Atherosclerosis is a leading cardiovascular disease typified by fatty streaks accumulating within arterial walls, culminating in potential plaque ruptures and subsequent strokes. Existing clinical risk scores, such as systematic coronary risk estimation and Framingham risk score, profile cardiovascular risks based on factors like age, cholesterol, and smoking, among others. However, these scores display limited sensitivity in early disease detection. Parallelly, ultrasound-based risk markers, such as the carotid intima media thickness, while informative, only offer limited predictive power. Notably, current models largely focus on either ultrasound image-derived risk markers or clinical risk factor data without combining both for a comprehensive, multimodal assessment. This study introduces a multimodal ensemble learning framework to assess atherosclerosis severity, especially in its early sub-clinical stage. We utilize a multi-objective optimization targeting both performance and diversity, aiming to integrate features from each modality effectively. Our objective is to measure the efficacy of models using multimodal data in assessing vascular aging, i.e., plaque presence and vascular age, over a six-year period. We also delineate a procedure for optimal model selection from a vast pool, focusing on best-suited models for classification tasks. Additionally, through eXplainable Artificial Intelligence techniques, this work delves into understanding key model contributors and discerning unique subject subgroups.

X-ray medical report generation is one of the important applications of artificial intelligence in healthcare. With the support of large foundation models, the quality of medical report generation has significantly improved. However, challenges such as hallucination and weak disease diagnostic capability still persist. In this paper, we first construct a large-scale multi-modal medical knowledge graph (termed M3KG) based on the ground truth medical report using the GPT-4o. It contains 2477 entities, 3 kinds of relations, 37424 triples, and 6943 disease-aware vision tokens for the CheXpert Plus dataset. Then, we sample it to obtain multi-granularity semantic graphs and use an R-GCN encoder for feature extraction. For the input X-ray image, we adopt the Swin-Transformer to extract the vision features and interact with the knowledge using cross-attention. The vision tokens are fed into a Q-former and retrieved the disease-aware vision tokens using another cross-attention. Finally, we adopt the large language model to map the semantic knowledge graph, input X-ray image, and disease-aware vision tokens into language descriptions. Extensive experiments on multiple datasets fully validated the effectiveness of our proposed knowledge graph and X-ray report generation framework. The source code of this paper will be released on https://github.com/Event-AHU/Medical_Image_Analysis.

Accurate localization of the epileptogenic zone (EZ) is essential for surgical success in temporal lobe epilepsy. While stereoelectroencephalography (SEEG) and structural magnetic resonance imaging (MRI) provide complementary insights, existing unimodal methods fail to fully capture epileptogenic brain activity, and multimodal fusion remains challenging due to data complexity and surgeon-dependent interpretations. To address these issues, we proposed a novel multimodal framework to improve EZ localization with SEEG-drived electrophysiology with structural connectivity in temporal lobe epilepsy. By retrospectively analyzing SEEG, post-implant Computed Tomography (CT) and MRI (T1 & Diffusion Tensor Imaging (DTI)) data from 15 patients, we reconstructed SEEG electrode positions and obtained the SEEG and structural connectivity fusion features. We then proposed a spatiotemporal co-attention deep neural network (ST-CANet) to identify the fusion features, categorizing electrodes into seizure onset zone (SOZ), propagation zone (PZ), and non-involved zone (NIZ). Anatomical EZ boundaries were delineated by fusing the electrode position and classification information on brain atlas. The proposed method was evaluated based on the identification and localization performance of three epilepsy-related zones. The experiment results demonstrate that our method achieves 98.08% average accuracy and outperforms other identification methods, and improves the localization with Dice similarity coefficients (DSC) of 95.65% (SOZ), 92.13% (PZ), and 99.61% (NIZ), aligning with clinically validated surgical resection areas. This multimodal fusion strategy based on electrophysiological and structural connectivity information promises to assist neurosurgeons in accurately localizing EZ and may find broader applications in preoperative planning for epilepsy surgeries.

Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advances in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modeling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver for the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input. We extensively evaluated RIIR on brain MRI, lung CT, and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only 5% of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.

The REgistry of Flow and Perfusion Imaging for Artificial Intelligence with PET (REFINE PET) was established to collect multicenter PET and associated computed tomography (CT) images, together with clinical data and outcomes, into a comprehensive research resource. REFINE PET will enable validation and development of both standard and novel cardiac PET/CT processing methods. REFINE PET is a multicenter, international registry that contains both clinical and imaging data. The PET scans were processed using QPET software (Cedars-Sinai Medical Center, Los Angeles, CA), while the CT scans were processed using deep learning (DL) to detect coronary artery calcium (CAC). Patients were followed up for the occurrence of major adverse cardiovascular events (MACE), which include death, myocardial infarction, unstable angina, and late revascularization (>90 days from PET). The REFINE PET registry currently contains data for 35,588 patients from 14 sites, with additional patient data and sites anticipated. Comprehensive clinical data (including demographics, medical history, and stress test results) were integrated with more than 2200 imaging variables across 42 categories. The registry is poised to address a broad range of clinical questions, supported by correlating invasive angiography (within 6 months of MPI) in 5972 patients and a total of 9252 major adverse cardiovascular events during a median follow-up of 4.2 years. The REFINE PET registry leverages the integration of clinical, multimodality imaging, and novel quantitative and AI tools to advance the role of PET/CT MPI in diagnosis and risk stratification.

This study employed machine learning models to quantitatively analyze liver fat content from MRI images for the evaluation of liver fibrosis and disease severity in patients with metabolic dysfunction-associated fatty liver disease (MAFLD). A total of 26 confirmed MAFLD cases, along with MRI image sequences obtained from public repositories, were included to perform a comprehensive assessment. Radiomics features-such as contrast, correlation, homogeneity, energy, and entropy-were extracted and used to construct a random forest classification model with optimized hyperparameters. The model achieved outstanding performance, with an accuracy of 96.8%, sensitivity of 95.7%, specificity of 97.8%, and an F1-score of 96.8%, demonstrating its strong capability in accurately evaluating the degree of liver fibrosis and overall disease severity in MAFLD patients. The integration of machine learning with MRI-based analysis offers a promising approach to enhancing clinical decision-making and guiding treatment strategies, underscoring the potential of advanced technologies to improve diagnostic precision and disease management in MAFLD.

Existing Lung Cancer Diagnosis (LCD) models have difficulty in detecting early-stage lung cancer due to the asymptomatic nature of the disease which leads to an increased death rate of patients. Therefore, it is important to diagnose lung disease at an early stage to save the lives of affected persons. Hence, the research work aims to develop an efficient lung disease diagnosis using deep learning techniques for the early and accurate detection of lung cancer. This is achieved by. Initially, the proposed model collects the mandatory CT images from the standard benchmark datasets. Then, the lung cancer segmentation is done by using the development of Hybrid Convolution (2D/3D)-based Adaptive DenseUnet with Attention mechanism (HC-ADAM). The Hybrid Sewing Training with Spider Monkey Optimization (HSTSMO) is introduced to optimize the parameters in the developed HC-ADAM segmentation approach. Finally, the dissected lung nodule imagery is considered for the lung cancer classification stage, where the Hybrid Adaptive Dilated Networks with Attention mechanism (HADN-AM) are implemented with the serial cascading of ResNet and Long Short Term Memory (LSTM) for attaining better categorization performance. The accuracy, precision, and F1-score of the developed model for the LIDC-IDRI dataset are 96.3%, 96.38%, and 96.36%, respectively.

BackgroundMagnetic Resonance Imaging (MRI) is a cornerstone in diagnosing brain tumors. However, the complex nature of these tumors makes accurate segmentation in MRI images a demanding task.ObjectiveAccurate brain tumor segmentation remains a critical challenge in medical image analysis, with early detection crucial for improving patient outcomes.MethodsTo develop and evaluate a novel UNet-based architecture for improved brain tumor segmentation in MRI images. This paper presents a novel UNet-based architecture for improved brain tumor segmentation. The UNet model architecture incorporates Leaky ReLU activation, batch normalization, and regularization to enhance training and performance. The model consists of varying numbers of layers and kernel sizes to capture different levels of detail. To address the issue of class imbalance in medical image segmentation, we employ focused loss and generalized Dice (GDL) loss functions.ResultsThe proposed model was evaluated on the BraTS'2020 dataset, achieving an accuracy of 99.64% and Dice coefficients of 0.8984, 0.8431, and 0.8824 for necrotic core, edema, and enhancing tumor regions, respectively.ConclusionThese findings demonstrate the efficacy of our approach in accurately predicting tumors, which has the potential to enhance diagnostic systems and improve patient outcomes.

To propose and evaluate an accelerated <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> quantification method that combines <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> -weighted fast spin echo (FSE) images and proton density (PD)-weighted anatomical FSE images, leveraging deep learning models for <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> mapping. The goal is to reduce scan time and facilitate integration into routine clinical workflows for osteoarthritis (OA) assessment. This retrospective study utilized MRI data from 40 participants (30 OA patients and 10 healthy volunteers). A volume of PD-weighted anatomical FSE images and a volume of <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> -weighted images acquired at a non-zero spin-lock time were used as input to train deep learning models, including a 2D U-Net and a multi-layer perceptron (MLP). <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> maps generated by these models were compared with ground truth maps derived from a traditional non-linear least squares (NLLS) fitting method using four <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> -weighted images. Evaluation metrics included mean absolute error (MAE), mean absolute percentage error (MAPE), regional error (RE), and regional percentage error (RPE). The best-performed deep learning models achieved RPEs below 5% across all evaluated scenarios. This performance was consistent even in reduced acquisition settings that included only one PD-weighted image and one <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> -weighted image, where NLLS methods cannot be applied. Furthermore, the results were comparable to those obtained with NLLS when longer acquisitions with four <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> -weighted images were used. The proposed approach enables efficient <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics> <mrow> <msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn> <mi>ρ</mi></mrow> </msub> </mrow> <annotation>$$ {T}_{1\rho } $$</annotation></semantics> </math> mapping using PD-weighted anatomical images, reducing scan time while maintaining clinical standards. This method has the potential to facilitate the integration of quantitative MRI techniques into routine clinical practice, benefiting OA diagnosis and monitoring.

BackgroundSex differences in Alzheimer's disease (AD) progression offer insights into pathogenesis and clinical management. White matter (WM) amplitude of low-frequency fluctuation (ALFF), reflecting neural activity, represents a potential disease biomarker.ObjectiveTo explore whether there are sex differences in regional WM ALFF among AD patients, amnestic mild cognitive impairment (aMCI) patients, and healthy controls (HCs), how it is related to cognitive performance, and whether it can be used for disease classification.MethodsResting-state functional magnetic resonance images and cognitive assessments were obtained from 85 AD (36 female), 52 aMCI (23 female), and 78 HCs (43 female). Two-way ANOVA examined group × sex interactions for regional WM ALFF and cognitive scores. WM ALFF-cognition correlations and support vector machine diagnostic accuracy were evaluated.ResultsSex × group interaction effects on WM ALFF were detected in the right superior longitudinal fasciculus (<i>F</i> = 20.08, <i>p</i>_{FDR_corrected} < 0.001), left superior longitudinal fasciculus (<i>F</i> = 5.45, <i>p</i>_{GRF_corrected} < 0.001) and right inferior longitudinal fasciculus (<i>F</i> = 6.00, <i>p</i>_{GRF_corrected} = 0.001). These WM ALFF values positively correlated with different cognitive performance between sexes. The support vector machine learning best differentiated aMCI from AD in the full cohort and males (accuracy = 75%), and HCs from aMCI in females (accuracy = 93%).ConclusionsSex differences in regional WM ALFF during AD progression are associated with cognitive performance and can be utilized for disease classification.