Tomography Magnetic Resonance Imaging Research Articles

P10.22.B PREDICTING INTRAOPERATIVE 5-ALA-INDUCED TUMOR FLUORESCENCE VIA MRI AND DEEP LEARNING IN GLIOMAS WITH RADIOGRAPHIC LOWER-GRADE CHARACTERISTICS

Abstract BACKGROUND Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely resected to avoid undergrading. We aimed to analyze whether a deep learning model can predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Material and Methods: The MRI images of gliomas lacking high-grade characteristics (necrosis, extended contrast-enhancement, a.o.) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a 10-fold cross-validation procedure. RESULTS We evaluated a cohort of 163 glioma patients categorized as fluorescent (n=83) or non-fluorescent (n=80). Our proposed approach’s performance was evaluated using metrics such as mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. CONCLUSION Our findings highlight the potential of a U-Net model, coupled with a random forest classifier, for intraoperative fluorescence prediction. We achieved good accuracy using advanced techniques such as deep learning-based tumor segmentation and Variational Autoencoder for radiomics feature extraction. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

A novel classification framework for genome-wide association study of whole brain MRI images using deep learning.

Genome-wide association studies (GWASs) have been widely applied in the neuroimaging field to discover genetic variants associated with brain-related traits. So far, almost all GWASs conducted in neuroimaging genetics are performed on univariate quantitative features summarized from brain images. On the other hand, powerful deep learning technologies have dramatically improved our ability to classify images. In this study, we proposed and implemented a novel machine learning strategy for systematically identifying genetic variants that lead to detectable nuances on Magnetic Resonance Images (MRI). For a specific single nucleotide polymorphism (SNP), if MRI images labeled by genotypes of this SNP can be reliably distinguished using machine learning, we then hypothesized that this SNP is likely to be associated with brain anatomy or function which is manifested in MRI brain images. We applied this strategy to a catalog of MRI image and genotype data collected by the Alzheimer's Disease Neuroimaging Initiative (ADNI) consortium. From the results, we identified novel variants that show strong association to brain phenotypes.

Role of Advanced Magnetic Resonance Imaging in Differentiating among Glioma Subtypes and Predicting Tumor-Proliferative Behavior

Abstract Objective Gliomas are a devastating and heterogeneous group of primary brain tumors. Previously, the source of glioma was undetermined. Recent literature indicates that neural stem cells, or progenitors, are proposed to be the source of glioma. The prognosis of different types of gliomas differs due to their various biological tissue types. Besides the histological grade, the two useful immunohistochemistry markers that show the tumor's biological behavior are isocitrate dehydrogenase (IDH) labeling and the Ki-67 labeling index. We sought to determine the magnetic resonance imaging (MRI) characteristics associated with IDH mutational status and ascertain whether MRI combined with IDH mutational status, can better predict the clinical outcomes of gliomas. Materials and Methods This period study was conducted in the Department of Radiology, Sri Ramachandra Institute of Higher Education and Research, Chennai, Tamil Nadu, India for 5 years (May 2016–May 2021). The study cohort included 30 patients diagnosed with gliomas who underwent preoperative MRI followed by surgical resection and histopathological examination. Preoperative MRI images were done to assess qualitative tumor characteristics such as location, margin of tumor, extent, cortical involvement, cystic component, mineralization or hemorrhage, and contrast enhancement. Discussion Differences in MRI features between IDH-mutant (MT) and IDH-wild-type (WT) groups were analyzed using the chi-square test for categorical variables and the Mann–Whitney U test for continuous variables. Statistical analysis was conducted using SPSS software. Results Among the 30 patients evaluated, 18 had IDH-WT and 12 had IDH-MT type gliomas. Male predominance (73.33%) was noted in our study. Brainstem location, indistinct borders (83.33%), less cortical involvement (72.22%), less cystic changes (88.89%), more area of necrotic component (44.44%), significantly increased choline/creatine (Cho/Cr) ratio, and choline/N-acetyl aspartate (Cho/NAA) ratio favors IDH-WT tumors. Positive T2-fluid-attenuated inversion recovery mismatch sign is more frequently seen in IDH-MT (7/12; 58.33%) tumors than in IDH-WT (4/18; 22.22%) tumors. Whereas well-defined contours (66.67%), more cortical involvement (83.33%), more cystic changes (58.33%), and less area of necrotic component favor IDH-MT type tumors. Conclusion MRI is a very promising and valuable tool for differentiating among glioma subtypes and predicting tumor-proliferative behavior in glioma cases. The combination of MRI characteristics with IDH mutation status enhances the predictive accuracy for clinical outcomes in glioma patients. This approach could potentially guide treatment planning and improve prognostic assessments.

THE ASSOCIATION BETWEEN FACET JOINT TROPISM AND LUMBAR DISC HERNIATION

ABSTRACT Background/Aims: Facet joint tropism is thought to be associated with lumbar disc herniation (LDH), but this relationship has not been fully established. The aim of this study was to investigate the relationship between facet joint tropism and LDH in patients (25-30 years old and body-mass index 28-30 kg/m²) using computed tomography (CT) and lumbar magnetic resonance imaging (MRI). Methods: Facet joint angles were measured on lumbar MRI and CT images of 24 male patients with left-sided LDH; 16 patients with right-sided LDH. Facet joint angle was measured by calculating the angle of the facet joints with the vertebral sagittal line in axial sections parallel to the end plate plane. Patients with trauma, rheumatic and oncologic diseases, additional lumbar or spinal and systemic diseases, patients with far lateral, foraminal and central lumbar disc herniations were excluded. Results: The mean left facet joint angle was 44,56º+/-11,29° and the mean right facet joint angle was 41,2º+/-11,27° in 24 patients with left-sided LDH. In 16 patients with right-sided LDH, the mean right facet joint angle was 45,87º +/-16,41°and the mean left facet joint angle was 42,74º+/-12,54°. Conclusions: In the statistical evaluation, no significant correlation was found between LDH and facet joint angle, but in the numerical analysis, it was observed that the left facet joint angle was larger in patients with left-sided LDH and the right facet joint angle was larger in patients with right-sided LDH.

Upfront Thoracic Magnetic Resonance Imaging for the Evaluation of Thymic Lesions to Reduce Non-Therapeutic Diagnostic Thymectomy: A Narrative Review.

Background: Thymic pathologies represent the most common lesions of the anterior mediastinum. They may be classified as malignant or benign. Current diagnostic pathways recommend an initial assessment with computed tomography (CT) imaging to delineate potentially malignant thymic lesions. Despite this, high rates of non-therapeutic thymectomy continue to be observed. This carries with it significant anaesthetic, operative, and post-operative risks, in addition to healthcare costs. Consequently, there is a growing interest in magnetic resonance imaging (MRI) as a primary diagnostic modality for lesions of the anterior mediastinum. This narrative review outlines the current approaches to the evaluation of thymic lesions, with a discussion of the strengths and limitations of CT and MRI imaging modalities. It also evaluates the current discourse on the use of upfront MRI for thymic and anterior mediastinal lesion assessment. Methods: A narrative review was performed following a search on the Medline database. Articles that were evaluated had explored the role of MRI on the evaluation of thymic and anterior mediastinal lesions. Results: Current work-up for thymic and anterior mediastinal lesions are highly variable and centre around the use of CT. Upfront MRI demonstrates a similar accuracy to CT for various thymic and anterior mediastinal pathologies; however, the efforts to integrate this approach into routine practice remain in their infancy, with no standardised guidelines that exist. Conclusions: This narrative review demonstrates that there is a paucity of evidence relating to the sensitivity and specificity of MRI compared to CT for thymic lesion analysis and their subsequent relationship with non-therapeutic thymectomy. Future prospective trials to assess the role of MRI in thymic lesion determination are required to understand whether MRI can more accurately characterise these lesions to reduce non-therapeutic thymectomy. Additionally, further research efforts are required to characterise best-practice methods for integrating MRI into diagnostic pathways for these lesions in a cost-effective and resource-conscious manner.

Recovering MRI magnetic field strength properties using machine learning based on image compression quality scores

AbstractOver the years, significant hardware advancements have led to higher magnetic field MRI (Magnetic Resonance Imaging) acquisitions, providing improved diagnostic image quality at a higher cost. While higher image quality is desired, the investment required for high-field MRI imaging systems remains a significant consideration. Furthermore, historical patient records may still contain low-field magnetic strength MRI data. In this work, we present how image compression quality scores of MRI images could be used to recover their magnetic field strength properties. This work presents an interesting inverse problem scenario where output properties are used to recover an input property of an image. We implemented supervised machine learning models that utilize compressed image quality scores - based on Mean Squared Error (MSE), Structural Similarity Index (SSIM), Visual Information Fidelity (VIF), and Earth Movers Distance (EM) metrics - as inputs. These models classify images into specific classes of magnetic field strength at which they were acquired (Low, Medium, and High) based solely on the quality scores of their compressed copies. The trained machine learning models (Support Vector Machine (SVM), Logistic Regression, K-nearest Neighbours (KNN), Decision Tree and Random Forest) achieved nearly 100% performance efficiency based on accuracy and F-1 score for all considered quality measures. This comprehensive evaluation offers insights into how compression techniques and quality factors impact image fidelity across various MRI magnetic field strengths. The findings of this study may prove valuable in recovering missing meta-tag information in historical image DICOM records and Context-Based Retrieval Systems (CBRS). The approach of using quality scores as features in training machine learning models, as demonstrated in this work, can be extended to other image groups where input parameters create statistically significant distinctions or are challenging to extract from images.

Performing magnetic resonance imaging in patients with gunshot wounds: a guide for radiologists

INTRODUCTION: The safety of magnetic resonance imaging (MRI) in patients with metallic foreign bodies is an important aspect that has been the subject of many scientific papers and guidelines. The issue of MRI in patients with implanted medical devices is well researched. However, for gunshot wounds, there are no clear guidelines for practitioners, and most recommendations are to refuse to perform the study if there is the slightest doubt about its safety.OBJECTIVE: To systematize information on the safety and quality of MRI in patients with gunshot wounds and to develop practical guidelines for radiologists.MATERIALS AND METHODS: We have analyzed and summarized the main domestic and foreign recommendations for ensuring safety during MRI, generally accepted classifications and mechanisms of gunshot wounds.RESULTS: A review of physical risk factors in MRI, their causes, and recommendations for their minimization is presented. The influence of metallic objects on the appearance of artefacts on MRI images is considered. The algorithm of decision making on the safety of MRI in a patient with a bullet or shotgun wound is given. Two clinical observations are presented to illustrate the application of this algorithm.CONCLUSION: Performing MRI in gunshot wounds is feasible but requires careful analysis of the risks and the importance of diagnostic information. Interviewing the patient in these situations is often uninformative, so radiography or CT are the methods of choice for detection of metallic foreign bodies. To minimize the risks of MRI, a scan protocol should be prepared in advance and the patient should be monitored after each pulse sequence.

ADVANCEMENTS IN ALZHEIMER’S DIAGNOSIS THROUGH MRI USING BAYESIAN CONVOLUTIONAL NEURAL NETWORKS AND VARIATIONAL INFERENCE

Alzheimer’s disease is one of the brain disorders that can be deadly in older. The disease is less treated and less recognized, but Alzheimer’s disease is now a significant public health problem. Early detection of the disease can significantly reduce symptoms. However, the lack of medical personnel makes handling this disease complex. Therefore, an automatic diagnosis of Alzheimer’s disease is needed with a Magnetic Resonance Imaging (MRI) examination to get an accurate diagnosis of the disease. This study classified the type of Alzheimer’s disease with deep learning methods using the Bayesian Convolutional Neural Network (BCNN) and the Variational Inference (VI) technique. It aims to determine image classification and accuracy level at the level of Alzheimer’s disease by using 2,400 brain MRI images, divided into three classes (non-demented, very mild demented, and mild demented) based on severity. The data was acquired from the kaggle.com website. We use a dataset scenario of 80% for training and 20% for testing, 100x100 pixels, kernel size 3x3, and optimizer Adam with epoch 200. The accuracy of the image classification process is 80%. The non-demented label predicts that the uncertainty is 0.371, and the other uncertainty prediction is 0.002. The ability to anticipate uncertainty enables clinicians to make informed decisions regarding the reliability of the model’s output and the need for additional validation or confirmation.

Role of Artificial intelligence model in prediction of low back pain using T2 weighted MRI of Lumbar spine.

Low back pain (LBP), the primary cause of disability, is the most common musculoskeletal disorder globally and the primary cause of disability. Magnetic resonance imaging (MRI) studies are inconclusive and less sensitive for identifying and classifying patients with LBP. Hence, this study aimed to investigate the role of artificial intelligence (AI) models in the prediction of LBP using T2 weighted MRI image of the lumbar spine. This was a prospective case-control study. A total of 200 MRI patients (100 cases and controls each) referred for lumbar spine and whole spine screening were included. The scans were performed using 3.0 Tesla MRI (United Imaging Healthcare). T2 weighted images of the lumbar spine were segmented to extract radiomic features. Machine learning (ML) models, such as random forest, decision tree, logistic regression, K-nearest neighbors, adaboost, and deep learning methods (DL), such as ResNet and GoogleNet, were used, and performance measures were calculated. Our study showed that Random forest and AdaBoost are the most reliable ML models for predicting LBP. Random forest showed high performance with area under curve (AUC) values from 0.83 to 0.88 across all lumbar vertebrae and L2-L3, L3-L4, and L4-L5 intervertebral discs (IVDs), with AUCs of 0.88 the highest at L5-S1 IVD (0.92). Adaboost demonstrated high performance at the L2-L5 vertebrae with AUC values of 0.82 to 0.90, with the highest AUC (0.97) at the L5-S1 IVD. Among the DL models, GoogleNet outperformed the other models at 30 epochs with an accuracy of 0.85, followed by ResNet 18 (30 epochs) with an accuracy of 0.84. The study demonstrated that ML and DL models can effectively predict LBP from MRI T2 weighted image of the lumbar spine. ML and DL models could also enhance the diagnostic accuracy of LBP, potentially leading to better patient management and outcomes.

Federated learning and deep learning framework for MRI image and speech signal-based multi-modal depression detection

Adolescence is a significant period for developing skills and knowledge and learning about managing relationships and emotions by gathering attributes for maturity. Recently, Depression arises as a common mental health issue in adolescents and this affects the daily life of the person. This leads to educational and social impairments and this acts as a major risk for suicide. As a result, the identification and treatment for this disorder are essential. By applying Deep learning (DL) algorithms to medical data, the mental condition of a person can be predicted. However, the traditional deep learning models face the challenge in processing the huge sized data. Hence, FL has emerged as an efficient solution for addressing the data size issue of DL. Here, Depression detection in adolescents is carried out by considering the FL framework, which comprises two modules, namely the local module and the Global module. The detection process is done in the local module using the proposed Exponential African Pelican Optimization based Deep Convolutional Neural Network (ExpAPO-DCNN), whereas the Global module produces the aggregated output of the local module. In this research, FL utilizes the DL model in producing the output, where the DL model considered two modalities of inputs, such as speech signal and Magnetic Resonance Imaging (MRI) image. The processing steps used for this research are pre-processing, feature extraction and detection. For MRI and speech signals, all the above processes are carried out individually. Finally, both the outputs are fused utilizing the overlap coefficient. The ExpAPO-DCNN obtained accuracy, Loss, Root mean Squared error (RMSE), Mean Squared error (MSE), True Negative rate (TNR), and True Positive rate (TPR) of 98.00 %, 0.023, 0.058, 0.240, 97.90 %, and 96.30 %, respectively.

Algorithm development and metal oxide nanoparticle analysis in magnetic resonance imaging: Advancing neurodegenerative disease diagnostics

Magnetic resonance imaging (MRI) is critical in the diagnosis of neurodegenerative diseases, enabling the detection of brain lesions. Recent research has examined metallic nanoparticles (NPs) as MRI contrast agents (CAs) that can enhance lesion visibility by altering relaxation times. This study investigates the effects of metal oxide NPs on MRI relaxation times and brain lesion signals and proposes an algorithm for automated relaxation time determination using these NPs. The utilized NPs were synthesized using the sol‒gel method and characterized using Fourier-transform infrared spectroscopy and X-ray diffraction. MRI scans were performed on a phantom infused with varying concentrations of each metal oxide NP to assess changes in pixel signal intensities and relaxation rates. Our analysis involved segmenting the MRI images to focus on regions with different NP concentrations. The algorithm computed the longitudinal relaxation time for each region, revealing that Fe2O3 NPs exhibited the most substantial effect on signal intensity and relaxation time. The results indicated a high correlation (r = 0.9977), demonstrating strong agreement and confirming the reliability of our method. Our findings suggest that metallic oxide NPs, particularly Fe2O3, can considerably alter magnetization and act as effective negative CAs in MRI. These capabilities can improve the monitoring and treatment efficacy of neurodegenerative diseases. Our method for quantifying longitudinal relaxation times can potentially enhance routine clinical MRI assessments, offering a promising tool for future clinical applications.

The first experience of multi-modal in vivo PET/SPECT/CT and MRI imaging of laboratory mice with melanoma B16F10 (short message)

Background. For in vivo determination of size and metabolic characteristics of model tumors in laboratory animals, it is recommended to use imaging methods: positron emission tomography (PET), single-photon emission computed tomography (SPECT), computed tomography (CT) and magnetic resonance imaging (MRI). Due to the limited availability of hybrid scanners, it is necessary to investigate the feasibility of obtaining tomograms on separate devices with subsequent geometric comparison of images.Aim. To investigate the feasibility of multimodal imaging of mice with subcutaneous melanoma B16F10.Materials and methods. PET, SPECT and CT were performed using a preclinical VECTor 6 tomograph (MILabs, the Netherlands), MRI was performed using a preclinical nanoScan® 3T tomograph (Mediso, Hungary). The following modality combinations were studied: MRI and PET / CT with 18F-fluorodeoxyglucose; MRI and PET / CT with 18F-boronphenylalanine; MRI and PET / SPECT / CT with 18F-fluoroethyltyrosine (18F-FET) and 177lutetium – prostate-specific membrane antigen (177Lu-PSMA). Mice were immobilized in a custom-made device during scanning and during movement between tomographs. PET and MRI, SPECT and MRI images were fused in the program InterView FUSION 3.09.008.0000 through an intermediate stage of fusion with CT.Results. Multimodal PET / CT / MRI and PET / SPECT / CT / MRI images of tumor-bearing mice were obtained for the first time in Russia. PET / MRI data confirmed development of the tumor from 6 × 4 × 4 mm in size. PET / SPECT / CT / MRI enabled to image visceral organs with high accumulation of radionuclide tracers: pancreas with 18F-FET (standardized uptake value 2.6) and kidneys with 177Lu-PSMA (standardized uptake value 4.4), while the obtained images of organs did not merge and did not overlap.Conclusion. Multimodal imaging enables the selection of experimental animals with tumors of specific size and metabolic activity for the study of new radiopharmaceuticals, including those with vector delivery.

Investigation of lumbar multifidus muscle, pain, and fear of falling in patients with lumbar spinal stenosis with poor balance

BackgroundThis study aimed to compare the muscle thickness and cross-sectional area (CSA), pain, disability, and fear of falling in patients with lumbar spinal stenosis (LSS) with and without balance problems. MethodsSixty-four patients diagnosed with LSS by magnetic resonance imaging (MRI) were included in this cross-sectional study. The patients were divided into poor (n=31) and normal balance (n=33) groups according to the single leg standing test. Low back pain (Numeric rating scale), dynamic balance (Time up and go test), disability (Oswestry disability index) and fear of falling (International fall efficacy scale) in patients with LSS levels were evaluated. Lumbar (L4/5) multifidus muscle thickness and CSA were obtained from MRI images. ResultsThe poor balance group had a lower L4/5 multifidus thickness (p<0.05) and CSA (p<0.05) than the normal balance group. It was determined that an increase in left L4/5 multifidus muscle CSA was associated with decreased impaired balance (p=0.036). Also, a significant correlation was detected between static balance and muscle thickness and CSA (p<0.01). In addition, low back pain, disability, and fear of falling were significantly higher in LSS patients in the poor balance group (p<0.05). ConclusionMuscle atrophy and decrease in CSA are more common in LSS patients with poor balance. Decreased L4/5 multifidus muscle CSA may increase the risk of balance impairment. Also, LSS patients with poor balance are more likely to experience pain, disability, and fear of falling. Strategies to improve lumbar muscle stability, mass, and pain may reduce impaired balance in LSS.

HQNet: A hybrid quantum network for multi-class MRI brain classification via quantum computing

The complex and nonlinear nature of brain tumor morphology and texture pose significant challenges for representative feature extraction from magnetic resonance imaging (MRI) images, ultimately leading to inaccurate diagnoses of brain tumors. To tackle this problem, we propose a novel approach termed the hybrid quantum–classical convolutional network (HQNet) for detecting MRI brain tumors. Firstly, we use data augmentation techniques to deal with the issues of class imbalance and the sample scarcity within brain tumor MRI images. Secondly, we integrate channel attention and self-attention mechanisms to capture both channel and spatial dependencies from MRI images. This integration enables us to effectively fuse these dependencies and mitigate the discrepancies between them. However, the varying dependence of brain tumors at different scales can result in a decline in classification performance. To address this issue, we extract brain tumor features at various scales and combine them to alleviate this effect. Thirdly, a new parameterized quantum circuit is designed based on the principles of quantum computing to maximize the potential advantages of quantum computing and improve feature extraction. Finally, we compress the features and pass them through the fully connected layer to generate the final classification result. The effectiveness of our model is demonstrated through its superior performance when evaluated using three benchmark datasets.

Application of deep learning reconstruction in abdominal magnetic resonance cholangiopancreatography for image quality improvement and acquisition time reduction

PurposeTo compare deep learning (DL)-based and conventional reconstruction through subjective and objective analysis and ascertain whether DL-based reconstruction improves the quality and acquisition speed of clinical abdominal magnetic resonance imaging (MRI). MethodsThe 124 patients who underwent abdominal MRI between January and July 2021 were retrospectively studied. For each patient, two-dimensional axial T2-weighted single-shot fast spin-echo MRI images with or without fat saturation were reconstructed using DL-based and conventional methods. The subjective image quality scores and objective metrics, including signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) of the images were analysed. An explorative analysis was performed to compare 20 patients’ MRI images with site routine settings, high-resolution settings and high-speed settings. Paired t tests and Wilcoxon signed-rank tests were used for subjective and objective comparisons. ResultsA total of 144 patients were evaluated (mean age, 62.2 ± 14.1 years; 83 men). The MRI images reconstructed using DL-based methods had higher SNRs and CNRs than did those reconstructed using conventional methods (all p < 0.01). The subjective scores of the images reconstructed using DL-based methods were higher than those of the images reconstructed using conventional methods (p < 0.01), with significantly lower variation (p < 0.01). Exploratory analysis revealed that the DL-based reconstructions with thin slice thickness and higher temporal resolution had the highest image quality and were associated with the shortest scan times. ConclusionsDL-based reconstruction methods can be used to improve the quality with higher stability and accelerate the acquisition of abdominal MRI.

Robust brain MRI image classification with SIBOW-SVM

Primary Central Nervous System tumors in the brain are among the most aggressive diseases affecting humans. Early detection and classification of brain tumor types, whether benign or malignant, glial or non-glial, is critical for cancer prevention and treatment, ultimately improving human life expectancy. Magnetic Resonance Imaging (MRI) is the most effective technique for brain tumor detection, generating comprehensive brain scans. However, human examination can be error-prone and inefficient due to the complexity, size, and location variability of brain tumors. Recently, automated classification techniques using machine learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated significantly higher accuracy than manual screening. However, deep learning-based image classification methods, including CNNs, face challenges in estimating class probabilities without proper model calibration (Guo et al., 2017; Minderer et al., 2021). In this paper, we propose a novel brain tumor image classification method called SIBOW-SVM, which integrates the Bag-of-Features model with SIFT feature extraction and weighted Support Vector Machines. This new approach can effectively extract hidden image features, enabling differentiation of various tumor types, provide accurate label predictions, and estimate probabilities of images belonging to each class, offering high-confidence classification decisions. We have also developed scalable and parallelable algorithms to facilitate the practical implementation of SIBOW-SVM for massive image datasets. To benchmark our method, we apply SIBOW-SVM to a public dataset of brain tumor MRI images containing four classes: glioma, meningioma, pituitary, and normal. Our results demonstrate that the new method outperforms state-of-the-art techniques, including CNNs, in terms of uncertianty quantification, classification accuracy, computational efficiency, and data robustness.

Improving Osteoporosis Prediction Using Vertebral Bone Quality Score and Paravertebral Muscle Measurements From Lumbar MRI Scans.

Retrospective cohort. This study aims to use a novel method of combining vertebral bone quality score with paravertebral cross-sectional area measurements to improve the accuracy of predicting individuals with total hip T-scores <-2.5. Osteoporosis is a prevalent skeletal condition associated with decreased bone density and increased fracture risk. Dual-energy x-ray absorptiometry (DXA) is the conventional method for diagnosing osteoporosis, but it has limitations. Opportunistic osteoporosis screening techniques using lumbar magnetic resonance imaging (MRI), particularly the vertebral bone quality (VBQ) score, have shown promise. This study aims to improve the accuracy of predicting individuals with low total hip T-scores using a novel method that combines VBQ scores with paravertebral cross-sectional area (CSA) measurements. A retrospective cohort of 98 patients with DXA and lumbar MRI scans was analyzed. VBQ scores were calculated based on lumbar MRI images, and CSA measurements of paravertebral and psoas muscles were obtained. Threshold-based logistic regression was used to identify optimal thresholds for predicting total hip T-scores <-2.5. The combined model incorporating the VBQ score and paravertebral muscle percent achieved an accuracy of 96.9% for predicting total hip T-scores <-2.5, compared to 81.6% when using the VBQ score alone. Incorporating paravertebral muscle measurements significantly improved the accuracy of identifying osteoporotic individuals. The combination of VBQ score and paravertebral muscle measurements enhances the accuracy of predicting individuals with low total hip T-scores. Lumbar MRI scans provide valuable information beyond opportunistic osteoporosis screening, and the inclusion of paravertebral muscle measurements could aid in identifying at-risk individuals more accurately.

Mesoporous Polydopamine Nanotherapeutics for MRI-Guided Cancer Photothermal and Anti-Inflammatory Therapy.

As a burgeoning cancer treatment modality, photothermal therapy (PTT) has shown robust anti-tumor effects. However, it still faces numerous challenges, such as triggering an inflammatory response and potentially increasing the risk of cancer recurrence. To address these concerns, integration of PTT with anti-inflammatory therapies presents a promising approach to enhance the efficacy of cancer treatment and meanwhile reduce the risk of recurrence. In this study, Gd3+ was first chelated with dopamine to create Gd-DA chelates, and then the mesoporous dopamine nanoparticles MX@Arg-Gd-MPDA (MAGM NPs) were synthesized by combining arginine (Arg) and the anti-inflammatory medication meloxicam (MX). The photothermal properties of MAGM NPs were then defined and examined; the in vivo MRI imaging effect, as well as MAGM NPs' anti-cancer and anti-inflammatory efficiency, were tested in a mouse model of breast cancer. The incorporation of Arg doping into MAGM NPs was intended to boost its photothermal conversion efficiency and reactive oxygen species (ROS) scavenging ability. Additionally, synergizing with the anti-inflammatory agent meloxicam (MX) within the nanoparticles aimed to enhance the anti-inflammatory effect following photothermal therapy. Furthermore, gadolinium ions (Gd3+) were chelated into the nanostructure to enable precise T1-T2 dual-mode magnetic resonance imaging (MRI) of the intratumor accumulation profile. This imaging capability was leveraged to guide the implementation of photothermal therapy. Animal experiments demonstrated that MAGM NPs exerted a notable anticancer effect in a 4T1 breast cancer mouse model, under the precise guidance of MRI.

Magnetic Resonance Imaging of Anterior Cruciate Ligament Injury.

The Anterior Cruciate Ligament (ACL) is considered the most commonly injured ligament of the knee. Magnetic Resonance Imaging (MRI) has become an indispensable imaging tool and modality of choice for assessing and managing knee conditions. This article outlines an effective MRI imaging technique that improves the diagnostic accuracy of ACL injuries of the knee, covering the appropriate pulse sequences and optimal imaging planes. Furthermore, the article provides a comprehensive review of the appearance of complete and partial ACL tears on MRI in the acute and chronic phases. In addition, it identifies and illustrates the primary MRI signs (signs related to the absence or abnormal visualization of the ACL fibers) and secondary MRI signs (signs related to the mechanism of injury or associated knee injuries) of ACL injury.

Complex-valued image reconstruction for compressed sensing MRI using hierarchical constraint

In Magnetic Resonance Imaging (MRI), the sequential acquisition of raw complex-valued image data in Fourier space, also known as k-space, results in extended examination times. To speed up the MRI scans, k-space data are usually undersampled and processed using numerical techniques such as compressed sensing (CS). While the majority of CS-MRI algorithms primarily focus on magnitude images due to their significant diagnostic value, the phase components of complex-valued MRI images also hold substantial importance for clinical diagnosis, including neurodegenerative diseases. In this work, complex-valued MRI reconstruction is studied with a focus on the simultaneous reconstruction of both magnitude and phase images. The proposed algorithm is based on the nonsubsampled contourlet transform (NSCT) technique, which offers shift invariance in images. Instead of directly transforming the complex-valued image into the NSCT domain, we introduce a wavelet transform within the NSCT domain, reducing the size of the sparsity of coefficients. This two-level hierarchical constraint (HC) enforces sparse representation of complex-valued images for CS-MRI implementation. The proposed HC is seamlessly integrated into a proximal algorithm simultaneously. Additionally, to effectively minimize the artifacts caused by sub-sampling, thresholds related to different sub-bands in the HC are applied through an alternating optimization process. Experimental results show that the novel method outperforms existing CS-MRI techniques in phase-regularized complex-valued image reconstructions.