cushing's syndrome is a rare disease with an endogenous cause of excess cortisol secretion. More evidence substantially links cortisol levels to the pachychoroid spectrum diseases. In this systematic review and meta-analysis, we summarize available evidence on pachychoroid spectrum diseases in patients with Cushing's syndrome. We performed a systematic literature search in 11 databases on 21 May 2022. Studies were considered eligible if they performed retinal examination of a consecutive group of patients with Cushing's syndrome using optical coherence tomography (OCT) scans. We extracted data on subfoveal choroidal thickness in patients with Cushing's syndrome compared to matched controls. We also extracted data on the prevalence of pachychoroid pigment epitheliopathy (PPE), central serous chorioretinopathy (CSC), and polypoidal choroidal vasculopathy (PCV). We identified six eligible studies with a total of 159 patients with Cushing's syndrome. On average, patients with Cushing's syndrome have 49.5 µm thicker subfoveal choroidal thickness compared to matched healthy individuals. Pachychoroid spectrum diseases were relatively common in these patients: PPE in 20.8%, CSC in 7.7%, and PCV in 2.8%. We conclude that there should be low threshold to recommend ophthalmic examination to patients with Cushing's syndrome, and that a macular OCT is recommended during this examination. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results