IU Indianapolis ScholarWorks :: Browsing by Subject "Magnetic resonance imaging"

Browsing by Subject "Magnetic resonance imaging"

Now showing 1 - 10 of 87

30-minute CMR for common clinical indications: a Society for Cardiovascular Magnetic Resonance white paper
(BMC, 2022-03-01) Raman, Subha V.; Markl, Michael; Patel, Amit R.; Bryant, Jennifer; Allen, Bradley D.; Plein, Sven; Seiberlich, Nicole; Medicine, School of Medicine
Background: Despite decades of accruing evidence supporting the clinical utility of cardiovascular magnetic resonance (CMR), adoption of CMR in routine cardiovascular practice remains limited in many regions of the world. Persistent use of long scan times of 60 min or more contributes to limited adoption, though techniques available on most scanners afford routine CMR examination within 30 min. Incorporating such techniques into standardize protocols can answer common clinical questions in daily practice, including those related to heart failure, cardiomyopathy, ventricular arrhythmia, ischemic heart disease, and non-ischemic myocardial injury. BODY: In this white paper, we describe CMR protocols of 30 min or shorter duration with routine techniques with or without stress perfusion, plus specific approaches in patient and scanner room preparation for efficiency. Minimum requirements for the scanner gradient system, coil hardware and pulse sequences are detailed. Recent advances such as quantitative myocardial mapping and other add-on acquisitions can be incorporated into the proposed protocols without significant extension of scan duration for most patients. Conclusion: Common questions in clinical cardiovascular practice can be answered in routine CMR protocols under 30 min; their incorporation warrants consideration to facilitate increased access to CMR worldwide.
A deep learning framework identifies dimensional representations of Alzheimer’s Disease from brain structure
(Springer Nature, 2021-12-03) Yang, Zhijian; Nasrallah, Ilya M.; Shou, Haochang; Wen, Junhao; Doshi, Jimit; Habes, Mohamad; Erus, Guray; Abdulkadir, Ahmed; Resnick, Susan M.; Albert, Marilyn S.; Maruff, Paul; Fripp, Jurgen; Morris, John C.; Wolk, David A.; Davatzikos, Christos; iSTAGING Consortium; Baltimore Longitudinal Study of Aging (BLSA); Alzheimer’s Disease Neuroimaging Initiative (ADNI); Radiology and Imaging Sciences, School of Medicine
Heterogeneity of brain diseases is a challenge for precision diagnosis/prognosis. We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a semi-supervised deep-clustering method, which examines neuroanatomical heterogeneity contrasted against normal brain structure, to identify disease subtypes through neuroimaging signatures. When applied to regional volumes derived from T1-weighted MRI (two studies; 2,832 participants; 8,146 scans) including cognitively normal individuals and those with cognitive impairment and dementia, Smile-GAN identified four patterns or axes of neurodegeneration. Applying this framework to longitudinal data revealed two distinct progression pathways. Measures of expression of these patterns predicted the pathway and rate of future neurodegeneration. Pattern expression offered complementary performance to amyloid/tau in predicting clinical progression. These deep-learning derived biomarkers offer potential for precision diagnostics and targeted clinical trial recruitment.
A large open access dataset of brain metastasis 3D segmentations on MRI with clinical and imaging information
(Springer Nature, 2024-02-29) Ramakrishnan, Divya; Jekel, Leon; Chadha, Saahil; Janas, Anastasia; Moy, Harrison; Maleki, Nazanin; Sala, Matthew; Kaur, Manpreet; Cassinelli Petersen, Gabriel; Merkaj, Sara; von Reppert, Marc; Baid, Ujjwal; Bakas, Spyridon; Kirsch, Claudia; Davis, Melissa; Bousabarah, Khaled; Holler, Wolfgang; Lin, MingDe; Westerhoff, Malte; Aneja, Sanjay; Memon, Fatima; Aboian, Mariam S.; Pathology and Laboratory Medicine, School of Medicine
Resection and whole brain radiotherapy (WBRT) are standard treatments for brain metastases (BM) but are associated with cognitive side effects. Stereotactic radiosurgery (SRS) uses a targeted approach with less side effects than WBRT. SRS requires precise identification and delineation of BM. While artificial intelligence (AI) algorithms have been developed for this, their clinical adoption is limited due to poor model performance in the clinical setting. The limitations of algorithms are often due to the quality of datasets used for training the AI network. The purpose of this study was to create a large, heterogenous, annotated BM dataset for training and validation of AI models. We present a BM dataset of 200 patients with pretreatment T1, T1 post-contrast, T2, and FLAIR MR images. The dataset includes contrast-enhancing and necrotic 3D segmentations on T1 post-contrast and peritumoral edema 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging information. We used a streamlined approach to database-building through a PACS-integrated segmentation workflow.
A Patch-Wise Deep Learning Approach for Myocardial Blood Flow Quantification with Robustness to Noise and Nonrigid Motion
(IEEE, 2021) Youssef, Khalid; Heydari, Bobby; Rivero, Luis Zamudio; Beaulieu, Taylor; Cheema, Karandeep; Dharmakumar, Rohan; Sharif, Behzad; Medicine, School of Medicine
Quantitative analysis of dynamic contrast-enhanced cardiovascular MRI (cMRI) datasets enables the assessment of myocardial blood flow (MBF) for objective evaluation of ischemic heart disease in patients with suspected coronary artery disease. State-of-the-art MBF quantification techniques use constrained deconvolution and are highly sensitive to noise and motion-induced errors, which can lead to unreliable outcomes in the setting of high-resolution MBF mapping. To overcome these limitations, recent iterative approaches incorporate spatial-smoothness constraints to tackle pixel-wise MBF mapping. However, such iterative methods require a computational time of up to 30 minutes per acquired myocardial slice, which is a major practical limitation. Furthermore, they cannot enforce robustness to residual nonrigid motion which can occur in clinical stress/rest studies of patients with arrhythmia. We present a non-iterative patch-wise deep learning approach for pixel-wise MBF quantification wherein local spatio-temporal features are learned from a large dataset of myocardial patches acquired in clinical stress/rest cMRI studies. Our approach is scanner-independent, computationally efficient, robust to noise, and has the unique feature of robustness to motion-induced errors. Numerical and experimental results obtained using real patient data demonstrate the effectiveness of our approach.Clinical Relevance- The proposed patch-wise deep learning approach significantly improves the reliability of high-resolution myocardial blood flow quantification in cMRI by improving its robustness to noise and nonrigid myocardial motion and is up to 300-fold faster than state-of-the-art iterative approaches.
A review of deep learning and radiomics approaches for pancreatic cancer diagnosis from medical imaging
(Wolters Kluwer, 2023) Yao, Lanhong; Zhang, Zheyuan; Keles, Elif; Yazici, Cemal; Tirkes, Temel; Bagco, Ulas; Radiology and Imaging Sciences, School of Medicine
Purpose of review: Early and accurate diagnosis of pancreatic cancer is crucial for improving patient outcomes, and artificial intelligence (AI) algorithms have the potential to play a vital role in computer-aided diagnosis of pancreatic cancer. In this review, we aim to provide the latest and relevant advances in AI, specifically deep learning (DL) and radiomics approaches, for pancreatic cancer diagnosis using cross-sectional imaging examinations such as computed tomography (CT) and magnetic resonance imaging (MRI). Recent findings: This review highlights the recent developments in DL techniques applied to medical imaging, including convolutional neural networks (CNNs), transformer-based models, and novel deep learning architectures that focus on multitype pancreatic lesions, multiorgan and multitumor segmentation, as well as incorporating auxiliary information. We also discuss advancements in radiomics, such as improved imaging feature extraction, optimized machine learning classifiers and integration with clinical data. Furthermore, we explore implementing AI-based clinical decision support systems for pancreatic cancer diagnosis using medical imaging in practical settings. Summary: Deep learning and radiomics with medical imaging have demonstrated strong potential to improve diagnostic accuracy of pancreatic cancer, facilitate personalized treatment planning, and identify prognostic and predictive biomarkers. However, challenges remain in translating research findings into clinical practice. More studies are required focusing on refining these methods, addressing significant limitations, and developing integrative approaches for data analysis to further advance the field of pancreatic cancer diagnosis.
Acute penetrating injury of the spinal cord by a wooden spike with delayed surgery: a case report
(Wolters Kluwer, 2023) Guest, James D.; Luo, Zhuojing; Liu, Yansheng; Gao, Hongkun; Wang, Dianchun; Xu, Xiao-Ming; Zhu, Hui; Neurology, School of Medicine
Rarely, penetrating injuries to the spinal cord result from wooden objects, creating unique challenges to mitigate neurological injury and high rates of infection and foreign body reactions. We report a man who sustained a penetrating cervical spinal cord injury from a sharpened stick. While initially tetraparetic, he rapidly recovered function. The risks of neurological deterioration during surgical removal made the patient reluctant to consent to surgery despite the impalement of the spinal cord. A repeat MRI on day 3 showed an extension of edema indicating progressive inflammation. On the 7th day after injury, fever and paresthesias occurred with a large increase in serum inflammatory indicators, and the patient agreed to undergo surgical removal of the wooden object. We discuss the management nuances related to wood, the longitudinal evolution of MRI findings, infection risk, surgical risk mitigation and technique, an inflammatory marker profile, long-term recovery, and the surprisingly minimal neurological deficits associated with low-velocity midline spinal cord injuries. The patient had an excellent clinical outcome. The main lessons are that a wooden penetrating central nervous system injury has a high risk for infection, and that surgical removal from the spinal cord should be performed soon after injury and under direct visualization.
Adverse Outcome Following Mild Traumatic Brain Injury Is Associated with Microstructure Alterations at the Gray and White Matter Boundary
(MDPI, 2023-08-21) Pankatz, Lara; Rojczyk, Philine; Seitz-Holland, Johanna; Bouix, Sylvain; Jung, Leonard B.; Wiegand, Tim L. T.; Bonke, Elena M.; Sollmann, Nico; Kaufmann, Elisabeth; Carrington, Holly; Puri, Twishi; Rathi, Yogesh; Coleman, Michael J.; Pasternak, Ofer; George, Mark S.; McAllister, Thomas W.; Zafonte, Ross; Stein, Murray B.; Marx, Christine E.; Shenton, Martha E.; Koerte, Inga K.; Psychiatry, School of Medicine
The gray matter/white matter (GM/WM) boundary of the brain is vulnerable to shear strain associated with mild traumatic brain injury (mTBI). It is, however, unknown whether GM/WM microstructure is associated with long-term outcomes following mTBI. The diffusion and structural MRI data of 278 participants between 18 and 65 years of age with and without military background from the Department of Defense INTRuST study were analyzed. Fractional anisotropy (FA) was extracted at the GM/WM boundary across the brain and for each lobe. Additionally, two conventional analytic approaches were used: whole-brain deep WM FA (TBSS) and whole-brain cortical thickness (FreeSurfer). ANCOVAs were applied to assess differences between the mTBI cohort (n = 147) and the comparison cohort (n = 131). Associations between imaging features and post-concussive symptom severity, and functional and cognitive impairment were investigated using partial correlations while controlling for mental health comorbidities that are particularly common among military cohorts and were present in both the mTBI and comparison group. Findings revealed significantly lower whole-brain and lobe-specific GM/WM boundary FA (p < 0.011), and deep WM FA (p = 0.001) in the mTBI cohort. Whole-brain and lobe-specific GM/WM boundary FA was significantly negatively correlated with post-concussive symptoms (p < 0.039), functional (p < 0.016), and cognitive impairment (p < 0.049). Deep WM FA was associated with functional impairment (p = 0.002). Finally, no significant difference was observed in cortical thickness, nor between cortical thickness and outcome (p > 0.05). Findings from this study suggest that microstructural alterations at the GM/WM boundary may be sensitive markers of adverse long-term outcomes following mTBI.
Alcohol Use and Prefrontal Cortex Volume Trajectories in Young Adults with Mood Disorders and Associated Clinical Outcomes
(MDPI, 2022-02-22) Kirsch, Dylan E.; Tretyak, Valeria; Le, Vanessa; Huffman, Ansley; Fromme, Kim; Strakowski, Stephen M.; Lippard, Elizabeth T. C.; Psychiatry, School of Medicine
Background: Alcohol use in the course of mood disorders is associated with worse clinical outcomes. The mechanisms by which alcohol use alters the course of illness are unclear but may relate to prefrontal cortical (PFC) sensitivity to alcohol. We investigated associations between alcohol use and PFC structural trajectories in young adults with a mood disorder compared to typically developing peers. Methods: 41 young adults (24 with a mood disorder, agemean = 21 ± 2 years) completed clinical evaluations, assessment of alcohol use, and two structural MRI scans approximately one year apart. Freesurfer was used to segment PFC regions of interest (ROIs) (anterior cingulate, orbitofrontal cortex, and frontal pole). Effects of group, alcohol use, time, and interactions among these variables on PFC ROIs at baseline and follow-up were modeled. Associations were examined between alcohol use and longitudinal changes in PFC ROIs with prospective mood. Results: Greater alcohol use was prospectively associated with decreased frontal pole volume in participants with a mood disorder, but not typically developing comparison participants (time-by-group-by-alcohol interaction; p = 0.007); however, this interaction became a statistical trend in a sensitivity analysis excluding one outlier in terms of alcohol use. Greater alcohol use and a decrease in frontal pole volume related to longer duration of major depression during follow-up (p’s < 0.05). Conclusion: Preliminary findings support more research on alcohol use, PFC trajectories, and depression recurrence in young adults with a mood disorder including individuals with heavier drinking patterns.
Altered dynamics of the prefrontal networks are associated with the risk for postpartum psychosis: a functional magnetic resonance imaging study
(Springer Nature, 2021-05-12) Sambataro, Fabio; Cattarinussi, Giulia; Lawrence, Andrew; Biaggi, Alessandra; Fusté, Montserrat; Hazelgrove, Katie; Mehta, Mitul A.; Pawlby, Susan; Conroy, Susan; Seneviratne, Gertrude; Craig, Michael C.; Pariante, Carmine M.; Miele, Maddalena; Dazzan, Paola; Psychiatry, School of Medicine
Postpartum psychosis (PP) is a severe mental disorder that affects women in the first few weeks after delivery. To date there are no biomarkers that distinguish which women at risk (AR) develop a significant psychiatric relapse postpartum. While altered brain connectivity may contribute to the risk for psychoses unrelated to the puerperium, this remains unexplored in PP. We followed up 32 AR and 27 healthy (HC) women from pregnancy to 8-week postpartum. At this point, we classified women as AR-unwell (n = 15) if they had developed a psychiatric relapse meeting DSM-IV diagnostic criteria, or impacting on daily functioning and requiring treatment, or AR-well (n = 17) if they remained asymptomatic. Women also underwent an fMRI scan at rest and during an emotional-processing task, to study within- and between-networks functional connectivity. Women AR, and specifically those in the AR-well group, showed increased resting connectivity within an executive network compared to HC. During the execution of the emotional task, women AR also showed decreased connectivity in the executive network, and altered emotional load-dependent connectivity between executive, salience, and default-mode networks. AR-unwell women particularly showed increased salience network-dependent modulation of the default-mode and executive network relative to AR-well, who showed greater executive network-dependent modulation of the salience network. Our finding that the executive network and its interplay with other brain networks implicated in goal-directed behavior are intrinsically altered suggest that they could be considered neural phenotypes for postpartum psychosis and help advance our understanding of the pathophysiology of this disorder.
Apathy Is Associated With Ventral Striatum Volume in Schizophrenia Spectrum Disorder
(American Psychiatric Association, 2016) Roth, Robert M.; Garlinghouse, Matthew A.; Flashman, Laura A.; Koven, Nancy S.; Pendergrass, J. Cara; Ford, James C.; McAllister, Thomas W.; Saykin, Andrew J.; Psychiatry, School of Medicine
Apathy is prevalent in schizophrenia, but its etiology has received little investigation. The ventral striatum (VS), a key brain region involved in motivated behavior, has been implicated in studies of apathy. We therefore evaluated whether apathy is associated with volume of the VS on MRI in 23 patients with schizophrenia using voxel-based morphometry. Results indicated that greater self-reported apathy severity was associated with smaller volume of the right VS even when controlling for age, gender, depression, and total gray matter volume. The finding suggests that apathy is related to abnormality of brain circuitry subserving motivated behavior in patients with schizophrenia.

Browsing by Subject "Magnetic resonance imaging"

Results Per Page

Sort Options