MRI Technology Research Articles

Design and Implementation of Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that uses MRI technology to quantify brain activity by detecting changes in blood flow and applying the Blood-oxygen-level dependent (BOLD) contrast. Current neuroscience research suggests a modular brain structure. To understand the complex patterns of interaction between brain areas. The proposed system makes use of the CNN algorithm, which is an efficient method for dividing segmentation. A brain area is defined as a collection of subjects who exhibit a similar pattern of interaction between their brain areas. A thorough experimental examination utilizing benchmark data demonstrates that our technique is both effective and efficient. Two real-world fMRI studies found that the rifleman technique has the potential to improve comprehension of both normal brain activity and the abnormalities associated with psychiatric diseases. That is, mental diseases are typically defined by How an individual feels, acts, thinks, or perceives events. This is typically linked to specific areas or functions of the brain or the rest of the nervous system. This is unacceptable for a variety of time series sectors. As a result, we provide the statistical region merging approach, which is applied to picture segmentation. The method evaluates the values inside a regional range and combines them using the merging criteria, resulting in a smaller list. . As a result, we gather additional information and compare the findings to those already in the database. As a result, we decide if a person is normal or aberrant, as well as whether they are unwell.

Mice and minipigs with compromised expression of the Alzheimer's disease gene SORL1 show cerebral metabolic disturbances on hyperpolarized [1-13C]pyruvate and sodium MRI.

The sortilin-related receptor 1 (SORL1) gene, encoding the cellular endosomal sorting-related receptor with A-type repeats (SORLA), is now established as a causal gene for Alzheimer's disease. As the latest addition to the list of causal genes, the pathophysiological effects and biomarker potential of SORL1 variants remain relatively undiscovered. Metabolic dysfunction is, however, well described in patients with Alzheimer's disease and is used as an imaging biomarker in clinical diagnosis settings. To understand the metabolic consequences of loss-of-function SORL1 mutations, we applied two metabolic MRI technologies, sodium (23Na) MRI and MRI with hyperpolarized [1-13C]pyruvate, in minipigs and mice with compromised expression of SORL1. At the age analysed here, both animal models display no conventional imaging evidence of neurodegeneration but show biochemical signs of elevated amyloid production, thus representing the early preclinical disease. With hyperpolarized MRI, the exchange from [1-13C]pyruvate to [1-13C]lactate and 13C-bicarbonate was decreased by 32 and 23%, respectively, in the cerebrum of SORL1-haploinsufficient minipigs. A robust 11% decrease in the sodium content was observed with 23Na-MRI in the same minipigs. Comparably, the brain sodium concentration gradually decreased from control to SORL1 haploinsufficient (-11%) to SORL1 knockout mice (-23%), suggesting a gene dose dependence in the metabolic dysfunction. The present study highlights that metabolic MRI technologies are sensitive to the functional, metabolic consequences of Alzheimer's disease and Alzheimer's disease-linked genotypes. Further, the study suggests a potential avenue of research into the mechanisms of metabolic alterations by SORL1 mutations and their potential role in neurodegeneration.

Radiologic Classification of Hippocampal Sclerosis in Epilepsy.

Temporal lobe epilepsy is a common form of epilepsy that is often associated with hippocampal sclerosis (HS). Although HS is commonly considered a binary assessment in radiologic evaluation, it is known that histopathologic changes occur in distinct clusters. Some subtypes of HS only affect certain subfields, resulting in minimal changes to the overall volume of the hippocampus. This is likely a major reason why whole hippocampal volumetrics have underperformed versus expert readers in the diagnosis of HS. With recent advancements in MRI technology, it is now possible to characterize the substructure of the hippocampus more accurately. However, this is not consistently addressed in radiographic evaluations. The histologic subtype of HS is critical for prognosis and treatment decision-making, necessitating improved radiologic classification of HS. The International League Against Epilepsy (ILAE) has issued a consensus classification scheme for subtyping HS histopathologic changes. This review aims to explore how the ILAE subtypes of HS correlate with radiographic findings, introduce a grading system that integrates radiologic and pathologic reporting in HS, and outline an approach to detecting HS subtypes by using MRI. This framework will not only benefit current clinical evaluations, but also enhance future studies involving high-resolution MRI in temporal lobe epilepsy.

Neuroimaging of Parkinson's disease by quantitative susceptibility mapping

Parkinson's disease (PD) is a common neurodegenerative disease, and apart from a few rare genetic causes, its pathogenesis remains largely unclear. Recent scientific interest has been captured by the involvement of iron biochemistry and the disruption of iron homeostasis, particularly within the brain regions specifically affected in PD. The advent of Quantitative Susceptibility Mapping (QSM) has enabled non-invasive quantification of brain iron in vivo by MRI, which has contributed to the understanding of iron-associated pathogenesis and has the potential for the development of iron-based biomarkers in PD. This review elucidates the biochemical underpinnings of brain iron accumulation, details advancements in iron-sensitive MRI technologies, and discusses the role of QSM as a biomarker of iron deposition in PD. Despite considerable progress, several challenges impede its clinical application after a decade of QSM studies. The initiation of multi-site research is warranted for developing robust, interpretable, and disease-specific biomarkers for monitoring PD disease progression.

Dynamic parallel imaging at 9.4 T using reconfigurable receive coaxial dipoles.

Parallel imaging is one of the key MRI technologies that allow reduction of image acquisition time. However, the parallel imaging reconstruction commonly leads to a signal-to-noise ratio (SNR) drop evaluated using a so-called geometrical factor (g-factor). The g-factor is minimized by increasing the number of array elements and their spatial diversity. At the same time, increasing the element count requires a decrease in their size. This may lead to insufficient coil loading, an increase in the relative noise contribution from the RF coil itself, and hence SNR reduction. Previously, instead of increasing the channel number, we introduced the concept of electronically switchable time-varying sensitivities, which was shown to improve parallel imaging performance. In this approach, each reconfigurable receive element supports two spatially distinct sensitivity profiles. In this work, we developed and evaluated a novel eight-element human head receive-only reconfigurable coaxial dipole array for human head imaging at 9.4 T. In contrast to the previously reported reconfigurable dipole array, the new design does not include direct current (DC) control wires connected directly to the dipoles. The coaxial cable itself is used to deliver DC voltage to the PIN diodes located at the ends of the antennas. Thus, the novel reconfigurable coaxial dipole design opens a way to scale the dynamic parallel imaging up to a realistic number of channels, that is, 32 and above. The novel array was optimized and tested experimentally, including in vivo studies. It was found that dynamic sensitivity switching provided an 8% lower mean and 33% lower maximum g-factor (for Ry × Rz = 2 × 2 acceleration) compared with conventional static sensitivities.

Deep learning applications in MRI for brain tumor detection and image segmentation

Deep learning holds great potential in the field of MRI applications. By leveraging its advanced algorithms and neural networks, it can effectively analyze and interpret intricate patterns in medical images, aiding in precise disease detection, segmentation, and classification. Integrating deep learning techniques with MRI technology is expected to revolutionize radiology practice, facilitating enhanced diagnostic accuracy and customized treatment strategies, ultimately leading to improved patient outcomes. This article provides an overview of of the latest advancements in deep learning techniques applied to magnetic resonance imaging, specifically focusing on brain tumor detection and segmentation. The study examines eight different deep learning methods, including a multi-scale convolutional neural network, U-Net-based fully convolutional networks, cascaded anisotropic convolutional neural networks, missing modality-based tumor segmentation, Hough-CNN for deep brain region segmentation, k-Space deep learning for accelerated MRI, Multi-level Kronecker Convolutional Neural Network, and a heuristic approach for clinical brain tumor segmentation. Each method is analyzed, highlighting its specific techniques, advantages, and limitations. The comparative performance of these methods in terms of accuracy and efficiency, addressing key factors such as computational requirements, training time, and robustness, was discussed in this article. By assessing the merits and limitations of different approaches, this review seeks to offer valuable perspectives on effective utilization of deep learning techniques in clinical MRI settings for detecting and delineating brain tumors.

Cutting-Edge MRI Technology Reveals Post-COVID Alterations in the Brain

Cutting-Edge MRI Technology Reveals Post-COVID Alterations in the Brain

Abstract 89: Portable, Low-Field Magnetic Resonance Imaging: Determining Mismatch Following Acute Ischemic Stroke

Background and Aims: Treatment options for acute ischemic stroke (AIS) are uniquely dependent on the time of stroke onset. Intravenous thrombolysis must be administered within 4.5 hours of symptoms commencing, yet a subset of patients wake-up with symptoms and time of onset is unknown. Mismatch between fluid-attenuated inversion recovery (FLAIR) and diffusion-weighted imaging (DWI) MRI can be used to qualify wake-up strokes for thrombolysis. This has been shown to lead to improved functional outcomes in multicenter trials (WAKE-UP, MR-WITNESS). However, access to MRI is a barrier to differential diagnosis and subsequent treatment. Recent advances in portable, low-field MRI (LF-MRI) offer a solution to increase access to MRI technologies and circumvent the limitations of conventional systems. As such, in this pilot study, we sought to establish the utility of portable LF-MRI to identify DWI-FLAIR mismatch following AIS. Methods: Patients with a diagnosis of AIS presenting to Emergency Department or Intensive Care Unit of the Yale New Haven Hospital or Massachusetts General Hospital from January 2020 to June 2023 underwent DWI and FLAIR acquisition on a 0.064T MRI (Hyperfine Research Inc.) at <4.5 hours ( n =7), 4.5-6 hours ( n =7), and 6-48 hours ( n =110) since last known well (LKW). Conventional high-field (HF) MR images were acquired within 72 hours of LF-MRI. HF-DWI images were co-registered to LF-FLAIR and the hyperintense DWI stroke lesion segmented and superimposed on the FLAIR. The segmentation was mirrored to the contralateral hemisphere of the LF-FLAIR to establish a FLAIR signal intensity ratio (SIR). Results: The FLAIR SIR on images <4.5 hours since LKW was 0.98±0.08. The SIR for cases 4.5-6 hours was 1.34±0.33. Cases 6-48 hours produced a SIR of 1.56±0.36. The SIR at <4.5 hours was significantly less than that observed >6 hours since LKW ( p =0.03). Conclusion: This pilot study demonstrates that a 0.064T portable MRI is capable of distinguishing hyperacute stroke from later stroke onset using FLAIR SIR. Future research is needed in a larger cohort to determine if this imaging technology can be used to guide thrombolysis in the setting of wake-up stroke.

Primer on Adhesive Arachnoiditis

This article explores the resurgence of adhesive arachnoiditis (AA), a previously rare disorder, in the 21st century. Historically linked to tuberculosis and other infections, AA’s re-emergence is attributed to advancements in MRI technology, aiding in improved diagnosis and an increase in spinal procedures, possibly leading to iatrogenic cases. Complications of AA include chronic pain and motor dysfunction, significantly impacting quality of life. Treatment involves a multidisciplinary approach, including pharmacological and osteopathic treatments, possible surgical interventions, and psychological support. The article provides an in-depth look at AA’s epidemiology, clinical profile, causes, diagnosis, and treatment strategies, highlighting its complex nature and the necessity for heightened awareness among medical practitioners.

Harnessing technology to measure individual differences in spatial thinking in early childhood from a relational developmental systems perspective.

According to the Relational Developmental Systems perspective, the development of individual differences in spatial thinking (e.g., mental rotation, spatial reorientation, and spatial language) are attributed to various psychological (e.g., children's cognitive strategies), biological (e.g., structure and function of hippocampus), and cultural systems (e.g., caregiver spatial language input). Yet, measuring the development of individual differences in spatial thinking in young children, as well as the psychological, biological, and cultural systems that influence the development of these abilities, presents unique challenges. The current paper outlines ways to harness available technology including eye-tracking, eye-blink conditioning, MRI, Zoom, and LENA technology, to study the development of individual differences in young children's spatial thinking. The technologies discussed offer ways to examine children's spatial thinking development from different levels of analyses (i.e., psychological, biological, cultural), thereby allowing us to advance the study of developmental theory. We conclude with a discussion of the use of artificial intelligence.

TransUNet for Precise and Robust GI tract Segmentation in MRI Images

Medical image processing is revolutionizing Gastrointestinal (GI) cancer radiation therapy by enabling precise targeting of high X-ray beam dosages to the tumors while protecting the surrounding healthy organs. However, the manual segmentation of healthy organs at risk from MR-Linac images is a time-consuming process that can delay treatment and increase patient suffering. Deep learning-based medical image processing algorithms have the potential to automate the segmentation of organs at risk, thereby improving the accuracy and efficiency of GI cancer radiation therapy. Every day, the MR-Linac, a cutting-edge MRI technology, tracks the ever-changing positions of tumors. This advanced tool empowers medical professionals to fine-tune cancer treatments with remarkable precision. This study presents a TransUNet model, a combination of transformer architecture with Convolutional Neural Networks (CNNs). TransUNet achieves remarkable results in segmenting and labeling different regions within images by integrating the spatial comprehension of CNNs with the self-attention mechanisms of transformers. Our research compares the TransUNet model with various combinations of loss functions. The model outperforms with Dice+BCE loss function.

Ethical, legal, and policy challenges in field-based neuroimaging research using emerging portable MRI technologies: guidance for investigators and for oversight

Abstract Researchers are rapidly developing and deploying highly portable MRI technology to conduct field-based research. The new technology will widen access to include new investigators in remote and unconventional settings and will facilitate greater inclusion of rural, economically disadvantaged, and historically underrepresented populations. To address the ethical, legal, and societal issues raised by highly accessible and portable MRI, an interdisciplinary Working Group (WG) engaged in a multi-year structured process of analysis and consensus building, informed by empirical research on the perspectives of experts and the general public. This article presents the WG’s consensus recommendations. These recommendations address technology quality control, design and oversight of research, including safety of research participants and others in the scanning environment, engagement of diverse participants, therapeutic misconception, use of artificial intelligence algorithms to acquire and analyze MRI data, data privacy and security, return of results and managing incidental findings, and research participant data access and control.

Advancement in brain tumour detection using deep learning technique

The advancements in medical imaging technology, such as integrating InceptionV3 algorithms with MRI scans, have revolutionized brain tumor detection. These algorithms leverage deep learning to analyze MRI images rapidly and accurately, aiding in the precise identification of potential tumors. This integration enhances the efficiency of radiologists, enabling timely interventions and improving patient outcomes. The seamless synergy between MRI technology an deep learning algorithms marks a significant leap forward in neurology, promising more personalized and effective care for patients with brain tumors. Ongoing innovation in medical imaging and AI holds great potential for further improving diagnostic accuracy and treatment effectiveness in the future.

Assessment of undergraduates nursing students’ knowledge toward MRI safety: Cross-sectional study

IntroductionMagnetic resonance imaging (MRI) has been traditionally regarded as a relatively safe imaging modality due to the absence of ionizing radiation. However, considerable immediate safety risks are intrinsic to the MRI environment, necessitating comprehensive awareness and training among healthcare professionals, particularly nurses, who accompany their patients to the MRI department in most cases. This study was carried out to evaluate the level of knowledge and awareness of MRI safety issues among nursing students within the nursing faculty at Jazan University (JU). Materials and methodsA descriptive, cross-sectional survey encompassing 128 undergraduate nursing students was conducted. A structured questionnaire comprising 25 questions was employed and classified into three sections, encompassing demographic data and MRI safety awareness. Data were analyzed using Microsoft Excel, and frequencies and percentages of responses were calculated and summarized. ResultsOf the 128 participants, 111 were females, and 17 were males, distributed across the 2nd (41%), 3rd (20%), and 4th (39%) academic years. Participants exhibited a commendable grasp of MRI contraindications related to ferromagnetic materials such as oxygen cylinders and metal needles. However, their knowledge concerning the operational aspects of MRI, such as examination duration, was found to be lacking, indicating a significant deficiency in comprehension regarding the operational aspects of MRI technology. ConclusionThis study highlights the relatively high level of awareness regarding MRI safety among nursing students at JU. However, the identified lack of knowledge pertaining to the operational aspects of MRI technology emphasizes the need for further education and training in this area. To address this gap, we recommend the establishment of comprehensive MRI safety courses and training programs customized for undergraduate nursing students.

7 Tesla Brain MRI: A Paradigm Shifting Technology for Clinical Research in Aging and Dementia Science

AbstractBackgroundAs the usage of MRI for biomedical research increases, an ongoing goal for extending the usefulness of MRIs has been the increase of the magnet’s field strength to 3T, 7T, and beyond. The 7T field strength has recently been given FDA‐approval for clinical use, due to recognition of its safety and ability to characterize “smaller structures and subtle pathologies” 1 when compared to 3T (Fig. 1.)Technological developments at the 7 Tesla Bioengineering Research Program (7TBRP) at University of Pittsburgh is currently enabling neuroimaging translational research for 35 active 7T‐based NIH research projects with projected ∼ 7000 7T scan sessions that focus on studying aging, AD, COVID‐19 among several other neurodegenerative diseases.MethodsWe have developed a new (Fig. 2 and 3) device (Version 2 of Tic Tac Toe radiofrequency (RF) coil system) composed of 60 transmit channels – first of a kind ‐ and 32 receive channels. The coil has been deployed to Pittsburgh’s Imaging Community and is currently being used in a wide variety of NIH‐funded studies.ResultsCompared to other commercially available coils, this new RF coil system provides more homogeneous excitation, signal/contrast to noise ratio, and extended coverage of hard‐to‐reach regions at 7T (brain stem/temporal lobes/cerebellum.) Furthermore, the new RF coil system is also an anti‐claustrophobia solution at 7T as it provides a face opening in the front of the head resulting in more comfortable breathing, less claustrophobia, and a better overall 7T MRI experience for the participants.ConclusionAmong several other neurodegenerative diseases, advances in 7T MRI technology have allowed us to explore the common biology underlying aging, Alzheimer disease as well as the neurological sequelae following infection with SARS‐CoV‐2 (from imaging data harmonized across 3 different 7T sites) Funding: R56AG074467, R01MH111265 and R01AG0635251. https://www.fda.gov/news-events/press-announcements/fda-clears-first-7t-magnetic-resonance-imaging-device

NIMG-26. DIFFERENTIATION OF IDH-WILDTYPE GLIOBLASTOMA AND TUMEFACTIVE MULTIPLE SCLEROSIS USING PRE-OPERATIVE BRAIN MRI AND DEEP LEARNING: RIGOROUS AND UNBIASED EXPERIMENTAL DESIGN AND ANALYTICAL APPROACH

Abstract Clinical management of IDH wildtype glioblastoma (GBM) and tumefactive multiple sclerosis (tMS) is drastically different. GBM requires maximal safe resection followed by chemoradiation, while tMS outcome is worsened by surgery and radiotherapy. Misdiagnosis of brain lesions may expose patients to unnecessary anxiety, surgery, or radiotherapy. Noninvasive methods to help with accurate diagnosis of tumor and non-tumor etiologies are needed. tMS subjects were identified by the Mayo Clinic Center for Multiple Sclerosis and Autoimmune Neurology (CMSAN). GBM subjects were matched to tMS by age at diagnosis, index MRI date, and sex. Inclusion criteria included one cm minimal lesion size and pre-operative post-contrast T1 and T2 images available for analysis. To identify potential experimental design bias, MRI technology and clinical characteristics were compared across groups. A 3D-DenseNet121 was used to develop a classification model using prespecified parameters: 600 epochs, batch size 16, learning rate 10-3, cross entropy loss, and AdamW optimizer. The stopping rule was defined as three sequential epoch cross entropy loss < 0.02. Five-fold cross validation (CV) was utilized to obtain an unbiased estimate of predictive performance (overfitting) and sensitivity of the 3D-DenseNet121 algorithm was evaluated. 224 subjects (114 GBM, 110 tMS) were analyzed: 40% male, median age 46. After one round of CV, the average unbiased estimate of sensitivity and specificity for predicting GBM from the final classification model was 0.86 and 0.73, respectively. To assess the reproducibility of the deep learning algorithm (3D-DenseNet121), the exact same CV folds were rerun resulting in average sensitivity and specificity of 0.82 and 0.75, respectively. Obtaining unbiased estimates of model performance using internal validation is critical before evaluating a final model on an external dataset. Understanding sensitivity of a deep learning algorithm is important for model validity. Differentiation of GBM and tMS appears reasonable with MRI; external validation is in progress.

Letter to the Editor: Comparing quantitative MRI technologies in steatotic liver disease.

Letter to the Editor: Comparing quantitative MRI technologies in steatotic liver disease.

Reply: Comparing quantitative MRI technologies in steatotic liver disease.

Reply: Comparing quantitative MRI technologies in steatotic liver disease.

Augmenting breast cancer diagnosis: Incorporating MRI for the assessment of major molecular subtypes

Objectives: Breast cancer (BC) is one of the commonly encountered cancer in women around the world. It is a diverse medical disorder with multiple molecular subtypes that respond differently to therapy and have different prognoses. Subjects with the same stage of cancer and identical histological findings, on the other hand, can have disparities in clinical features and prognosis. Luminal A, Luminal B, Human epidermal growth factor receptor 2 (HER2) enriched, and triple-negative molecular subtypes were identified using novel technologies in expression analysis with DNA microarray. The precise identification of these subtypes is crucial for tailoring appropriate treatment strategies and improving patient outcomes. Dynamic contrast-enhanced magnetic resonance imaging (DCEMRI) is an excellent imaging technique for determining the extent of disease in BC patients prior to surgery. DECMRI with gadolinium-based contrasts is now the most sensitive identification tool for diagnosis, and it can be used in conjunction with mammography and ultrasound (USG). It aids in the detection of lesions that are not visible using other approaches. Material and Methods: Cross-sectional, observational study done over a period of 1 year. Sample size: 50 Inclusion criteria: Patients with morphological features of Breast Imaging Reporting and Data System (BI-RADS) 4b,4c,5 on USG or mammogram. Patients with malignancy confirmed through biopsy - BI-RADS 6. Patients aged above 18 years. Patients who provided informed consent to participate in the study. Exclusion criteria: Pregnant and lactating women. Patients with pacemakers, prosthetic heart valves, cochlear implants, or any metallic implants. Patients having a history of claustrophobia. Patients with prior surgery in the breast, hormonal therapy, radiation, or chemotherapy. Patients with previous allergic or anaphylactoid reactions to a gadolinium-based contrast. Patients with altered renal function test and estimated glomerular filtration rate <30 mL/min/1.73 mm2. Results: There was a substantial relationship between shape and molecular subtype. The majority of the luminal type of cancers was irregular, whereas the basal type was round. There was no link found between margin and molecular subtypes. Noncircumscribed margins, on the other hand, were more common in luminal subtypes. Internal enhancement and molecular subtypes were found to be significantly related. Rim enhancement was more prevalent in the basal subtype. According to ANOVA analysis, there was a significant relationship between volume and molecular subtypes. At the time of presentation, Luminal B tumors had a significant tumor volume. Conclusion: In conclusion, MRI plays a pivotal role in the evaluation of molecular subtypes of breast cancer, providing valuable information for personalized treatment decisions. Advancements in MRI technology and radiogenomics hold great promise for enhancing subtype-specific characterization and improving patient outcomes.

EP02.09: The evaluation of embryo development in early pregnancy using 3D Crystal Vue, MRI, and digital embryos technology

EP02.09: The evaluation of embryo development in early pregnancy using 3D Crystal Vue, MRI, and digital embryos technology