Search

Abstract Best current practice in the analysis of dynamic contrast enhanced (DCE)-MRI is to employ a voxel-by-voxel model selection from a hierarchy of nested models. This nested model selection (NMS) assumes that the observed time-trace of contrast-agent (CA) concentration within a voxel, corresponds to a singular physiologically nested model. However, admixtures of different models may exist within a voxel’s CA time-trace. This study introduces an unsupervised feature engineering technique (Kohonen-Self-Organizing-Map (K-SOM)) to estimate the voxel-wise probability of each nested model. Sixty-six immune-compromised-RNU rats were implanted with human U-251 N cancer cells, and DCE-MRI data were acquired from all the rat brains. The time-trace of change in the longitudinal-relaxivity (ΔR1) for all animals’ brain voxels was calculated. DCE-MRI pharmacokinetic (PK) analysis was performed using NMS to estimate three model regions: Model-1: normal vasculature without leakage, Model-2: tumor tissues with leakage without back-flux to the vasculature, Model-3: tumor vessels with leakage and back-flux. Approximately two hundred thirty thousand (229,314) normalized ΔR1 profiles of animals’ brain voxels along with their NMS results were used to build a K-SOM (topology-size: 8 × 8, with competitive-learning algorithm) and probability map of each model. K-fold nested-cross-validation (NCV, k = 10) was used to evaluate the performance of the K-SOM probabilistic-NMS (PNMS) technique against the NMS technique. The K-SOM PNMS’s estimation for the leaky tumor regions were strongly similar (Dice-Similarity-Coefficient, DSC = 0.774 [CI: 0.731–0.823], and 0.866 [CI: 0.828–0.912] for Models 2 and 3, respectively) to their respective NMS regions. The mean-percent-differences (MPDs, NCV, k = 10) for the estimated permeability parameters by the two techniques were: -28%, + 18%, and + 24%, for vp, Ktrans, and ve, respectively. The KSOM-PNMS technique produced microvasculature parameters and NMS regions less impacted by the arterial-input-function dispersion effect. This study introduces an unsupervised model-averaging technique (K-SOM) to estimate the contribution of different nested-models in PK analysis and provides a faster estimate of permeability parameters.

Abstract Neuroimaging has greatly improved our understanding of phobic mechanisms. To expand on these advancements, we present data on the heterogeneity of neural patterns in spider phobia combined with various psychological dimensions of spider phobia, using spider-relevant stimuli of various intensities. Specifically, we have created a database in which 49 spider-fearful individuals viewed 225 spider-relevant images in the fMRI scanner and performed behavioral avoidance tasks before and after the fMRI scan. For each participant, the database consists of the neuroimaging part, which includes an anatomical scan, five passive-viewing, and two resting-state functional runs in both raw and pre-processed form along with associated quality control reports. Additionally, the behavioral section includes self-report questionnaires and avoidance tasks collected in pre- and post-sessions. The dataset is well suited for investigating neural mechanisms of phobias, brain-behavior correlations, and also contributes to the existing phobic neuroimaging datasets with spider-fearful samples.

IntroductionGlioma segmentation is vital for diagnostic decision-making, monitoring disease progression, and surgical planning. However, this task is hindered by substantial heterogeneity within gliomas and imbalanced region distributions, posing challenges to existing segmentation methods.MethodsTo address these challenges, we propose the DeepGlioSeg network, a U-shaped architecture with skip connections for continuous contextual feature integration. The model includes two primary components. First, a CTPC (CNN-Transformer Parallel Combination) module leverages parallel branches of CNN and Transformer networks to fuse local and global features of glioma images, enhancing feature representation. Second, the model computes a region-based probability by comparing the number of pixels in tumor and background regions and assigns greater weight to regions with lower probabilities, thereby focusing on the tumor segment. Test-time augmentation (TTA) and volume-constrained (VC) post-processing are subsequently applied to refine the final segmentation outputs.ResultsExtensive experiments were conducted on three publicly available glioma MRI datasets and one privately owned clinical dataset. The quantitative and qualitative findings consistently show that DeepGlioSeg achieves superior segmentation performance over other state-of-the-art methods.DiscussionBy integrating CNN- and Transformer-based features in parallel and adaptively emphasizing underrepresented tumor regions, DeepGlioSeg effectively addresses the challenges associated with glioma heterogeneity and imbalanced region distributions. The final pipeline, augmented with TTA and VC post-processing, demonstrates robust segmentation capabilities. The source code for this work is publicly available at https://github.com/smallboy-code/Brain-tumor-segmentation.

Background: Deep learning-based segmentation of brain metastases relies on large amounts of fully annotated data by domain experts. Semi-supervised learning offers potential efficient methods to improve model performance without excessive annotation burden., Purpose: This work tests the viability of semi-supervision for brain metastases segmentation., Study Type: Retrospective., Subjects: There were 156, 65, 324, and 200 labeled scans from four institutions and 519 unlabeled scans from a single institution. All subjects included in the study had diagnosed with brain metastases., Field Strength/sequences: 1.5 T and 3 T, 2D and 3D T1-weighted pre- and post-contrast, and fluid-attenuated inversion recovery (FLAIR)., Assessment: Three semi-supervision methods (mean teacher, cross-pseudo supervision, and interpolation consistency training) were adapted with the U-Net architecture. The three semi-supervised methods were compared to their respective supervised baseline on the full and half-sized training., Statistical Tests: Evaluation was performed on a multinational test set from four different institutions using 5-fold cross-validation. Method performance was evaluated by the following: the number of false-positive predictions, the number of true positive predictions, the 95th Hausdorff distance, and the Dice similarity coefficient (DSC). Significance was tested using a paired samples t test for a single fold, and across all folds within a given cohort., Results: Semi-supervision outperformed the supervised baseline for all sites with the best-performing semi-supervised method achieved an on average DSC improvement of 6.3% ± 1.6%, 8.2% ± 3.8%, 8.6% ± 2.6%, and 15.4% ± 1.4%, when trained on half the dataset and 3.6% ± 0.7%, 2.0% ± 1.5%, 1.8% ± 5.7%, and 4.7% ± 1.7%, compared to the supervised baseline on four test cohorts. In addition, in three of four datasets, the semi-supervised training produced equal or better results than the supervised models trained on twice the labeled data., Data Conclusion: Semi-supervised learning allows for improved segmentation performance over the supervised baseline, and the improvement was particularly notable for independent external test sets when trained on small amounts of labeled data., Plain Language Summary: Artificial intelligence requires extensive datasets with large amounts of annotated data from medical experts which can be difficult to acquire due to the large workload. To compensate for this, it is possible to utilize large amounts of un-annotated clinical data in addition to annotated data. However, this method has not been widely tested for the most common intracranial brain tumor, brain metastases. This study shows that this approach allows for data efficient deep learning models across multiple institutions with different clinical protocols and scanners., Level of Evidence: 3 TECHNICAL EFFICACY: Stage 2., (© 2025 The Author(s). Journal of Magnetic Resonance Imaging published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.)

Background: Alzheimer’s disease is a progressive neurological condition marked by a decline in cognitive abilities. Early diagnosis is crucial but challenging due to overlapping symptoms among impairment stages, necessitating non-invasive, reliable diagnostic tools. Methods: We applied information geometry and manifold learning to analyze grayscale MRI scans classified into No Impairment, Very Mild, Mild, and Moderate Impairment. Preprocessed images were reduced via Principal Component Analysis (retaining 95% variance) and converted into statistical manifolds using estimated mean vectors and covariance matrices. Geodesic distances, computed with the Fisher Information metric, quantified class differences. Graph Neural Networks, including Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and GraphSAGE, were utilized to categorize impairment levels using graph-based representations of the MRI data. Results: Significant differences in covariance structures were observed, with increased variability and stronger feature correlations at higher impairment levels. Geodesic distances between No Impairment and Mild Impairment (58.68, p<0.001) and between Mild and Moderate Impairment (58.28, p<0.001) are statistically significant. GCN and GraphSAGE achieve perfect classification accuracy (precision, recall, F1-Score: 1.0), correctly identifying all instances across classes. GAT attains an overall accuracy of 59.61%, with variable performance across classes. Conclusions: Integrating information geometry, manifold learning, and GNNs effectively differentiates AD impairment stages from MRI data. The strong performance of GCN and GraphSAGE indicates their potential to assist clinicians in the early identification and tracking of Alzheimer’s disease progression.

Background: The Graph theory provides the platform that could be used to model complex brain networks mathematically, and it could play a significant role in the diagnosis of various neurodegenerative diseases such as Alzheimer's. Purpose: The main aim of our study is to perform a comparative analysis in terms of various graph theoretic measures of structural brain networks. In particular, the paper evaluates graph theoretical measures by first forming graphs using magnetic resonance imaging (MRI) data. Method: In this paper, we study and evaluate graph theoretical measures using MRI data, namely characteristic path length, global efficiency, strength, and clustering coefficient, in a cohort of normal controls (N = 30), a cohort of mild cognitive impairment (MCI) (N = 30), and a cohort of Alzheimer's disease (AD) (N = 30). In our work, MRI data is preprocessed and cortical thickness is extracted for each brain region. The connectivity matrix is obtained, and thus a graph is formed. We have also performed receiver operating characteristic (ROC) and area under the ROC analyses of all graph theoretical measures to better elucidate and validate the results. Results: It is observed that these measures may be used to differentiate Alzheimer's from normal. In our study, we observed that a very random and disrupted network is obtained in the case of Alzheimer's in comparison with the normal and MCI cases. The other observations in terms of graph theoretic measures are an increase in characteristic path length, a decrease in global efficiency, a decrease in strength, and a reduction in values of the clustering coefficient in the case of Alzheimer's. Conclusion: The findings suggest that graph theoretical measures and alterations in network topology could be used as quantitative biomarkers of AD. [ABSTRACT FROM AUTHOR]

Background: Alzheimer’s disease (AD) is a neurodegenerative condition that has no definitive treatment, and its early diagnosis can help to prevent or slow down its progress. Structural magnetic resonance imaging (sMRI) and the progress of artificial intelligence (AI) have significant attention in AD detection. This study aims to differentiate AD from NC and distinguish between LMCI and EMCI from the other two classes. Another goal is the diagnostic performance (accuracy and AUC) of sMRI for predicting AD in its early stages. Methods: In this study, 398 participants were used from the ADNI and OASIS global database of sMRI including 98 individuals with AD, 102 with early mild cognitive impairment (EMCI), 98 with late mild cognitive impairment (LMCI), and 100 normal controls (NC). Results: The proposed model achieved high area under the curve (AUC) values and an accuracy of 99.7%, which is very remarkable for all four classes: NC vs. AD: AUC = [0.985], EMCI vs. NC: AUC = [0.961], LMCI vs. NC: AUC = [0.951], LMCI vs. AD: AUC = [0.989], and EMCI vs. LMCI: AUC = [1.000]. Conclusions: The results reveal that this model incorporates DenseNet169, transfer learning, and class decomposition to classify AD stages, particularly in differentiating EMCI from LMCI. The proposed model performs well with high accuracy and area under the curve for AD diagnostics at early stages. In addition, the accurate diagnosis of EMCI and LMCI can lead to early prediction of AD or prevention and slowing down of AD before its progress.

Deep learning models have become essential for automated medical image analysis in brain tumor detection. Existing Convolutional Neural Network (CNN) models like Visual Geometry Group 19 (VGG19), Residual Network 18 (ResNet18), and Residual Network 34 (ResNet34), despite their success in image classification and recognition, face challenges such as unclear boundary detection, limited generalization, and lower computational efficiency in detecting brain tumors. To address these issues, this study introduces VGG19-Brain’s MRI for Tumor (BMT), an enhanced version of the classic VGG19 model. VGG19-BMT incorporates targeted optimizations, including adjustments to convolutional layers and improved feature extraction modules. A systematic comparative analysis of VGG19-BMT and traditional CNN models was conducted using the Kaggle dataset “Brain MRI Images for Brain Tumor Detection.” The results demonstrate that VGG19-BMT outperforms conventional models’ boundary recognition accuracy, generalization, and computational efficiency, providing a more effective solution for automated brain tumor detection. This advancement not only enhances diagnostic capabilities but also sets the stage for future model improvements and clinical applications in medical imaging.

Background: Volumetric analysis and segmentation of magnetic resonance imaging (MRI) data is an important tool for evaluating neurological disease progression and neurodevelopment. Fully automated segmentation pipelines offer faster and more reproducible results. However, since these analysis pipelines were trained on or run based on atlases consisting of neurotypical controls, it is important to evaluate how accurate these methods are for neurodegenerative diseases. In this study, we compared 5 fully automated segmentation pipelines including FSL, Freesurfer, volBrain, SPM12, and SimNIBS with a manual segmentation process in GM1 gangliosidosis patients and neurotypical controls., Methods: We analyzed 45 MRI scans from 16 juvenile GM1 gangliosidosis patients, 11 MRI scans from 8 late-infantile GM1 gangliosidosis patients, and 19 MRI scans from 11 neurotypical controls. We compared results for 7 brain structures including volumes of the total brain, bilateral thalamus, ventricles, bilateral caudate nucleus, bilateral lentiform nucleus, corpus callosum, and cerebellum., Results: We found volBrain's vol2Brain pipeline to have the strongest correlations with the manual segmentation process for the whole brain, ventricles, and thalamus. We also found Freesurfer's recon-all pipeline to have the strongest correlations with the manual segmentation process for the caudate nucleus. For the cerebellum, we found a combination of volBrain's vol2Brain and SimNIBS' headreco to have the strongest correlations depending on the cohort. For the lentiform nucleus, we found a combination of recon-all and FSL's FIRST to give the strongest correlations depending on the cohort. Lastly, we found segmentation of the corpus callosum to be highly variable., Conclusion: Previous studies have considered automated segmentation techniques to be unreliable, particularly in neurodegenerative diseases. However, in our study we produced results comparable to those obtained with a manual segmentation process. While manual segmentation processes conducted by neuroradiologists remain the gold standard, we present evidence to the capabilities and advantages of using an automated process including the ability to segment white matter throughout the brain or analyze large datasets, which pose feasibility issues to fully manual processes. Future investigations should consider the use of artificial intelligence-based segmentation pipelines to determine their accuracy in GM1 gangliosidosis, lysosomal storage disorders, and other neurodegenerative diseases., Competing Interests: Competing Interests The authors declare no conflict of interest.

Deep learning (DL)-based image synthesis has recently gained enormous interest in medical imaging, allowing for generating multi-contrast data and therefore, the recovery of missing samples from interrupted or artefact-distorted acquisitions. However, the accuracy of DL models heavily relies on the representativeness of the training datasets naturally characterized by their distributions, experimental setups or preprocessing schemes. These complicate generalizing DL models across multi-site heterogeneous data sets while maintaining the confidentiality of the data. One of the possible solutions is to employ federated learning (FL), which enables the collaborative training of a DL model in a decentralized manner, demanding the involved sites to share only the characteristics of the models without transferring their sensitive medical data. The paper presents a DL-based magnetic resonance (MR) data translation in a FL way. We introduce a new aggregation strategy called FedBAdam that couples two state-of-the-art methods with complementary strengths by incorporating momentum in the aggregation scheme and skipping the batch normalization layers. The work comprehensively validates 10 FL-based strategies for an image-to-image multi-contrast MR translation, considering healthy and tumorous brain scans from five different institutions. Our study has revealed that the FedBAdam shows superior results in terms of mean squared error and structural similarity index over personalized methods, like the FedMRI, and standard FL-based aggregation techniques, such as the FedAvg or FedProx, considering multi-site multi-vendor heterogeneous environment. The FedBAdam has prevented the overfitting of the model and gradually reached the optimal model parameters, exhibiting no oscillations.

Quantitative analysis of pseudo-diffusion in diffusion-weighted magnetic resonance imaging (DWI) data shows potential for assessing fetal lung maturation and generating valuable imaging biomarkers. Yet, the clinical utility of DWI data is hindered by unavoidable fetal motion during acquisition. We present IVIM-morph, a self-supervised deep neural network model for motion-corrected quantitative analysis of DWI data using the Intra-voxel Incoherent Motion (IVIM) model. IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion. To promote physically plausible image registration, we introduce a biophysically informed loss function that effectively balances registration and model-fitting quality. We validated the efficacy of IVIM-morph by establishing a correlation between the predicted IVIM model parameters of the lung and gestational age (GA) using fetal DWI data of 39 subjects. Our approach was compared against six baseline methods: 1) no motion compensation, 2) affine registration of all DWI images to the initial image, 3) deformable registration of all DWI images to the initial image, 4) deformable registration of each DWI image to its preceding image in the sequence, 5) iterative deformable motion compensation combined with IVIM model parameter estimation, and 6) self-supervised deep-learning-based deformable registration. IVIM-morph exhibited a notably improved correlation with gestational age (GA) when performing in-vivo quantitative analysis of fetal lung DWI data during the canalicular phase. Specifically, over 2 test groups of cases, it achieved an R f 2 of 0.44 and 0.52, outperforming the values of 0.27 and 0.25, 0.25 and 0.00, 0.00 and 0.00, 0.38 and 0.00, and 0.07 and 0.14 obtained by other methods. IVIM-morph shows potential in developing valuable biomarkers for non-invasive assessment of fetal lung maturity with DWI data. Moreover, its adaptability opens the door to potential applications in other clinical contexts where motion compensation is essential for quantitative DWI analysis. The IVIM-morph code is readily available at:https://github.com/TechnionComputationalMRILab/qDWI-Morph.

Background Multimodality imaging is essential for personalized prognostic stratification in suspected coronary artery disease (CAD). Machine learning (ML) methods can help address this complexity by incorporating a broader spectrum of variables. Purpose To investigate the performance of an ML model that uses both stress cardiac MRI and coronary CT angiography (CCTA) data to predict major adverse cardiovascular events (MACE) in patients with newly diagnosed CAD. Materials and Methods This retrospective study included consecutive symptomatic patients without known CAD referred for CCTA between December 2008 and January 2020. Patients with obstructive CAD (at least one ≥50% stenosis at CCTA) underwent stress cardiac MRI for functional assessment. Eighteen clinical, two electrocardiogram, nine CCTA, and 12 cardiac MRI parameters were evaluated as inputs for the ML model, which involved automated feature selection with the least absolute shrinkage and selection operator algorithm and model building with an XGBoost algorithm. The primary outcome was MACE, defined as a composite of cardiovascular death and nonfatal myocardial infarction. External testing was performed using two independent datasets. Performance was compared between the ML model and existing scores and other approaches using the area under the receiver operating characteristic curve (AUC). Results Of 2210 patients who completed cardiac MRI, 2038 (mean age, 70 years ± 12 [SD]; 1091 [53.5%] female participants) completed follow-up (median duration, 7 years [IQR, 6-9 years]); 281 experienced MACE (13.8%). The ML model exhibited a higher AUC (0.86) for MACE prediction than the European Society of Cardiology score (0.55), QRISK3 score (0.60), Framingham Risk Score (0.50), segment involvement score (0.71), CCTA data alone (0.76), or stress cardiac MRI data alone (0.83) ( P value range, <.001 to .004). The ML model also exhibited good performance in the two external validation datasets (AUC, 0.84 and 0.92). Conclusion An ML model including both CCTA and stress cardiac MRI data demonstrated better performance in predicting MACE than traditional methods and existing scores in patients with newly diagnosed CAD. © RSNA, 2025 Supplemental material is available for this article.

Purpose To combine deep learning and biology-based modeling to predict the response of locally advanced, triple-negative breast cancer before initiating neoadjuvant chemotherapy (NAC). Materials and Methods In this retrospective study, a biology-based mathematical model of tumor response to NAC was constructed and calibrated on a patient-specific basis using imaging data from patients enrolled in the MD Anderson A Robust TNBC Evaluation FraMework to Improve Survival trial (ARTEMIS; ClinicalTrials.gov registration no. NCT02276443) between April 2018 and May 2021. To relate the calibrated parameters in the biology-based model and pretreatment MRI data, a convolutional neural network (CNN) was employed. The CNN predictions of the calibrated model parameters were used to estimate tumor response at the end of NAC. CNN performance in the estimations of total tumor volume (TTV), total tumor cellularity (TTC), and tumor status was evaluated. Model-predicted TTC and TTV measurements were compared with MRI-based measurements using the concordance correlation coefficient and area under the receiver operating characteristic curve (for predicting pathologic complete response at the end of NAC). Results The study included 118 female patients (median age, 51 years [range, 29-78 years]). For comparison of CNN predicted to measured change in TTC and TTV over the course of NAC, the concordance correlation coefficient values were 0.95 (95% CI: 0.90, 0.98) and 0.94 (95% CI: 0.87, 0.97), respectively. CNN-predicted TTC and TTV had an area under the receiver operating characteristic curve of 0.72 (95% CI: 0.34, 0.94) and 0.72 (95% CI: 0.40, 0.95) for predicting tumor status at the time of surgery, respectively. Conclusion Deep learning integrated with a biology-based mathematical model showed good performance in predicting the spatial and temporal evolution of a patient's tumor during NAC using only pre-NAC MRI data. Keywords: Triple-Negative Breast Cancer, Neoadjuvant Chemotherapy, Convolutional Neural Network, Biology-based Mathematical Model Supplemental material is available for this article. Clinical trial registration no. NCT02276443 ©RSNA, 2024 See also commentary by Mei and Huang in this issue.

A new approach to analysis of prostate hybrid multidimensional MRI (HM-MRI) data was introduced in this study. HM-MRI data were acquired for a combination of a few echo times (TEs) and a few b-values. Naturally, there is a matrix associated with HM-MRI data for each image pixel. To process the data, we first linearized HM-MRI data by taking the natural logarithm of the imaging signal intensity. Subsequently, a hybrid symmetric matrix was constructed by multiplying the matrix for each pixel by its own transpose. The eigenvalues for each pixel could then be calculated from the hybrid symmetric matrix. In order to compare eigenvalues between patients, three b-values and three TEs were used, because this was smallest number of b-values and TEs among all patients. The results of eigenvalues were displayed as qualitative color maps for easier visualization. For quantitative analysis, the ratio (λ r ) of eigenvalues (λ 1 , λ 2 , λ 3 ) was defined as λ r  = (λ 1 /λ 2 )/λ 3 to compare region of interest (ROI) between prostate cancer (PCa) and normal tissue. The results show that the combined eigenvalue maps show PCas clearly and these maps are quite different from apparent diffusion coefficient (ADC) and T2 maps of the same prostate. The PCa has significant larger λ r , smaller ADC and smaller T2 values than normal prostate tissue (p < 0.001). This suggests that the matrix-based method for analyzing HM-MRI data provides new information that may be clinically useful. The method is easy to use and could be easily implemented in clinical practice. The eigenvalues are associated with combination of ADC and T2 values, and could aid in the identification and staging of PCa., (© 2024 The Author(s). Journal of Applied Clinical Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Purpose To extend a previously developed machine learning algorithm for harmonizing brain volumetric data of individuals undergoing neuroradiologic assessment of Alzheimer disease not encountered during model training. Materials and Methods Neuroharmony is a recently developed method that uses image quality metrics as predictors to remove scanner-related effects in brain-volumetric data using random forest regression. To account for the interactions between Alzheimer disease pathology and image quality metrics during harmonization, the authors developed a multiclass extension of Neuroharmony for individuals with and without cognitive impairment. Cross-validation experiments were performed to benchmark performance against other available strategies using data from 20 864 participants with and without cognitive impairment, spanning 11 prospective and retrospective cohorts and 43 scanners. Evaluation metrics assessed the ability to remove scanner-related variations in brain volumes (marker concordance between scanner pairs) while retaining the ability to delineate different diagnostic groups (preserving disease-related signal). Results For each strategy, marker concordances between scanners were significantly better ( P < .001) compared with preharmonized data. The proposed multiclass model achieved significantly higher concordance (mean, 0.75 ± 0.09 [SD]) than the Neuroharmony model trained on individuals without cognitive impairment (mean, 0.70 ± 0.11) and preserved disease-related signal (∆AUC [area under the receiver operating characteristic curve] = -0.006 ± 0.027) better than the Neuroharmony model trained on individuals with and without cognitive impairment that did not use the proposed extension (∆AUC = -0.091 ± 0.036). The marker concordance was better in scanners seen during training (concordance > 0.97) than unseen (concordance < 0.79), independent of cognitive status. Conclusion In a large-scale multicenter dataset, the proposed multiclass Neuroharmony model outperformed other available strategies for harmonizing brain volumetric data from unseen scanners in a clinical setting. Keywords: Image Postprocessing, MR Imaging, Dementia, Random Forest Supplemental material is available for this article. Published under a CC BY 4.0 license See also commentary by Haller in this issue.

Objective: The objective of this study is to develop and validate a multiparametric MRI model employing machine learning to predict the effectiveness of treatment and the stage of breast cancer., Methods: The study encompassed 400 female patients diagnosed with breast cancer, with 200 individuals allocated to both the control and experimental groups, undergoing examinations in Shenzhen, China, during the period 2017-2023. This study pertains to retrospective research. Multiparametric MRI was employed to extract data concerning tumor size, blood flow, and metabolism., Results: The model achieved high accuracy, predicting treatment outcomes with an accuracy of 92%, sensitivity of 88%, and specificity of 95%. The model effectively classified breast cancer stages: stage I, 38% ( P  = 0.027); stage II, 72% ( P  = 0.014); stage III, 50% ( P  = 0.032); and stage IV, 45% ( P  = 0.041)., Conclusions: The developed model, utilizing multiparametric MRI and machine learning, exhibits high accuracy in predicting the effectiveness of treatment and breast cancer staging. These findings affirm the model's potential to enhance treatment strategies and personalize approaches for patients diagnosed with breast cancer. Our study presents an innovative approach to the diagnosis and treatment of breast cancer, integrating MRI data with machine learning algorithms. We demonstrate that the developed model exhibits high accuracy in predicting treatment efficacy and differentiating cancer stages. This underscores the importance of utilizing MRI and machine learning algorithms to enhance the diagnosis and individualization of treatment for this disease., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.)

Background: Alzheimer's disease is a progressive neurological condition marked by a decline in cognitive abilities. Early diagnosis is crucial but challenging due to overlapping symptoms among impairment stages, necessitating non-invasive, reliable diagnostic tools. Methods: We applied information geometry and manifold learning to analyze grayscale MRI scans classified into No Impairment, Very Mild, Mild, and Moderate Impairment. Preprocessed images were reduced via Principal Component Analysis (retaining 95% variance) and converted into statistical manifolds using estimated mean vectors and covariance matrices. Geodesic distances, computed with the Fisher Information metric, quantified class differences. Graph Neural Networks, including Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and GraphSAGE, were utilized to categorize impairment levels using graph-based representations of the MRI data. Results: Significant differences in covariance structures were observed, with increased variability and stronger feature correlations at higher impairment levels. Geodesic distances between No Impairment and Mild Impairment (58.68, p < 0.001 ) and between Mild and Moderate Impairment (58.28, p < 0.001 ) are statistically significant. GCN and GraphSAGE achieve perfect classification accuracy (precision, recall, F1-Score: 1.0), correctly identifying all instances across classes. GAT attains an overall accuracy of 59.61%, with variable performance across classes. Conclusions: Integrating information geometry, manifold learning, and GNNs effectively differentiates AD impairment stages from MRI data. The strong performance of GCN and GraphSAGE indicates their potential to assist clinicians in the early identification and tracking of Alzheimer's disease progression. [ABSTRACT FROM AUTHOR]