Validation of a new T2* algorithm and its uncertainty value for cardiac and liver iron load determination from MRI magnitude images.
Ontology highlight
ABSTRACT: Purpose
To validate an automatic algorithm for offline T2* measurements, providing robust, vendor-independent T2*, and uncertainty estimates for iron load quantification in the heart and liver using clinically available imaging sequences.Methods
A T2* region of interest (ROI)-based algorithm was developed for robustness in an offline setting. Phantom imaging was performed on a 1.5 Tesla system, with clinically available multiecho gradient-recalled-echo (GRE) sequences for cardiac and liver imaging. A T2* single-echo GRE sequence was used as reference. Simulations were performed to assess accuracy and precision from 2000 measurements. Inter- and intraobserver variability was obtained in a patient study (n = 23).Results
Simulations: Accuracy, in terms of the mean differences between the proposed method and true T2* ranged from 0-0.73 ms. Precision, in terms of confidence intervals of repeated measurements, was 0.06-4.74 ms showing agreement between the proposed uncertainty estimate and simulations. Phantom study: Bias and variability were 0.26 ± 4.23 ms (cardiac sequence) and -0.23 ± 1.69 ms (liver sequence). Patient study: Intraobserver variability was similar for experienced and inexperienced observers (0.03 ± 1.44 ms versus 0.16 ± 2.33 ms). Interobserver variability was 1.0 ± 3.77 ms for the heart and -0.52 ± 2.75 ms for the liver.Conclusion
The proposed algorithm was shown to provide robust T2* measurements and uncertainty estimates over the range of clinically relevant T2* values. Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance.
SUBMITTER: Bidhult S
PROVIDER: S-EPMC4791092 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:IntroductionBladder magnetic resonance imaging (MRI) has been recently integrated in the diagnosis pathway of bladder cancer. However, automatic recognition of suspicious lesions is still challenging. Thus, development of a solution for proper delimitation of the tumor and its separation from the healthy tissue is of primordial importance. As a solution to this unmet medical need, we aimed to develop an artificial intelligence-based decision support system, which automatically segments the bladder wall and the tumor as well as any suspect area from the 3D MRI images.MaterialsWe retrospectively assessed all patients diagnosed with bladder cancer, who underwent MRI at our department (n=33). All examinations were performed using a 1.5 Tesla MRI scanner. All images were reviewed by two radiologists, who performed manual segmentation of the bladder wall and all lesions. First, the performance of our fully automated end-to-end segmentation model based on a 3D U-Net architecture (by considering various depths of 4, 5 or 6 blocks) trained in two data augmentation scenarios (on 5 and 10 augmentation datasets per original data, respectively) was tested. Second, two learning setups were analyzed by training the segmentation algorithm with 7 and 14 MRI original volumes, respectively.ResultsWe obtained a Dice-based performance over 0.878 for automatic segmentation of bladder wall and tumors, as compared to manual segmentation. A larger training dataset using 10 augmentations for 7 patients could further improve the results of the U-Net-5 model (0.902 Dice coefficient at image level). This model performed best in terms of automated segmentation of bladder, as compared to U-Net-4 and U-Net-6. However, in this case increased time for learning was needed as compared to U-Net-4. We observed that an extended dataset for training led to significantly improved segmentation of the bladder wall, but not of the tumor.ConclusionWe developed an intelligent system for bladder tumors automated diagnostic, that uses a deep learning model to segment both the bladder wall and the tumor. As a conclusion, low complexity networks, with less than five-layers U-Net architecture are feasible and show good performance for automatic 3D MRI image segmentation in patients with bladder tumors.
| S-EPMC10033524 | biostudies-literature
Project description:Despite the proliferation of deep learning techniques for accelerated MRI acquisition and enhanced image reconstruction, the construction of large and diverse MRI datasets continues to pose a barrier to effective clinical translation of these technologies. One major challenge is in collecting the MRI raw data (required for image reconstruction) from clinical scanning, as only magnitude images are typically saved and used for clinical assessment and diagnosis. The image phase and multi-channel RF coil information are not retained when magnitude-only images are saved in clinical imaging archives. Additionally, preprocessing used for data in clinical imaging can lead to biased results. While several groups have begun concerted efforts to collect large amounts of MRI raw data, current databases are limited in the diversity of anatomy, pathology, annotations, and acquisition types they contain. To address this, we present a method for synthesizing realistic MR data from magnitude-only data, allowing for the use of diverse data from clinical imaging archives in advanced MRI reconstruction development. Our method uses a conditional GAN-based framework to generate synthetic phase images from input magnitude images. We then applied ESPIRiT to derive RF coil sensitivity maps from fully sampled real data to generate multi-coil data. The synthetic data generation method was evaluated by comparing image reconstruction results from training Variational Networks either with real data or synthetic data. We demonstrate that the Variational Network trained on synthetic MRI data from our method, consisting of GAN-derived synthetic phase and multi-coil information, outperformed Variational Networks trained on data with synthetic phase generated using current state-of-the-art methods. Additionally, we demonstrate that the Variational Networks trained with synthetic k-space data from our method perform comparably to image reconstruction networks trained on undersampled real k-space data.
| S-EPMC10045391 | biostudies-literature
Project description:Current protocol of Amide Proton Transfer-weighted (APTw) imaging commonly starts with the acquisition of high-resolution T2-weighted (T2w) images followed by APTw imaging at particular geometry and locations (i.e. slice) determined by the acquired T2w images. Although many advanced MRI reconstruction methods have been proposed to accelerate MRI, existing methods for APTw MRI lacks the capability of taking advantage of structural information in the acquired T2w images for reconstruction. In this paper, we present a novel APTw image reconstruction framework that can accelerate APTw imaging by reconstructing APTw images directly from highly undersampled k-space data and corresponding T2w image at the same location. The proposed framework starts with a novel sparse representation-based slice matching algorithm that aims to find the matched T2w slice given only the undersampled APTw image. A Recurrent Feature Sharing Reconstruction network (RFS-Rec) is designed to utilize intermediate features extracted from the matched T2w image by a Convolutional Recurrent Neural Network (CRNN), so that the missing structural information can be incorporated into the undersampled APT raw image thus effectively improving the image quality of the reconstructed APTw image. We evaluate the proposed method on two real datasets consisting of brain data from rats and humans. Extensive experiments demonstrate that the proposed RFS-Rec approach can outperform the state-of-the-art methods.
| S-EPMC7577831 | biostudies-literature
Project description:OBJECTIVE::Prior studies advocate the subjective visual differences between meningioma and schwannoma on T2 weighted images, however objective measurement of signal intensity differences may be useful in certain cases. The aim of this study was to investigate whether an objective evaluation of SIs on T2 weighted images would be useful to differentiate spinal schwannomas from meningiomas. METHODS::The patients with spinal MRIs demonstrating path proven and subsequently treated intradural extramedullary spinal tumors were selected between April 2008 and May 2017. Regions of interest (ROIs) were measured in the tumor and subcutaneous fat on the same image, and we calculated the SI ratio between tumor and fat ROIs. RESULTS::Twenty patients each with meningioma and schwannoma were enrolled. The SI ratios of schwannomas were significantly higher than those of meningiomas (both researcher 1 and 2: p = 0.002). The areas under the curve by researchers 1 and 2 were 0.780. The cutoff value of SI ratio by both of researchers 1 and 2 to differentiate between schwannomas from meningiomas was 0.420 (sensitivity: 80.0%, specificity: 70.0-75.0%). CONCLUSION::The SI ratio, calculated from the SIs of the tumor and fat on T2 weighted images, is useful for differentiating spinal schwannomas from meningiomas to obtain an accurate diagnosis. ADVANCES IN KNOWLEDGE::Signal intensity ratio of the spinal tumor and fat on T2 weighted images is useful for differentiating schwannomas from meningiomas to obtain an accurate diagnosis.
| S-EPMC6319836 | biostudies-literature
Project description:To compare the similarity of the non-patented T2* and the high cost patented R2 (Ferriscan®) MRI techniques in the measurement of liver iron concentration (LIC) in heavily transfused patients with thalassaemia major in a real- life Sri Lankan hospital setup. We compared LIC measured by MRI, obtained 2 weeks apart, using both T2* and R2 techniques in 15 patients with beta thalassaemia major. They all had a history of > 100 units of blood transfusions life long and also a history of sub optimal chelation. MRI R2 and MRI T2* scan values showed a negative correlation (co-rrelation coefficient = - 0.63, p = 0.01) This correlation was strong in lower LICs and progressively decreased with upper LIC values. Thus a significant discrepancy was observed between median values of two MRI technologies (p = 0.0005) with T2* tending to underestimate iron overload especially in those with very high LIC identified by R2. The lack of concordance of T2* and R2 especially in those with very high reading on R2 suggest the potential errors in interpretations that can occur in "non-expert centres"; which are likely to lead to errors in clinical judgement on the intensity of chelation therapy needed.
| S-EPMC6977251 | biostudies-literature
Project description:The value of iron-based MRI changes for the diagnosis and staging of Alzheimer's disease (AD) depends on an association between cortical iron accumulation and AD pathology. Therefore, this study determined the cortical distribution pattern of MRI contrast changes in cortical regions selected based on the known distribution pattern of tau pathology and investigated whether MRI contrast changes reflect the underlying AD pathology in the different lobes. T2*-weighted MRI was performed on postmortem cortical tissue of controls, late-onset AD (LOAD), and early-onset AD (EOAD) followed by histology and correlation analyses. Combining ex vivo high-resolution MRI and histopathology revealed that: 1) LOAD and EOAD have a different distribution pattern of AD pathological hallmarks and MRI contrast changes over the cortex, with EOAD showing more severe MRI changes; 2) per lobe, severity of AD pathological hallmarks correlates with iron accumulation, and hence with MRI. Therefore, iron-sensitive MRI sequences allow detection of the cortical distribution pattern of AD pathology ex vivo.
| S-EPMC6218127 | biostudies-literature
Project description:BackgroundNeurodegeneration with brain iron accumulation (NBIA) defines a group of genetic disorders characterized by brain iron deposition and associated with neuronal death. The known causes of NBIA include pantothenate kinase-associated neurodegeneration (PKAN), neuroferritinopathy, infantile neuroaxonal dystrophy (INAD), and aceruloplasminemia.ObjectiveTo define the radiologic features of each NBIA subtype.MethodsBrain MRIs from patients with molecularly confirmed PKAN (26 cases), neuroferritinopathy (21 cases), INAD (four cases), and aceruloplasminemia (10 cases) were analyzed blindly to delineate patterns of iron deposition and neurodegeneration.ResultsIn most cases of PKAN, abnormalities were restricted to globus pallidus and substantia nigra, with 100% having an eye of the tiger sign. In a minority of PKAN cases there was hypointensity of the dentate nuclei (1/5 on T2* sequences, 2/26 on fast spin echo [FSE]). In INAD, globus pallidus and substantia nigra were involved on T2* and FSE scans, with dentate involvement only seen on T2*. By contrast, neuroferritinopathy had consistent involvement of the dentate nuclei, globus pallidus, and putamen, with confluent areas of hyperintensity due to probable cavitation, involving the pallida and putamen in 52%, and a subset having lesions in caudate nuclei and thalami. More uniform involvement of all basal ganglia and the thalami was typical in aceruloplasminemia, but without cavitation.ConclusionsIn the majority of cases, different subtypes of neurodegeneration associated with brain iron accumulation can be reliably distinguished with T2* and T2 fast spin echo brain MRI, leading to accurate clinical and subsequent molecular diagnosis.
| S-EPMC2706154 | biostudies-literature
Project description:The treatment of sickle cell disease (SCD) is mainly supportive, except for a minority, who receive bone marrow transplantation (BMT). Serum ferritin (SF) is routinely available but is notoriously unreliable as a tool for iron-overload assessment since it is an acute-phase reactant. Although blood transfusion is one of the most effective ways to deal with specific acute and chronic complications of SCD, this strategy is often associated with alloimmunization, iron overload, and hemolytic reactions. This study, thus, aims to evaluate iron overload in patients with SCD on chronic blood transfusions and specifically, correlate SF with the current standard of care of iron-overload assessment using MRI-based imaging techniques. Amongst a historic cohort of 58 chronically transfused patients with SCD, we were able to evaluate 44 patients who are currently alive and had multiple follow-up testing. Their mean age (±SD) was 35 (9) years and comprised of 68.2% of women. The studied iron-overload parameters included cardiac T2* MRI, liver iron concentration (LIC) by Liver T2* MRI, and serial SF levels. Additionally, in a smaller cohort, we also studied LIC by FerriScan© R2-MRI. Chronic blood transfusions were necessary for severe vaso-occlusive crisis (VOC) (38.6%), severe symptomatic anemia (38.6%), past history of stroke (15.9%), and recurrent acute chest syndrome (6.9%). About 14 (24%) patients among the original cohort died following SCD-related complications. Among the patients currently receiving chelation, 26 (96%) are on Deferasirox (DFX) [Jadenu® (24) or Exjade® (2)], with good compliance and tolerance. However, one patient is still receiving IV deferoxamine (DFO), in view of the significantly high systemic iron burden. In this evaluable cohort of 44 patients, the mean SF (±SD) reduced marginally from 4,311 to 4,230 ng/ml, mean Liver T2* MRI dropped from 12 to 10.3 mg/gm dry weight, while the mean cardiac T2*MRI improved from 36.8 to 39.5 ms. There was a mild to moderate correlation between the baseline and final values of SF ng/ml, r = 0.33, p = 0.01; Cardiac T2* MRI ms, r = 0.3, p = 0.02 and Liver T2* MRI mg/kg dry weight, r = 0.6, p < 0.001. Overall, there was a positive correlation between SF and Liver T2* MRI (Pearson's r = 0.78, p < 0.001). Cardiac T2*MRI increased with the decreasing SF concentration, showing a negative correlation which was statistically significant (Pearson's r = -0.6, p < 0.001). Furthermore, there was an excellent correlation between SF ng/ml and LIC by FerriScan© R2-MRI mg/g or mmol/kg (Spearmen's rho = -0.723, p < 0.008) in a small subset of patients (n = 14) who underwent the procedure. In conclusion, our study demonstrated a good correlation between serial SF and LIC by either Liver MRI T2* or by FerriScan© R2-MRI, even though SF is an acute-phase reactant. It also confirms the cardiac sparing effect in patients with SCD, even with the significant transfusion-related iron burden. About 14 (24%) patients of the original cohort died over the past 15 years, indicative of a negative impact of iron overload on disease morbidity and mortality.
| S-EPMC8573209 | biostudies-literature
Project description:Although shown to have a great utility for a wide range of neuroscientific and clinical applications, diffusion-weighted magnetic resonance imaging (dMRI) faces a major challenge of low signal-to-noise ratio (SNR), especially when pushing the spatial resolution for improved delineation of brain's fine structure or increasing the diffusion weighting for increased angular contrast or both. Here, we introduce a comprehensive denoising framework for denoising magnitude dMRI. The framework synergistically combines the variance stabilizing transform (VST) with optimal singular value manipulation. The purpose of VST is to transform the Rician data to Gaussian-like data so that an asymptotically optimal singular value manipulation strategy tailored for Gaussian data can be used. The output of the framework is the estimated underlying diffusion signal for each voxel in the image domain. The usefulness of the proposed framework for denoising magnitude dMRI is demonstrated using both simulation and real-data experiments. Our results show that the proposed denoising framework can significantly improve SNR across the entire brain, leading to substantially enhanced performances for estimating diffusion tensor related indices and for resolving crossing fibers when compared to another competing method. More encouragingly, the proposed method when used to denoise a single average of 7 Tesla Human Connectome Project-style diffusion acquisition provided comparable performances relative to those achievable with ten averages for resolving multiple fiber populations across the brain. As such, the proposed denoising method is expected to have a great utility for high-quality, high-resolution whole-brain dMRI, desirable for many neuroscientific and clinical applications.
| S-EPMC7292796 | biostudies-literature
Project description:Several advances in computing facilities were made due to the advancement of science and technology, including the implementation of automation in multi-specialty hospitals. This research aims to develop an efficient deep-learning-based brain-tumor (BT) detection scheme to detect the tumor in FLAIR- and T2-modality magnetic-resonance-imaging (MRI) slices. MRI slices of the axial-plane brain are used to test and verify the scheme. The reliability of the developed scheme is also verified through clinically collected MRI slices. In the proposed scheme, the following stages are involved: (i) pre-processing the raw MRI image, (ii) deep-feature extraction using pretrained schemes, (iii) watershed-algorithm-based BT segmentation and mining the shape features, (iv) feature optimization using the elephant-herding algorithm (EHA), and (v) binary classification and verification using three-fold cross-validation. Using (a) individual features, (b) dual deep features, and (c) integrated features, the BT-classification task is accomplished in this study. Each experiment is conducted separately on the chosen BRATS and TCIA benchmark MRI slices. This research indicates that the integrated feature-based scheme helps to achieve a classification accuracy of 99.6667% when a support-vector-machine (SVM) classifier is considered. Further, the performance of this scheme is verified using noise-attacked MRI slices, and better classification results are achieved.
| S-EPMC10252483 | biostudies-literature