Multimodal Magnetic Resonance Imaging Research Articles

Analysis of the Value of Quantitative Features in Multimodal MRI Images to Construct a Radio-Omics Model for Breast Cancer Diagnosis.

To analyze the diagnostic value of quantitative features in multimodal magnetic resonance imaging (MRI) images to construct a radio-omics model for breast cancer. Ninety-five patients with breast-related diseases from January 2020 to January 2021 were grouped into the benign group (n=57) and malignant group (n=38) according to the pathological findings. All cases were randomized as the training group (n=66) and validation group (n=29) in a 7:3 ratio based on the examination time. All subjects were examined by T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), dynamic contrast enhancement (DCE), and apparent diffusion coefficient (ADC) multimodality MRI. The MRI findings were analyzed against pathological findings. A diagnostic breast cancer radiomics model was constructed. The diagnostic efficacy of the model in the validation group was analyzed, and the diagnostic efficacy was analyzed via the ROC curve. Fibroadenoma accounted for 49.12% of benign breast diseases, and invasive ductal carcinoma accounted for 73.68% of malignant breast diseases. The sensitivity of T1WI, T2WI, DWI, ADC, and DCE in diagnosing breast cancer was 61.14%, 66.67%, 73.30%, 78.95%, and 85.96%, using the four-fold table method. The area under the curves (AUCs) of T1WI, T2WI, DWI, ADC, and DCE for diagnosing breast cancer were 0.715, 0.769, 0.785, 0.835, and 0.792, respectively. The AUCs of plain scan, diffuse, enhanced, plain scan + diffuse, plain scan + enhanced, enhanced + diffuse, and plain scan + enhanced + diffuse for diagnosing breast cancer were 0.746, 0.798, 0.816, 0.839, 0.890, 0.906, and 0.927, respectively. The construction of a radio-omics model by quantitative features in multimodal MRI images was valuable in the diagnosis of breast cancer. The value of radio-omics models such as plain scan + enhanced + diffuse was higher than the other models in diagnosing breast cancer and could be widely applied in clinical practice.

Adversarial Learning Based Node-Edge Graph Attention Networks for Autism Spectrum Disorder Identification.

Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks based on magnetic resonance imaging (MRI) data. However, previous studies are largely node-centralized and ignore edge features for graph classification tasks, resulting in moderate performance of graph classification accuracy. Moreover, the generalizability of GNN model is still far from satisfactory in brain disorder [e.g., autism spectrum disorder (ASD)] identification due to considerable individual differences in symptoms among patients as well as data heterogeneity among different sites. In order to address the above limitations, this study proposes a novel adversarial learning-based node-edge graph attention network (AL-NEGAT) for ASD identification based on multimodal MRI data. First, both node and edge features are modeled based on structural and functional MRI data to leverage complementary brain information and preserved in the constructed weighted adjacent matrix for individuals through the attention mechanism in the proposed NEGAT. Second, two AL methods are employed to improve the generalizability of NEGAT. Finally, a gradient-based saliency map strategy is utilized for model interpretation to identify important brain regions and connections contributing to the classification. Experimental results based on the public Autism Brain Imaging Data Exchange I (ABIDE I) data demonstrate that the proposed framework achieves a classification accuracy of 74.7% between ASD and typical developing (TD) groups based on 1007 subjects across 17 different sites and outperforms the state-of-the-art methods, indicating satisfying classification ability and generalizability of the proposed AL-NEGAT model. Our work provides a powerful tool for brain disorder identification.

Preoperative Grading of Brain Gliomas Using 3D-ResNet18 Based on Multimodal MRI and Attention Mechanism

In response to the prevalent challenge of imprecise preoperative glioma grading prediction, a multimodal Magnetic Resonance Imaging (MRI) image with attention mechanism prediction model based on Residual Network (ResNet) is proposed for accurate prediction. To achieve this, publicly accessible datasets from BraTS 2019 and BraTS 2020 were employed. MRI images across three modalities underwent preprocessing, cropping, and subsequent stacking to generate comprehensive multimodal representations. Meanwhile, An Efficient Channel Attention (ECA) mechanism based on 3D data (3D-ECA) is proposed and introduced to reduce the problem of slow network convergence and overfitting. Notably, experiments demonstrate that the 3D-ECA attention mechanism added to the model improves the network training speed and the classification accuracy of the model, and the classification accuracy reached 88.1%, with an impressive area under the subject working characteristic curve of 0.918. Therefore, the 3D-ResNet18 deep learning model, incorporating multimodal MRI and 3D-ECA attention mechanisms, demonstrates high accuracy and robustness in distinguishing between high-grade and low-grade gliomas. Thus, showcasing significant clinical potential for glioma classification and diagnosis.

Iron deposition in subcortical nuclei of Parkinson's disease: A meta-analysis of quantitative iron-sensitive magnetic resonance imaging studies.

Iron deposition plays a crucial role in the pathophysiology of Parkinson's disease (PD), yet the distribution pattern of iron deposition in the subcortical nuclei has been inconsistent across previous studies. We aimed to assess the difference patterns of iron deposition detected by quantitative iron-sensitive magnetic resonance imaging (MRI) between patients with PD and patients with atypical parkinsonian syndromes (APSs), and between patients with PD and healthy controls (HCs). A systematic literature search was conducted on PubMed, Embase, and Web of Science databases to identify studies investigating the iron content in PD patients using the iron-sensitive MRI techniques (R2* and quantitative susceptibility mapping [QSM]), up until May 1, 2023. The quality assessment of case-control and cohort studies was performed using the Newcastle-Ottawa Scale, whereas diagnostic studies were assessed using the Quality Assessment of Diagnostic Accuracy Studies-2. Standardized mean differences and summary estimates of sensitivity, specificity, and area under the curve (AUC) were calculated for iron content, using a random effects model. We also conducted the subgroup-analysis based on the MRI sequence and meta-regression. Seventy-seven studies with 3192 PD, 209 multiple system atrophy (MSA), 174 progressive supranuclear palsy (PSP), and 2447 HCs were included. Elevated iron content in substantia nigra (SN) pars reticulata (P <0.001) and compacta (P <0.001), SN (P <0.001), red nucleus (RN, P <0.001), globus pallidus (P <0.001), putamen (PUT, P=0.009), and thalamus (P=0.046) were found in PD patients compared with HCs. PD patients showed lower iron content in PUT (P <0.001), RN (P=0.003), SN (P=0.017), and caudate nucleus (P=0.027) than MSA patients, and lower iron content in RN (P=0.001), PUT (P <0.001), globus pallidus (P=0.004), SN (P=0.015), and caudate nucleus (P=0.001) than PSP patients. The highest diagnostic accuracy distinguishing PD from HCs was observed in SN (AUC: 0.85), and that distinguishing PD from MSA was found in PUT (AUC: 0.90). In addition, the best diagnostic performance was achieved in the RN for distinguishing PD from PSP (AUC: 0.84). Quantitative iron-sensitive MRI could quantitatively detect the iron content of subcortical nuclei in PD and APSs, while it may be insufficient to accurately diagnose PD. Future studies are needed to explore the role of multimodal MRI in the diagnosis of PD. PROSPERO; CRD42022344413.

Amygdala structural and functional reorganization as an indicator of affective dysfunction in patients with tinnitus.

The aim of this study was to systematically investigate structural and functional alterations in amygdala subregions using multimodal magnetic resonance imaging (MRI) in patients with tinnitus with or without affective dysfunction. Sixty patients with persistent tinnitus and 40 healthy controls (HCs) were recruited. Based on a questionnaire assessment, 26 and 34 patients were categorized into the tinnitus patients with affective dysfunction (TPAD) and tinnitus patients without affective dysfunction (TPWAD) groups, respectively. MRI-based measurements of gray matter volume, fractional anisotropy (FA), fractional amplitude of low-frequency fluctuations (fALFF), regional homogeneity (ReHo), degree centrality (DC), and functional connectivity (FC) were conducted within 14 amygdala subregions for intergroup comparisons. Associations between the MRI properties and clinical characteristics were estimated via partial correlation analyses. Compared with that of the HCs, the TPAD and TPWAD groups exhibited significant structural and functional changes, including white matter integrity (WMI), fALFF, ReHo, DC, and FC alterations, with more pronounced WMI changes in the TPAD group, predominantly within the left auxiliary basal or basomedial nucleus (AB/BM), right central nucleus, right lateral nuclei (dorsal portion), and left lateral nuclei (ventral portion containing basolateral portions). Moreover, the TPAD group exhibited decreased FC between the left AB/BM and left middle occipital gyrus and right superior frontal gyrus (SFG), left basal nucleus and right SFG, and right lateral nuclei (intermediate portion) and right SFG. In combination, these amygdalar alterations exhibited a sensitivity of 65.4% and specificity of 96.9% in predicting affective dysfunction in patients with tinnitus. Although similar structural and functional amygdala remodeling were observed in the TPAD and TPWAD groups, the changes were more pronounced in the TPAD group. These changes mainly involved alterations in functionality and white matter microstructure in various amygdala subregions; in combination, these changes could serve as an imaging-based predictor of emotional disorders in patients with tinnitus.

A brain subcortical segmentation tool based on anatomy attentional fusion network for developing macaques

Magnetic Resonance Imaging (MRI) plays a pivotal role in the accurate measurement of brain subcortical structures in macaques, which is crucial for unraveling the complexities of brain structure and function, thereby enhancing our understanding of neurodegenerative diseases and brain development. However, due to significant differences in brain size, structure, and imaging characteristics between humans and macaques, computational tools developed for human neuroimaging studies often encounter obstacles when applied to macaques. In this context, we propose an Anatomy Attentional Fusion Network (AAF-Net), which integrates multimodal MRI data with anatomical constraints in a multi-scale framework to address the challenges posed by the dynamic development, regional heterogeneity, and age-related size variations of the juvenile macaque brain, thus achieving precise subcortical segmentation. Specifically, we generate a Signed Distance Map (SDM) based on the initial rough segmentation of the subcortical region by a network as an anatomical constraint, providing comprehensive information on positions, structures, and morphology. Then we construct AAF-Net to fully fuse the SDM anatomical constraints and multimodal images for refined segmentation. To thoroughly evaluate the performance of our proposed tool, over 700 macaque MRIs from 19 datasets were used in this study. Specifically, we employed two manually labeled longitudinal macaque datasets to develop the tool and complete four-fold cross-validations. Furthermore, we incorporated various external datasets to demonstrate the proposed tool’s generalization capabilities and promise in brain development research. We have made this tool available as an open-source resource at https://github.com/TaoZhong11/Macaque_subcortical_segmentation for direct application.

#2484 Diffusion magnetic resonance imaging, a noninvasive tool to assess fibrosis level in both native and allograft kidneys

Abstract Background and Aims Renal cortical interstitial fibrosis is a well-established prognostic indicator for renal health, conventionally estimated by biopsy. Our prior research has enhanced DW-MRI sequencing, facilitating precise distinction between the renal cortex and medulla. This has enabled the measurement of the cortico-medullary apparent diffusion coefficient difference (ΔADC), which inversely correlates with the extent of histologically assessed interstitial fibrosis. The present study is designed to validate these findings, assess their reproducibility in a separate institution, and ascertain their significance in delineated subgroups, particularly between allograft recipients and native kidney patients. Method From 2014 to 2023, we orchestrated a prospective cohort study encompassing 309 patients diagnosed with chronic kidney disease (n = 106) or those with a renal allograft (n = 203). Each patient had undergone a biopsy, subsequent to which a multimodal magnetic resonance imaging (MRI) was systematically conducted in the following weeks. Initially, participants were recruited from Geneva hospitals, with subsequent inclusion of patients from Lausanne in Switzerland. The study's objective was to evaluate the correlation between ΔADC and the degree of renal fibrosis at biopsy. We performed subgroup analyses (per center, native/allograft kidneys) and applied linear regression models to investigate these associations rigorously. Results We included 270 participants in Geneva and 39 patients in Lausanne. A significant negative correlation was observed between ΔADC and the degree of fibrosis across the entire cohort (R = −0.41, p &amp;lt; 0.001). Subgroup analyses yielded consistent findings in both Geneva (R = −0.43, p &amp;lt; 0.001) and Lausanne University Hospitals (R = −0.35, p &amp;lt; 0.001). Furthermore, this association remained significant within subgroups of both native and allograft kidneys (respectively: R = −0.48, p &amp;lt; 0.001 and R = −0.38, p &amp;lt; 0.001). Conclusion Our findings reinforce the link between ΔADC and renal fibrosis, indicating that this association is consistent regardless of the center or kidney type (native or allograft). This supports the potential utility of diffusion MRI as a non-invasive tool for the assessment of renal fibrosis.

Deep learning ensembles for detecting brain metastases in longitudinal multi-modal MRI studies

Metastatic brain cancer is a condition characterized by the migration of cancer cells to the brain from extracranial sites. Notably, metastatic brain tumors surpass primary brain tumors in prevalence by a significant factor, they exhibit an aggressive growth potential and have the capacity to spread across diverse cerebral locations simultaneously. Magnetic resonance imaging (MRI) scans of individuals afflicted with metastatic brain tumors unveil a wide spectrum of characteristics. These lesions vary in size and quantity, spanning from tiny nodules to substantial masses captured within MRI. Patients may present with a limited number of lesions or an extensive burden of hundreds of them. Moreover, longitudinal studies may depict surgical resection cavities, as well as areas of necrosis or edema. Thus, the manual analysis of such MRI scans is difficult, user-dependent and cost-inefficient, and – importantly – it lacks reproducibility. We address these challenges and propose a pipeline for detecting and analyzing brain metastases in longitudinal studies, which benefits from an ensemble of various deep learning architectures originally designed for different downstream tasks (detection and segmentation). The experiments, performed over 275 multi-modal MRI scans of 87 patients acquired in 53 sites, coupled with rigorously validated manual annotations, revealed that our pipeline, built upon open-source tools to ensure its reproducibility, offers high-quality detection, and allows for precisely tracking the disease progression. To objectively quantify the generalizability of models, we introduce a new data stratification approach that accommodates the heterogeneity of the dataset and is used to elaborate training-test splits in a data-robust manner, alongside a new set of quality metrics to objectively assess algorithms. Our system provides a fully automatic and quantitative approach that may support physicians in a laborious process of disease progression tracking and evaluation of treatment efficacy.

Exploring Schizophrenia Classification Through Multimodal MRI and Deep Graph Neural Networks: Unveiling Brain Region-Specific Weight Discrepancies and Their Association With Cell-Type Specific Transcriptomic Features.

Schizophrenia (SZ) is a prevalent mental disorder that imposes significant health burdens. Diagnostic accuracy remains challenging due to clinical subjectivity. To address this issue, we explore magnetic resonance imaging (MRI) as a tool to enhance SZ diagnosis and provide objective references and biomarkers. Using deep learning with graph convolution, we represent MRI data as graphs, aligning with brain structure, and improving feature extraction, and classification. Integration of multiple modalities is expected to enhance classification. Our study enrolled 683 SZ patients and 606 healthy controls from 7 hospitals, collecting structural MRI and functional MRI data. Both data types were represented as graphs, processed by 2 graph attention networks, and fused for classification. Grad-CAM with graph convolution ensured interpretability, and partial least squares analyzed gene expression in brain regions. Our method excelled in the classification task, achieving 83.32% accuracy, 83.41% sensitivity, and 83.20% specificity in 10-fold cross-validation, surpassing traditional methods. And our multimodal approach outperformed unimodal methods. Grad-CAM identified potential brain biomarkers consistent with gene analysis and prior research. Our study demonstrates the effectiveness of deep learning with graph attention networks, surpassing previous SZ diagnostic methods. Multimodal MRI's superiority over unimodal MRI confirms our initial hypothesis. Identifying potential brain biomarkers alongside gene biomarkers holds promise for advancing objective SZ diagnosis and research in SZ.

Misalignment-Resistant Deep Unfolding Network for multi-modal MRI super-resolution and reconstruction

Multi-modal Magnetic Resonance Imaging (MRI) super-resolution (SR) and reconstruction aims to obtain a high-quality target image from corresponding sparsely sampled signals under the guidance of a reference image. However, existing techniques typically assume that the input multi-modal MR images are well aligned, which is challenging to achieve in clinical practice. This naive assumption has made their algorithms vulnerable to misalignment scenarios. Moreover, they often neglect many non-local common characteristics within and between modalities. In this work, we proposed a MisAlignment-Resistant Deep Unfolding Network (MAR-DUN) embedded in the tailored gradient descent module (GDM) and proximal mapping module (PMM) for multi-modal MRI SR and reconstruction. In the GDM, we employ an adaptive step-size sub-network (ASS-Net) to enhance the texture representation capacity of the proposed MAR-DUN. Furthermore, in the PMM, we propose a cross-modality non-local module (CNLM) featuring the inverse deformation layer (IDL). The IDL aligns features between the target and reference images by adaptively learning their spatial transformations, thus enhancing the robustness of the proposed network and allowing the CNLM to further explore the cross-modality non-local characteristics. On the other hand, the proposed CNLM aims to establish both the intra-modality and inter-modality non-local dependencies for fully exploiting the correlations between the target and reference images. Extensive experimental results show that our proposed method consistently achieves state-of-the-art reconstruction performance in alignment and misalignment scenarios, demonstrating its significant promise for real-world applications.

Multi-teacher cross-modal distillation with cooperative deep supervision fusion learning for unimodal segmentation

Accurate brain tumor segmentation is a labor-intensive and time-consuming task that requires automation to enhance its efficacy. Recent advanced techniques have shown promising results in segmenting brain tumors; however, their dependency on extensive multimodal magnetic resonance imaging (MRI) data limits their practicality in clinical environments where such data may not be readily available. To address this, we propose a novel multi-teacher cross-modal knowledge distillation framework, which utilizes the privileged multimodal data during training while relying solely on unimodal data for inference. Our framework is tailored to the unimodal segmentation of the T1ce MRI sequence, which is prevalently available in clinical practice and structurally akin to the T1 modality, providing ample information for the segmentation task. Our framework introduces two learning strategies for knowledge distillation (KD): (1) performance-aware response-based KD and (2) cooperative deep supervision fusion learning (CDSFL). The first strategy involves dynamically assigning confidence weights to each teacher model based on its performance, ensuring that the KD is performance-driven, and the CDSFL module augments the learning capabilities of the multi-teacher models by fostering mutual learning. Moreover, the fused information is distilled into the student model to improve its deep supervision. Extensive experiments on BraTS datasets demonstrate that our framework achieves promising unimodal segmentation results on the T1ce and T1 modalities and outperforms previous state-of-the-art methods. Code is available at https://github.com/ami-lab-knut/mtcm_kd.

Multimodal MRI reveals brainstem connections that sustain wakefulness in human consciousness.

Consciousness is composed of arousal (i.e., wakefulness) and awareness. Substantial progress has been made in mapping the cortical networks that underlie awareness in the human brain, but knowledge about the subcortical networks that sustain arousal in humans is incomplete. Here, we aimed to map the connectivity of a proposed subcortical arousal network that sustains wakefulness in the human brain, analogous to the cortical default mode network (DMN) that has been shown to contribute to awareness. We integrated data from ex vivo diffusion magnetic resonance imaging (MRI) of three human brains, obtained at autopsy from neurologically normal individuals, with immunohistochemical staining of subcortical brain sections. We identified nodes of the proposed default ascending arousal network (dAAN) in the brainstem, hypothalamus, thalamus, and basal forebrain. Deterministic and probabilistic tractography analyses of the ex vivo diffusion MRI data revealed projection, association, and commissural pathways linking dAAN nodes with one another and with DMN nodes. Complementary analyses of in vivo 7-tesla resting-state functional MRI data from the Human Connectome Project identified the dopaminergic ventral tegmental area in the midbrain as a widely connected hub node at the nexus of the subcortical arousal and cortical awareness networks. Our network-based autopsy methods and connectivity data provide a putative neuroanatomic architecture for the integration of arousal and awareness in human consciousness.

Multi-modal Magnetic Resonance Imaging to Assess Cerebrovascular Function in Atrial Fibrillation Patients

Atrial fibrillation (AF) is associated with an increased risk of cognitive decline, dementia, and stroke. Low cerebral blood flow (CBF) and low cerebrovascular carbon dioxide reactivity (CVRCO2) are associated with poor brain health outcomes. In the current study we employed magnetic resonance imaging (MRI) to quantify resting CBF and CVRCO2 in patients with AF and age-matched normal sinus rhythm (NSR) controls. We hypothesised that both resting CBF and CVRCO2 would be lower in patients with AF. Patients with AF (n=11, 65±14 years, 2 women) and NSR (n=12, 63±9 years, 7 women) underwent arterial spin labelling (ASL) at rest, and blood oxygen level-dependent (BOLD) MRI during a single-step increase in partial pressure of carbon dioxide (measured by end-tidal carbon dioxide (PETCO2)) induced by changing the fraction of inspired CO2 to 5% (21% O2, balance N2). Region of interest time courses were extracted with grey matter, middle cerebral artery, and posterior cerebral artery territory masks. CVRCO2 was defined as the percentage change (%Δ) in BOLD signal vs %Δ in PETCO2. Baseline CBF was not different between NSR and AF in grey matter (62±17 vs. 58±10 ml/min/100g, respectively; p=0.226), middle cerebral artery (59±16 vs. 56±14 ml/min/100g; p=0.361) and posterior cerebral artery (61±17 vs 53±15 ml/min/100g; p=0.138) territories. BOLD-derived CVRC02 was not different between NSR and AF groups in grey matter (0.11±0.04 vs. 0.12±0.03 %ΔBOLD/%ΔmmHg, respectively; p=0.372), middle cerebral artery (0.09±0.04 vs. 0.10±0.03 %ΔBOLD/%ΔmmHg; p=0.405) and posterior cerebral artery (0.13±0.04 vs. 0.14±0.05 %ΔBOLD/%ΔmmHg; p=0.367) territories. Collectively, these pilot data suggest that MRI-derived cerebrovascular CO2 responsiveness is not different in patients with AF and age-matched NSR controls that have similar resting CBF. Further investigations are required to extend these preliminary findings to a larger cohort to fully elucidate the effects of AF on cerebrovascular function. Support provided by the Royal Society of New Zealand Te Apārangi Marsden Fund (19-UOA-170). This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Investigating Sea-Level Brain Predictors for Acute Mountain Sickness: A Multimodal MRI Study before and after High-Altitude Exposure.

Acute mountain sickness is a series of brain-centered symptoms that occur when rapidly ascending to high altitude. Predicting acute mountain sickness before high-altitude exposure is crucial for protecting susceptible individuals. The present study aimed to evaluate the feasibility of predicting acute mountain sickness after high-altitude exposure by using multimodal brain MR imaging features measured at sea level. We recruited 45 healthy sea-level residents who flew to the Qinghai-Tibet Plateau (3650 m). We conducted T1-weighted structural MR imaging, resting-state fMRI, and arterial spin-labeling perfusion MR imaging both at sea level and high altitude. Acute mountain sickness was diagnosed for 5 days using Lake Louise Scoring. Logistic regression with Least Absolute Shrinkage and Selection Operator logistic regression was performed for predicting acute mountain sickness using sea-level MR imaging features. We also validated the predictors by using MR images obtained at high altitude. The incidence rate of acute mountain sickness was 80.0%. The model achieved an area under the receiver operating characteristic curve of 86.4% (sensitivity = 77.8%, specificity = 100.0%, and P < .001) in predicting acute mountain sickness At sea level, valid predictors included fractional amplitude of low-frequency fluctuations (fALFF) and degree centrality from resting-state fMRI, mainly distributed in the somatomotor network. We further learned that the acute mountain sickness group had lower levels of fALFF in the somatomotor network at high altitude, associated with smaller changes in CSF volume and higher Lake Louise Scoring, specifically relating to fatigue and clinical function. Our study found that the somatomotor network function detected by sea-level resting-state fMRI was a crucial predictor for acute mountain sickness and further validated its pathophysiologic impact at high altitude. These findings show promise for pre-exposure prediction, particularly for individuals in need of rapid ascent, and they offer insight into the potential mechanism of acute mountain sickness.

Enhancing Robust Liver Cancer Diagnosis: A Contrastive Multi-Modality Learner with Lightweight Fusion and Effective Data Augmentation

This article explores the application of self-supervised contrastive learning in the medical domain, focusing on classification of multi-modality Magnetic Resonance (MR) images. To address the challenges of limited and hard-to-annotate medical data, we introduce multi-modality data augmentation (MDA) and cross-modality group convolution (CGC). In the pre-training phase, we leverage Simple Siamese networks to maximize the similarity between two augmented MR images from a patient, without a handcrafted pretext task. Our approach also combines 3D and 2D group convolution with a channel shuffle operation to efficiently incorporate different modalities of image features. Evaluation on liver MR images from a well-known hospital in Taiwan demonstrates a significant improvement over previous methods. This work contributes to advancing multi-modality contrastive learning, particularly in the context of medical imaging, offering enhanced tools for analyzing complex image data.

Glioma segmentation based on dense contrastive learning and multimodal features recalibration

Accurate segmentation of different regions of gliomas from multimodal magnetic resonance (MR) images is crucial for glioma grading and precise diagnosis, but many existing segmentation methods are difficult to effectively utilize multimodal MR image information to recognize accurately the lesion regions with small size, low contrast and irregular shape. To address this issue, this work proposes a novel 3D glioma segmentation model DCL-MANet. DCL-MANet has an architecture of multiple encoders and one single decoder. Each encoder is used to extract MR image features of a given modality. To overcome the entangle problems of multimodal semantic features, a dense contrastive learning (DCL) strategy is presented to extract the modality-specific and common features. Following that, feature recalibration block (RFB) based on modality-wise attention is used to recalibrate the semantic features of each modality, enabling the model to focus on the features that are beneficial for glioma segmentation. These recalibrated features are input into the decoder to obtain the segmentation results. To verify the superiority of the proposed method, we compare it with several state-of-the-art (SOTA) methods in terms of Dice, average symmetric surface distance (ASSD), HD95 and volumetric similarity (Vs). The comparison results show that the average Dice, ASSD, HD95 and Vs of DCL-MANet on all tumor regions are improved at least by 0.66%, 3.47%, 8.94% and 1.07% respectively. For small enhance tumor (ET) region, the corresponding improvement can be up to 0.37%, 7.83%, 11.32%, and 1.35%, respectively. In addition, the ablation results demonstrate the effectiveness of the proposed DCL and RFB, and combining them can significantly increase Dice (1.59%) and Vs (1.54%) while decreasing ASSD (40.51%) and HD95 (45.16%) on ET region. The proposed DCL-MANet could disentangle multimodal features and enhance the semantics of modality-dependent features, providing a potential means to accurately segment small lesion regions in gliomas.

The Mexican dataset of a repetitive transcranial magnetic stimulation clinical trial on cocaine use disorder patients: SUDMEX TMS

Cocaine use disorder (CUD) is a global health problem with severe consequences, leading to behavioral, cognitive, and neurobiological disturbances. While consensus on treatments is still ongoing, repetitive transcranial magnetic stimulation (rTMS) has emerged as a promising approach for medication-resistant disorders, including substance use disorders. In this context, here we present the SUDMEX-TMS, a Mexican dataset from an rTMS clinical trial involving CUD patients. This longitudinal dataset comprises 54 CUD patients (including 8 females) with data collected at five time points: baseline (T0), two weeks (T1), three months (T2), six months (T3) follow-up, and twelve months (T4) follow-up. The clinical rTMS treatment followed a double-blinded randomized clinical trial design (n = 24 sham/30 active) for 2 weeks, followed by an open-label phase. The dataset includes demographic, clinical, and cognitive measures, as well as magnetic resonance imaging (MRI) data collected at all time points, encompassing structural (T1-weighted), functional (resting-state fMRI), and multishell diffusion-weighted (DWI-HARDI) sequences. This dataset offers the opportunity to investigate the impact of rTMS on CUD participants, considering clinical, cognitive, and multimodal MRI metrics in a longitudinal framework.

Association between Resting Heart Rate and Machine Learning-Based Brain Age in Middle- and Older-Age

BackgroundResting heart rate (RHR), has been related to increased risk of dementia, but the relationship between RHR and brain age is unclear.ObjectiveWe aimed to investigate the association of RHR with brain age and brain age gap (BAG, the difference between predicted brain age and chronological age) assessed by multimodal Magnetic Resonance Imaging (MRI) in mid- and old-aged adults.DesignA longitudinal study from the UK Biobank neuroimaging project where participants underwent brain MRI scans 9+ years after baseline.SettingA population-based study.ParticipantsA total of 33,381 individuals (mean age 54.74 ± 7.49 years; 53.44% female).MeasurementsBaseline RHR was assessed by blood pressure monitor and categorized as <60, 60–69 (reference), 70–79, or ≥80 beats per minute (bpm). Brain age was predicted using LASSO through 1,079 phenotypes in six MRI modalities (including T1-weighted MRI, T2-FLAIR, T2*, diffusion-MRI, task fMRI, and resting-state fMRI). Data were analyzed using linear regression models.ResultsAs a continuous variable, higher RHR was associated with older brain age (β for per 1-SD increase: 0.331, 95% [95% confidence interval, CI]: 0.265, 0.398) and larger BAG (β: 0.263, 95% CI: 0.202, 0.324). As a categorical variable, RHR 70–79 bpm and RHR ≥80 bpm were associated with older brain age (β [95% CI]: 0.361 [0.196, 0.526] / 0.737 [0.517, 0.957]) and larger BAG (0.256 [0.105, 0.407] / 0.638 [0.436, 0.839]), but RHR< 60 bpm with younger brain age (−0.324 [−0.500, −0.147]) and smaller BAG (−0.230 [−0.392, −0.067]), compared to the reference group. These associations between elevated RHR and brain age were similar in both middle-aged (<60) and older (≥60) adults, whereas the association of RHR< 60 bpm with younger brain age and larger BAG was only significant among middle-aged adults. In stratification analysis, the association between RHR ≥80 bpm and older brain age was present in people with and without CVDs, while the relation of RHR 70–79 bpm to brain age present only in people with CVD.ConclusionHigher RHR (>80 bpm) is associated with older brain age, even among middle-aged adults, but RHR< 60 bpm is associated with younger brain age. Greater RHR could be an indicator for accelerated brain aging.

Evaluating the relationship between magnetic resonance image quality metrics and deep learning-based segmentation accuracy of brain tumors.

Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment-based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal-to-noise, contrast-to-noise) and segmentation accuracy. Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL-based brain tumor segmentation accuracy toward developing more generalizable models for multi-institutional data. We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non-ET on MRI; with performance quantified via a 5-fold cross-validated Dice coefficient. MRI scans were evaluated through the open-source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as "better" quality (BQ) or "worse" quality (WQ), via relative thresholding. Segmentation performance was re-evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts. For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal-to-noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models. Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet-based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.

High-resolution 3T to 7T ADC map synthesis with a hybrid CNN-transformer model.

7 Tesla (7T) apparent diffusion coefficient (ADC) maps derived from diffusion-weighted imaging (DWI) demonstrate improved image quality and spatial resolution over 3 Tesla (3T) ADC maps. However, 7T magnetic resonance imaging (MRI) currently suffers from limited clinical unavailability, higher cost, and increased susceptibility to artifacts. To address these issues, we propose a hybrid CNN-transformer model to synthesize high-resolution 7T ADC maps from multimodal 3T MRI. The Vision CNN-Transformer (VCT), composed of both Vision Transformer (ViT) blocks and convolutional layers, is proposed to produce high-resolution synthetic 7T ADC maps from 3T ADC maps and 3T T1-weighted (T1w) MRI. ViT blocks enabled global image context while convolutional layers efficiently captured fine detail. The VCT model was validated on the publicly available Human Connectome Project Young Adult dataset, comprising 3T T1w, 3T DWI, and 7T DWI brain scans. The Diffusion Imaging in Python library was used to compute ADC maps from the DWI scans. A total of 171 patient cases were randomly divided into 130 training cases, 20 validation cases, and 21 test cases. The synthetic ADC maps were evaluated by comparing their similarity to the ground truth volumes with the following metrics: peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and mean squared error (MSE). In addition, RESULTS: The results are as follows: PSNR: 27.0±0.9dB, SSIM: 0.945±0.010, and MSE: 2.0E-3±0.4E-3. Both qualitative and quantitative results demonstrate that VCT performs favorably against other state-of-the-art methods. We have introduced various efficiency improvements, including the implementation of flash attention and training on 176×208 resolution images. These enhancements have resulted in the reduction of parameters and training time per epoch by 50% in comparison to ResViT. Specifically, the training time per epoch has been shortened from 7.67 min to 3.86 min. We propose a novel method to predict high-resolution 7T ADC maps from low-resolution 3T ADC maps and T1w MRI. Our predicted images demonstrate better spatial resolution and contrast compared to 3T MRI and prediction results made by ResViT and pix2pix. These high-quality synthetic 7T MR images could be beneficial for disease diagnosis and intervention, producing higher resolution and conformal contours, and as an intermediate step in generating synthetic CT for radiation therapy, especially when 7T MRI scanners are unavailable.