The decision to treat unruptured intracranial aneurysms remains a clinical dilemma. Middle cerebral artery (MCA) aneurysms represent a prevalent subtype of intracranial aneurysms. This study aims to develop a multimodal fusion deep learning model for stratifying rupture risk in MCA aneurysms. We retrospectively enrolled internal cohort and two external validation datasets with 578 and 51 MCA aneurysms, respectively. Multivariate logistic regression analysis was performed to identify independent predictors of rupture. Aneurysm morphological parameters were quantified using reconstructed CT angiography (CTA) images. Radiomics features of aneurysms were extracted through computational analysis. We developed MCANet - a multimodal data-driven classification model integrating raw CTA images, radiomics features, clinical parameters, and morphological characteristics - to establish an aneurysm rupture risk assessment framework. External validation was conducted using datasets from two independent medical centers to evaluate model generalizability and small-sample robustness. Four key metrics, including accuracy, F1-score, precision, and recall, were employed to assess model performance. In the internal cohort, 369 aneurysms were ruptured. Independent predictors of rupture included: the presence of multiple aneurysms, aneurysm location, aneurysm angle, presence of daughter-sac aneurysm, and height-width ratio. MCANet demonstrated satisfactory predictive performance with 91.38% accuracy, 96.33% sensitivity, 90.52% precision, and 93.33% F1-score. External validation maintained good discriminative ability across both independent cohorts. The MCANet model effectively integrates multimodal heterogeneous data for MCA aneurysm rupture risk prediction, demonstrating clinical applicability even in data-constrained scenarios. This model shows potential to optimize therapeutic decision-making and mitigate patient anxiety through individualized risk assessment.

Pulmonary nodules are critical indicators for the early detection of lung cancer; however, their diagnosis and management pose significant challenges due to the variability in nodule characteristics, reader fatigue, and limited clinical expertise, often leading to diagnostic errors. The rapid advancement of artificial intelligence (AI) presents promising solutions to address these issues. This review compares traditional rule-based methods, handcrafted feature-based machine learning, radiomics, deep learning, and hybrid models incorporating Transformers or attention mechanisms. It systematically compares their methodologies, clinical applications (diagnosis, treatment, prognosis), and dataset usage to evaluate performance, applicability, and limitations in pulmonary nodule management. AI advances have significantly improved pulmonary nodule management, with transformer-based models achieving leading accuracy in segmentation, classification, and subtyping. The fusion of multimodal imaging CT, PET, and MRI further enhances diagnostic precision. Additionally, AI aids treatment planning and prognosis prediction by integrating radiomics with clinical data. Despite these advances, challenges remain, including domain shift, high computational demands, limited interpretability, and variability across multi-center datasets. Artificial intelligence (AI) has transformative potential in improving the diagnosis and treatment of lung nodules, especially in improving the accuracy of lung cancer treatment and patient prognosis, where significant progress has been made.

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition with heterogeneous symptomatology, making accurate diagnosis challenging. Traditional methods rely on subjective behavioral assessments, often overlooking subtle neural biomarkers. This study introduces ASD-GraphNet, a novel graph-based learning framework for diagnosing ASD using functional Magnetic Resonance Imaging (fMRI) data. Leveraging the Autism Brain Imaging Data Exchange (ABIDE) dataset, ASD-GraphNet constructs brain networks based on established atlases (Craddock 200, AAL, and Dosenbach 160) to capture intricate connectivity patterns. The framework employs systematic preprocessing, graph construction, and advanced feature extraction to derive node-level, edge-level, and graph-level metrics. Feature engineering techniques, including Mutual Information-based selection and Principal Component Analysis (PCA), are applied to enhance classification performance. ASD-GraphNet evaluates a range of classifiers, including Logistic Regression, Support Vector Machines, and ensemble methods like XGBoost and LightGBM, achieving an accuracy of 75.25% in distinguishing individuals with ASD from healthy controls. This demonstrates the framework's potential to provide objective, data-driven diagnostics based solely on resting-state fMRI data. By integrating graph-based learning with neuroimaging and addressing dataset imbalance, ASD-GraphNet offers a scalable and interpretable solution for early ASD detection, paving the way for more reliable interventions. The GitHub repository for this project is available at: https://github.com/AmirDavoodi/ASD-GraphNet.

Early and precise diagnosis is essential for effectively treating and managing pulmonary tuberculosis. The purpose of this research is to leverage artificial intelligence (AI), specifically convolutional neural networks (CNNs), to expedite the diagnosis of tuberculosis (TB) using chest X-ray (CXR) images. Mycobacterium tuberculosis, an aerobic bacterium, is the causative agent of TB. The disease remains a global health challenge, particularly in densely populated countries. Early detection via chest X-rays is crucial, but limited medical expertise hampers timely diagnosis. This study explores the application of CNNs, a highly efficient method, for automated TB detection, especially in areas with limited medical expertise. Previously trained models, specifically VGG-16, VGG-19, ResNet 50, and Inception v3, were used to validate the data. Effective feature extraction and classification in medical image analysis, especially in TB diagnosis, is facilitated by the distinct design and capabilities that each model offers. VGG-16 and VGG-19 are very good at identifying minute distinctions and hierarchical characteristics from CXR images; on the other hand, ResNet 50 avoids overfitting while retaining both low and high-level features. The inception v3 model is quite useful for examining various complex patterns in a CXR image with its capacity to extract multi-scale features. Inception v3 outperformed other models, attaining 97.60% accuracy without pre-processing and 98.78% with pre-processing. The proposed model shows promising results as a tool for improving TB diagnosis, and reducing the global impact of the disease, but further validation with larger and more diverse datasets is needed.

The integration of artificial intelligence (AI) in radiology may necessitate refinement of the competencies expected of radiologists. There is currently a lack of understanding on what competencies radiology residency programs should ensure their graduates attain related to AI. This study aimed to identify what knowledge, skills, and attitudes are important for radiologists to use AI safely and effectively in clinical practice. Following Arksey and O'Malley's methodology, a scoping review was conducted by searching electronic databases (PubMed, Embase, Scopus, and ERIC) for articles published between 2010 and 2024. Two reviewers independently screened articles based on the title and abstract and subsequently by full-text review. Data were extracted using a standardized form to identify the knowledge, skills, and attitudes surrounding AI that may be important for its safe and effective use. Of 5920 articles screened, 49 articles met inclusion criteria. Core competencies were related to AI model development, evaluation, clinical implementation, algorithm bias and handling discrepancies, regulation, ethics, medicolegal issues, and economics of AI. While some papers proposed competencies for radiologists focused on technical development of AI algorithms, other papers centered competencies around clinical implementation and use of AI. Current AI educational programming in radiology demonstrates substantial heterogeneity with a lack of consensus on the knowledge, skills, and attitudes for the safe and effective use of AI in radiology. Further research is needed to develop consensus on the core competencies for radiologists to safely and effectively use AI to support the integration of AI training and assessment into residency programs.

To validate the diagnostic performance of a B-mode ultrasound-based deep learning (DL) model in distinguishing benign and malignant cervical lymphadenopathy (CLP). A total of 210 CLPs with conclusive pathological results were retrospectively included and separated as training (n = 169) or test cohort (n = 41) randomly at a ratio of 4:1. A DL model integrating convolutional neural network, deformable convolution network and attention mechanism was developed. Three diagnostic models were developed: (a) Model I, CLPs with at least one suspicious B-mode ultrasound feature (ratio of longitudinal to short diameter < 2, irregular margin, hyper-echogenicity, hilus absence, cystic necrosis and calcification) were deemed malignant; (b) Model II: total risk score of B-mode ultrasound features obtained by multivariate logistic regression and (c) Model III: CLPs with positive DL output are deemed malignant. The diagnostic utility of these models was assessed by the area under the receiver operating curve (AUC) and corresponding sensitivity and specificity. Multivariate analysis indicated that DL positive result was the most important factor associated with malignant CLPs [odds ratio (OR) = 39.05, p < 0.001], only followed by hilus absence (OR = 6.01, p = 0.001) in the training cohort. In the test cohort, the AUC of the DL model (0.871) was significantly higher than that in model I (AUC = 0.681, p = 0.04) and model II (AUC = 0.679, p = 0.03), respectively. In addition, model III obtained 93.3% specificity, which was significantly higher than that in model I (40.0%, p = 0.002) and model II (60.0%, p = 0.03), respectively. Although the sensitivity of model I was the highest, it did not show a significant difference compared to that of model III (96.2% vs.80.8%, p = 0.083). B-mode ultrasound-based DL is a potentially robust tool for the differential diagnosis of benign and malignant CLPs.

To investigate lumbar vertebral volumetric bone mineral density (vBMD) from ex vivo opportunistic multi-detector computed tomography (MDCT) scans using different protocols, and compare it to dedicated quantitative CT (QCT) values from the same specimens. Cadavers from two female donors (ages 62 and 68 years) were scanned (L1-L5) using six different MDCT protocols and one dedicated QCT scan. Opportunistic vBMD was extracted using an artificial intelligence-based algorithm. The vBMD measurements from the six MDCT protocols, which varied in peak tube voltage (80-140 kVp), tube load (72-200 mAs), slice thickness (0.75-1 mm), and/or slice increment (0.5-0.75 mm), were compared to those obtained from dedicated QCT. A strong positive correlation was observed between vBMD from opportunistic MDCT and reference QCT (ρ = 0.869, p < 0.01). Agreement between vBMD measurements from MDCT protocols and the QCT reference standard according to the intraclass correlation coefficient (ICC) was 0.992 (95% confidence interval [CI]: 0.982-0.998). Bland-Altman analysis showed biases ranging from - 12.66 to 8.00 mg/cm³ across the six MDCT protocols, with all data points falling within the respective limits of agreement (LOA) for both cadavers. Opportunistic vBMD measurements of lumbar vertebrae demonstrated reliable consistency ex vivo across various scan parameters when compared to dedicated QCT.

Quantifiable image patterns associated with disease progression and treatment response are critical tools for guiding individual treatment, and for developing novel therapies. Here, we show that unsupervised machine learning can identify a pattern vocabulary of liver tissue in magnetic resonance images that quantifies treatment response in diffuse liver disease. Deep clustering networks simultaneously encode and cluster patches of medical images into a low-dimensional latent space to establish a tissue vocabulary. The resulting tissue types capture differential tissue change and its location in the liver associated with treatment response. We demonstrate the utility of the vocabulary in a randomized controlled trial cohort of patients with nonalcoholic steatohepatitis. First, we use the vocabulary to compare longitudinal liver change in a placebo and a treatment cohort. Results show that the method identifies specific liver tissue change pathways associated with treatment and enables a better separation between treatment groups than established non-imaging measures. Moreover, we show that the vocabulary can predict biopsy derived features from non-invasive imaging data. We validate the method in a separate replication cohort to demonstrate the applicability of the proposed method.

To construct an intelligent analysis model for classifying fetal orientation during intrapartum ultrasound videos based on multi-feature fusion. The proposed model consists of the Input, Backbone Network and Classification Head modules. The Input module carries out data augmentation to improve the sample quality and generalization ability of the model. The Backbone Network was responsible for feature extraction based on Yolov8 combined with CBAM, ECA, PSA attention mechanism and AIFI feature interaction module. The Classification Head consists of a convolutional layer and a softmax function to output the final probability value of each class. The images of the key structures (the eyes, face, head, thalamus, and spine) were annotated with frames by physicians for model training to improve the classification accuracy of the anterior occipital, posterior occipital, and transverse occipital orientations. The experimental results showed that the proposed model had excellent performance in the tire orientation classification task with the classification accuracy reaching 0.984, an area under the PR curve (average accuracy) of 0.993, and area under the ROC curve of 0.984, and a kappa consistency test score of 0.974. The prediction results by the deep learning model were highly consistent with the actual classification results. The multi-feature fusion model proposed in this study can efficiently and accurately classify fetal orientation in intrapartum ultrasound videos.

To evaluate the cost-effectiveness of AI-assisted digital mammography (AI-DM) compared to conventional biennial breast cancer digital mammography screening (cDM) with double reading of screening mammograms, and to investigate the change in cost-effectiveness based on four different sub-strategies of AI-DM. A decision-analytic state-transition Markov model was used to analyse the decision of whether to use cDM or AI-DM in breast cancer screening. In this Markov model, one-year cycles were used, and the analysis was performed from a healthcare perspective with a lifetime horizon. In the model, we analysed 1000 hypothetical individuals attending mammography screenings assessed with AI-DM compared with 1000 hypothetical individuals assessed with cDM. The total costs, including both screening-related costs and breast cancer-related costs, were €3,468,967 and €3,528,288 for AI-DM and cDM, respectively. AI-DM resulted in a cost saving of €59,320 compared to cDM. Per 1000 individuals, AI-DM gained 10.8 quality-adjusted life years (QALYs) compared to cDM. Gained QALYs at a lower cost means that the AI-DM screening strategy was dominant compared to cDM. Break-even occurred at the second screening at age 42 years. This analysis showed that AI-assisted mammography for biennial breast cancer screening in a Swedish population of women aged 40-74 years is a cost-saving strategy compared to a conventional strategy using double human screen reading. Further clinical studies are needed, as scenario analyses showed that other strategies, more dependent on AI, are also cost-saving. Question To evaluate the cost-effectiveness of AI-DM in comparison to conventional biennial breast cDM screening. Findings AI-DM is cost-effective, and the break-even point occurred at the second screening at age 42 years. Clinical relevance The implementation of AI is clearly cost-effective as it reduces the total cost for the healthcare system and simultaneously results in a gain in QALYs.