Recent vision-language foundation models deliver state-of-the-art results on natural image classification but falter on medical images due to pronounced domain shifts. At the same time, training a medical foundation model requires substantial resources, including extensive annotated data and high computational capacity. To bridge this gap with minimal overhead, we introduce MedBridge, a lightweight multimodal adaptation framework that re-purposes pretrained VLMs for accurate medical image diagnosis. MedBridge comprises three key components. First, a Focal Sampling module that extracts high-resolution local regions to capture subtle pathological features and compensate for the limited input resolution of general-purpose VLMs. Second, a Query Encoder (QEncoder) injects a small set of learnable queries that attend to the frozen feature maps of VLM, aligning them with medical semantics without retraining the entire backbone. Third, a Mixture of Experts mechanism, driven by learnable queries, harnesses the complementary strength of diverse VLMs to maximize diagnostic performance. We evaluate MedBridge on five medical imaging benchmarks across three key adaptation tasks, demonstrating its superior performance in both cross-domain and in-domain adaptation settings, even under varying levels of training data availability. Notably, MedBridge achieved over 6-15% improvement in AUC compared to state-of-the-art VLM adaptation methods in multi-label thoracic disease diagnosis, underscoring its effectiveness in leveraging foundation models for accurate and data-efficient medical diagnosis. Our code is available at https://github.com/ai-med/MedBridge.

Predicting the risk of developing breast cancer is an important clinical tool to guide early intervention and tailoring personalized screening strategies. Early risk models have limited performance and recently machine learning-based analysis of mammogram images showed encouraging risk prediction effects. These models however are limited to the use of a single exam or tend to overlook nuanced breast tissue evolvement in spatial and temporal details of longitudinal imaging exams that are indicative of breast cancer risk. In this paper, we propose STA-Risk (Spatial and Temporal Asymmetry-based Risk Prediction), a novel Transformer-based model that captures fine-grained mammographic imaging evolution simultaneously from bilateral and longitudinal asymmetries for breast cancer risk prediction. STA-Risk is innovative by the side encoding and temporal encoding to learn spatial-temporal asymmetries, regulated by a customized asymmetry loss. We performed extensive experiments with two independent mammogram datasets and achieved superior performance than four representative SOTA models for 1- to 5-year future risk prediction. Source codes will be released upon publishing of the paper.

Early screening, diagnosis, and treatment of lung cancer are pivotal in clinical practice since the tumor stage remains the most dominant factor that affects patient survival. Previous initiatives have tried to develop new tools for decision-making of lung cancer. In this study, we proposed the China Protocol, a complete workflow of lung cancer tailored to the Chinese population, which is implemented by steps including early screening by evaluation of risk factors and three-dimensional thin-layer image reconstruction technique for low-dose computed tomography (Tre-LDCT), accurate diagnosis via artificial intelligence (AI) and novel biomarkers, and individualized treatment through non-invasive molecule visualization strategies. The application of this protocol has improved the early diagnosis and 5-year survival rates of lung cancer in China. The proportion of early-stage (stage I) lung cancer has increased from 46.3% to 65.6%, along with a 5-year survival rate of 90.4%. Moreover, especially for stage IA1 lung cancer, the diagnosis rate has improved from 16% to 27.9%; meanwhile, the 5-year survival rate of this group achieved 97.5%. Thus, here we defined stage IA1 lung cancer, which cohort benefits significantly from early diagnosis and treatment, as the "ultra-early stage lung cancer", aiming to provide an intuitive description for more precise management and survival improvement. In the future, we will promote our findings to multicenter remote areas through medical alliances and mobile health services with the desire to move forward the diagnosis and treatment of lung cancer.

One possible adverse effect of breast irradiation is the development of pulmonary fibrosis. The aim of this study was to determine whether planning CT scans can predict which patients are more likely to develop lung lesions after treatment. A retrospective analysis of 242 patient records was performed using different machine learning models. These models showed a remarkable correlation between the occurrence of fibrosis and the hounsfield units of lungs in CT data. Three different classification methods (Tree, Kernel-based, k-Nearest Neighbors) showed predictive values above 60%. The human predictive factor (HPF), a mathematical predictive model, further strengthened the association between lung hounsfield unit (HU) metrics and radiation-induced lung injury (RILI). These approaches optimize radiation treatment plans to preserve lung health. Machine learning models and HPF can also provide effective diagnostic and therapeutic support for other diseases.

Alzheimer's disease (AD) is the most prevalent type of dementia. It is linked with a gradual decline in various brain functions, such as memory. Many research efforts are now directed toward non-invasive procedures for early diagnosis because early detection greatly benefits the patient care and treatment outcome. Additional to an accurate diagnosis and reduction of the rate of misdiagnosis; Computer-Aided Design (CAD) systems are built to give definitive diagnosis. This paper presents a novel CAD system to determine stages of AD. Initially, deep learning techniques are utilized to extract features from the AD brain MRIs. Then, the extracted features are reduced using a proposed feature reduction technique named Deep Downsized Kernel Partial Least Squares (DDKPLS). The proposed approach selects a reduced number of samples from the initial information matrix. The samples chosen give rise to a new data matrix further processed by KPLS to deal with the high dimensionality. The reduced feature space is finally classified using ELM. The implementation is named DDKPLS-ELM. Reference tests have been performed on the Kaggle MRI dataset, which exhibit the efficacy of the DDKPLS-based classifier; it achieves accuracy up to 95.4% and an F1 score of 95.1%.

Accurate assessment of computed tomography (CT) image quality is crucial for ensuring diagnostic accuracy, optimizing imaging protocols, and preventing excessive radiation exposure. In clinical settings, where high-quality reference images are often unavailable, developing no-reference image quality assessment (NR-IQA) methods is essential. Recently, CT-NR-IQA methods using deep learning have been widely studied; however, significant challenges remain in handling multiple degradation factors and accurately reflecting real-world degradations. To address these issues, we propose a novel CT-NR-IQA method. Our approach utilizes a dataset that combines two degradation factors (noise and blur) to train convolutional neural network (CNN) models capable of handling multiple degradation factors. Additionally, we leveraged RadImageNet pre-trained models (ResNet50, DenseNet121, InceptionV3, and InceptionResNetV2), allowing the models to learn deep features from large-scale real clinical images, thus enhancing adaptability to real-world degradations without relying on artificially degraded images. The models' performances were evaluated by measuring the correlation between the subjective scores and predicted image quality scores for both artificially degraded and real clinical image datasets. The results demonstrated positive correlations between the subjective and predicted scores for both datasets. In particular, ResNet50 showed the best performance, with a correlation coefficient of 0.910 for the artificially degraded images and 0.831 for the real clinical images. These findings indicate that the proposed method could serve as a potential surrogate for subjective assessment in CT-NR-IQA.

Pineal region tumors (PRTs) are rare but deep-seated brain tumors, and complete surgical resection is crucial for effective tumor treatment. The choice of surgical approach is often challenging due to the low incidence and deep location. This study aims to combine machine learning and deep learning algorithms with pre-operative MRI images to build a model for PRTs surgical approaches recommendation, striving to model clinical experience for practical reference and education. This study was a retrospective study which enrolled a total of 173 patients diagnosed with PRTs radiologically from our hospital. Three traditional surgical approaches of were recorded for prediction label. Clinical and VASARI related radiological information were selected for machine learning prediction model construction. And MRI images from axial, sagittal and coronal views of orientation were also used for deep learning craniotomy approach prediction model establishment and evaluation. 5 machine learning methods were applied to construct the predictive classifiers with the clinical and VASARI features and all methods could achieve area under the ROC (Receiver operating characteristic) curve (AUC) values over than 0.7. And also, 3 deep learning algorithms (ResNet-50, EfficientNetV2-m and ViT) were applied based on MRI images from different orientations. EfficientNetV2-m achieved the highest AUC value of 0.89, demonstrating a significant high performance of prediction. And class activation mapping was used to reveal that the tumor itself and its surrounding relations are crucial areas for model decision-making. In our study, we used machine learning and deep learning to construct surgical approach recommendation models. Deep learning could achieve high performance of prediction and provide efficient and personalized decision support tools for PRTs surgical approach. Not applicable.

We explored the fractal and multifractal characteristics of breast mammogram micrographs to identify quantitative biomarkers associated with breast cancer progression. In addition to conventional fractal and multifractal analyses, we employed a recently developed fractal-functional distribution method, which transforms fractal measures into Gaussian distributions for more robust statistical interpretation. Given the sparsity of mammogram intensity data, we also analyzed how variations in intensity thresholds, used for binary transformations of the fractal dimension, follow unique trajectories that may serve as novel indicators of disease progression. Our findings demonstrate that fractal, multifractal, and fractal-functional parameters effectively differentiate between benign and cancerous tissue. Furthermore, the threshold-dependent behavior of intensity-based fractal measures presents distinct patterns in cancer cases. To complement these analyses, we applied the Inverse Participation Ratio (IPR) light localization technique to quantify structural disorder at the microscopic level. This multi-parametric approach, integrating spatial complexity and structural disorder metrics, offers a promising framework for enhancing the sensitivity and specificity of breast cancer detection.

Background and objective: Micro-ultrasound (micro-US) is a novel imaging modality with diagnostic accuracy comparable to MRI for detecting clinically significant prostate cancer (csPCa). We investigated whether artificial intelligence (AI) interpretation of micro-US can outperform clinical screening methods using PSA and digital rectal examination (DRE). Methods: We retrospectively studied 145 men who underwent micro-US guided biopsy (79 with csPCa, 66 without). A self-supervised convolutional autoencoder was used to extract deep image features from 2D micro-US slices. Random forest classifiers were trained using five-fold cross-validation to predict csPCa at the slice level. Patients were classified as csPCa-positive if 88 or more consecutive slices were predicted positive. Model performance was compared with a classifier using PSA, DRE, prostate volume, and age. Key findings and limitations: The AI-based micro-US model and clinical screening model achieved AUROCs of 0.871 and 0.753, respectively. At a fixed threshold, the micro-US model achieved 92.5% sensitivity and 68.1% specificity, while the clinical model showed 96.2% sensitivity but only 27.3% specificity. Limitations include a retrospective single-center design and lack of external validation. Conclusions and clinical implications: AI-interpreted micro-US improves specificity while maintaining high sensitivity for csPCa detection. This method may reduce unnecessary biopsies and serve as a low-cost alternative to PSA-based screening. Patient summary: We developed an AI system to analyze prostate micro-ultrasound images. It outperformed PSA and DRE in detecting aggressive cancer and may help avoid unnecessary biopsies.

The purpose is to evaluate the predictive value of dual-energy CT (DECT) combined with histogram parameters and a clinical prediction model for perineural invasion (PNI) in colorectal cancer (CRC). We retrospectively analyzed clinical and imaging data from 173 CRC patients who underwent preoperative DECT-enhanced scanning at two centers. Data from Qinghai University Affiliated Hospital (n = 120) were randomly divided into training and validation sets, while data from Lanzhou University Second Hospital (n = 53) served as the external validation set. Regions of interest (ROIs) were delineated to extract spectral and histogram parameters, and multivariate logistic regression identified optimal predictors. Six machine learning models-support vector machine (SVM), decision tree (DT), random forest (RF), logistic regression (LR), k-nearest neighbors (KNN), and extreme gradient boosting (XGBoost)-were constructed. Model performance and clinical utility were assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Four independent predictive factors were identified through multivariate analysis: entropy, CT40_KeV, CEA, and skewness. Among the six classifier models, RF model demonstrated the best performance in the training set (AUC = 0.918, 95% CI: 0.862-0.969). In the validation set, RF outperformed other models (AUC = 0.885, 95% CI: 0.772-0.972). Notably, in the external validation set, the XGBoost model achieved the highest performance (AUC = 0.823, 95% CI: 0.672-0.945). Dual-energy CT-based combined with histogram parameters and clinical prediction modeling can be effectively used for preoperative noninvasive assessment of perineural invasion in colorectal cancer.