The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialized domains remains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) that features strong capability in dense prediction tasks, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific pre-training. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D/3D classification and segmentation on a wide range of medical imaging modalities. We systematically analyze its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialization, such as in Whole-Slide Pathological Images (WSIs), Electron Microscopy (EM), and Positron Emission Tomography (PET). Furthermore, we observe that DINOv3 does not consistently obey scaling law in the medical domain; performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviors across tasks. Ultimately, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple complex medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.

Brain Metastases (BM) are a large contributor to mortality of patients with cancer. They are treated with Stereotactic Radiosurgery (SRS) and monitored with Magnetic Resonance Imaging (MRI) at regular follow-up intervals according to treatment guidelines. Analyzing and quantifying this longitudinal imaging represents an intractable workload for clinicians. As a result, follow-up images are not annotated and merely assessed by observation. Response to treatment in longitudinal imaging is being studied, to better understand growth trajectories and ultimately predict treatment success or toxicity as early as possible. In this study, we implement an automated pipeline to curate a large longitudinal dataset of SRS treatment data, resulting in a cohort of 896 BMs in 177 patients who were monitored for >360 days at approximately two-month intervals at Lausanne University Hospital (CHUV). We use a data-driven clustering to identify characteristic trajectories. In addition, we predict 12 months lesion-level response using classical as well as graph machine learning Graph Machine Learning (GML). Clustering revealed 5 dominant growth trajectories with distinct final response categories. Response prediction reaches up to 0.90 AUC (CI95%=0.88-0.92) using only pre-treatment and first follow-up MRI with gradient boosting. Similarly, robust predictive performance of up to 0.88 AUC (CI95%=0.86-0.90) was obtained using GML, offering more flexibility with a single model for multiple input time-points configurations. Our results suggest potential automation and increased precision for the comprehensive assessment and prediction of BM response to SRS in longitudinal MRI. The proposed pipeline facilitates scalable data curation for the investigation of BM growth patterns, and lays the foundation for clinical decision support systems aiming at optimizing personalized care.

Accurate evaluation of the response of glioblastoma to therapy is crucial for clinical decision-making and patient management. The Response Assessment in Neuro-Oncology (RANO) criteria provide a standardized framework to assess patients' clinical response, but their application can be complex and subject to observer variability. This paper presents an automated method for classifying the intervention response from longitudinal MRI scans, developed to predict tumor response during therapy as part of the BraTS 2025 challenge. We propose a novel hybrid framework that combines deep learning derived feature extraction and an extensive set of radiomics and clinically chosen features. Our approach utilizes a fine-tuned ResNet-18 model to extract features from 2D regions of interest across four MRI modalities. These deep features are then fused with a rich set of more than 4800 radiomic and clinically driven features, including 3D radiomics of tumor growth and shrinkage masks, volumetric changes relative to the nadir, and tumor centroid shift. Using the fused feature set, a CatBoost classifier achieves a mean ROC AUC of 0.81 and a Macro F1 score of 0.50 in the 4-class response prediction task (Complete Response, Partial Response, Stable Disease, Progressive Disease). Our results highlight that synergizing learned image representations with domain-targeted radiomic features provides a robust and effective solution for automated treatment response assessment in neuro-oncology.

We aimed to develop and validate a radiomics-based machine learning nomogram using multiparametric magnetic resonance imaging to preoperatively predict substantial lymphovascular space invasion in patients with endometrial cancer. This retrospective dual-center study included patients with histologically confirmed endometrial cancer who underwent preoperative magnetic resonance imaging (MRI). The patients were divided into training and test sets. Radiomic features were extracted from multiparametric magnetic resonance imaging to generate radiomic scores using a support vector machine algorithm. Three predictive models were constructed: clinical (Model^C), radiomics-only (Model^R), and fusion (Model^N). The models' performances were evaluated by analyzing their receiver operating characteristic curves, and pairwise comparisons of the models' areas under the curves were conducted using DeLong's test and adjusted using the Bonferroni correction. Decision curve analysis with integrated discrimination improvement was used for net benefit comparison. This study enrolled 283 women (training set: n = 198; test set: n = 85). The lymphovascular space invasion groups (substantial and no/focal) had significantly different radiomic scores (P < 0.05). Model^N achieved an area under the curve of 0.818 (95% confidence interval: 0.757-0.869) and 0.746 (95% confidence interval: 0.640-0.835) for the training and test sets, respectively, demonstrating a good fit according to the Hosmer-Lemeshow test (P > 0.05). The DeLong test with Bonferroni correction indicated that Model^N demonstrated better diagnostic efficiency than Model^C in predicting substantial lymphovascular space invasion in the two sets (adjusted P < 0.05). In addition, decision curve analysis demonstrated a higher net benefit for Model^N, with integrated discrimination improvements of 0.043 and 0.732 (P < 0.01) in the training and test sets, respectively. The multiparametric magnetic resonance imaging-based radiomics machine learning nomogram showed moderate diagnostic performance for substantial lymphovascular space invasion in patients with endometrial cancer.

Point-of-care ultrasonography has become a valuable tool for assessing diaphragmatic function in critically ill patients receiving invasive mechanical ventilation. However, conventional diaphragm ultrasound assessment remains highly operator-dependent and subjective. Previous research introduced automatic measurement of diaphragmatic excursion and velocity using 2D speckle-tracking technology. This study aimed to develop an artificial intelligence-multimodal learning framework to improve the prediction of weaning failure and guide individualized weaning strategies. This prospective study enrolled critically ill patients older than 18 years who received mechanical ventilation for more than 48 hours and were eligible for a spontaneous breathing trial in 2 intensive care units in Guangzhou, China. Before the spontaneous breathing trial, diaphragm ultrasound videos were collected using a standardized protocol, and automatic measurements of excursion and velocity were obtained. A total of 88 patients were included, with 50 successfully weaned and 38 experiencing weaning failure. Each patient record included 27 clinical and 6 diaphragmatic indicators, selected based on previous literature and phenotyping studies. Clinical variables were preprocessed using OneHotEncoder, normalization, and scaling. Ultrasound videos were interpolated to a uniform resolution of 224×224×96. Artificial intelligence-multimodal learning based on clinical characteristics, laboratory parameters, and diaphragm ultrasonic videos was established. Four experiments were conducted in an ablation setting to evaluate model performance using different combinations of input data: (1) diaphragmatic excursion only, (2) clinical and diaphragmatic indicators, (3) ultrasound videos only, and (4) all modalities combined (multimodal). Metrics for evaluation included classification accuracy, area under the receiver operating characteristic curve (AUC), average precision in the precision-recall curve, and calibration curve. Variable importance was assessed using SHAP (Shapley Additive Explanation) to interpret feature contributions and understand model predictions. The multimodal co-learning model outperformed all single-modal approaches. The accuracy improved when predicted through diaphragm ultrasound video data using Video Vision Transformer (accuracy=0.8095, AUC=0.852), clinical or ultrasound indicators (accuracy=0.7381, AUC=0.746), and the multimodal co-learning (accuracy=0.8331, AUC=0.894). The proposed co-learning model achieved the highest score (average precision=0.91) among the 4 experiments. Furthermore, calibration curve analysis demonstrated that the proposed colearning model was well calibrated, as the curve was closest to the perfectly calibrated line. Combining ultrasound and clinical data for colearning improved the accuracy of the weaning outcome prediction. Multimodal learning based on automatic measurement of point-of-care ultrasonography and automated collection of objective clinical indicators greatly enhanced the practical operability and user-friendliness of the system. The proposed model offered promising potential for widespread clinical application in intensive care settings.

In non-small cell lung cancer (NSCLC), non-invasive alternatives to biopsy-dependent driver mutation analysis are needed. We reviewed the effectiveness of radiomics alone or with clinical data and assessed the performance of artificial intelligence (AI) models in predicting oncogene mutation status. A PRISMA-compliant literature review for studies predicting oncogene mutation status in NSCLC patients using radiomics was conducted by a multidisciplinary team. Meta-analyses evaluating the performance of AI-based models developed with CT-derived radiomics features alone or combined with clinical data were performed. A meta-regression to analyze the influence of different predictors was also conducted. Of 890 studies identified, 124 evaluating models for the prediction of epidermal growth factor-1 (EGFR), anaplastic lymphoma kinase (ALK), and Kirsten rat sarcoma virus (KRAS) mutations were included in the systematic review, of which 51 were meta-analyzed. The AI algorithms' sensitivity/false positive rate (FPR) in predicting mutation status using radiomics-based models was 0.754 (95% CI 0.727-0.780)/0.344 (95% CI 0.308-0.381) for EGFR, 0.754 (95% CI 0.638-0.841)/0.225 (95% CI 0.163-0.302) for ALK and 0.475 (95% CI 0.153-0.820)/0.181 (95% CI 0.054-0.461) for KRAS. A meta-analysis of combined models was possible for EGFR mutation, revealing a sensitivity of 0.806 (95% CI 0.777-0.833) and a FPR of 0.315 (95% CI 0.270-0.364). No statistically significant results were obtained in the meta-regression. Radiomics-based models may offer a non-invasive alternative for determining oncogene mutation status in NSCLC. Further research is required to analyze whether clinical data might boost their performance. Question Can imaging-based radiomics and artificial intelligence non-invasively predict oncogene mutation status to improve diagnosis in non-small cell lung cancer (NSCLC)? Findings Radiomics-based models achieved high performance in predicting mutation status in NSCLC; adding clinical data showed limited improvement in predictive performance. Clinical relevance Radiomics and AI tools offer a non-invasive strategy to support molecular profiling in NSCLC. Validation studies addressing clinical and methodological aspects are essential to ensure their reliability and integration into routine clinical practice.

Preterm birth is a major cause of mortality and lifelong morbidity in childhood. Its complex and multifactorial origins limit the effectiveness of current clinical predictors and impede optimal care. In this study, a dual-branch deep learning architecture (PUUMA) was developed to predict gestational age (GA) at birth using T2* fetal MRI data from 295 pregnancies, encompassing a heterogeneous and imbalanced population. The model integrates both global whole-uterus and local placental features. Its performance was benchmarked against linear regression using cervical length measurements obtained by experienced clinicians from anatomical MRI and other Deep Learning architectures. The GA at birth predictions were assessed using mean absolute error. Accuracy, sensitivity, and specificity were used to assess preterm classification. Both the fully automated MRI-based pipeline and the cervical length regression achieved comparable mean absolute errors (3 weeks) and good sensitivity (0.67) for detecting preterm birth, despite pronounced class imbalance in the dataset. These results provide a proof of concept for automated prediction of GA at birth from functional MRI, and underscore the value of whole-uterus functional imaging in identifying at-risk pregnancies. Additionally, we demonstrate that manual, high-definition cervical length measurements derived from MRI, not currently routine in clinical practice, offer valuable predictive information. Future work will focus on expanding the cohort size and incorporating additional organ-specific imaging to improve generalisability and predictive performance.

Data scarcity hinders deep learning for medical imaging. We propose a framework for breast cancer classification in thermograms that addresses this using a Diffusion Probabilistic Model (DPM) for data augmentation. Our DPM-based augmentation is shown to be superior to both traditional methods and a ProGAN baseline. The framework fuses deep features from a pre-trained ResNet-50 with handcrafted nonlinear features (e.g., Fractal Dimension) derived from U-Net segmented tumors. An XGBoost classifier trained on these fused features achieves 98.0\% accuracy and 98.1\% sensitivity. Ablation studies and statistical tests confirm that both the DPM augmentation and the nonlinear feature fusion are critical, statistically significant components of this success. This work validates the synergy between advanced generative models and interpretable features for creating highly accurate medical diagnostic tools.

Quantification of brain atrophy currently requires visual rating scales which are time consuming and automated brain image analysis is warranted. We validated our automated deep learning (DL) tool measuring the Global Cerebral Atrophy (GCA) score against trained human raters, and associations with age and cognitive impairment, in representative older (>65 years) patients. CT-brain scans were obtained from patients in acute medicine (ORCHARD-EPR), acute stroke (OCS studies) and a legacy sample. Scans were divided in a 60/20/20 ratio for training, optimisation and testing. CT-images were assessed by two trained raters (rater-1=864 scans, rater-2=20 scans). Agreement between DL tool-predicted GCA scores (range 0-39) and the visual ratings was evaluated using mean absolute error (MAE) and Cohen's weighted kappa. Among 864 scans (ORCHARD-EPR=578, OCS=200, legacy scans=86), MAE between the DL tool and rater-1 GCA scores was 3.2 overall, 3.1 for ORCHARD-EPR, 3.3 for OCS and 2.6 for the legacy scans and half had DL-predicted GCA error between -2 and 2. Inter-rater agreement was Kappa=0.45 between the DL-tool and rater-1, and 0.41 between the tool and rater- 2 whereas it was lower at 0.28 for rater-1 and rater-2. There was no difference in GCA scores from the DL-tool and the two raters (one-way ANOVA, p=0.35) or in mean GCA scores between the DL-tool and rater-1 (paired t-test, t=-0.43, p=0.66), the tool and rater-2 (t=1.35, p=0.18) or between rater-1 and rater-2 (t=0.99, p=0.32). DL-tool GCA scores correlated with age and cognitive scores (both p<0.001). Our DL CT-brain analysis tool measured GCA score accurately and without user input in real-world scans acquired from older patients. Our tool will enable extraction of standardised quantitative measures of atrophy at scale for use in health data research and will act as proof-of-concept towards a point-of-care clinically approved tool.

<i>Background:</i> Neuroendocrine neoplasms (NENs) are a diverse group of malignancies in which somatostatin receptor expression can be crucial in guiding therapy. We aimed to evaluate the effectiveness of [^99mTc]Tc-EDDA/HYNIC-TOC SPECT/CT in differentiating neuroendocrine tumor histology, selecting candidates for radioligand therapy, and identifying correlations between somatostatin receptor expression and non-imaging parameters in metastatic NENs. <i>Methods:</i> This retrospective study included 65 patients (29 women, 36 men, mean age 61) with metastatic neuroendocrine neoplasms confirmed by histology, follow-up, or imaging, comprising 14 poorly differentiated carcinomas and 51 well-differentiated tumors. Somatostatin receptor SPECT/CT results were assessed visually and semiquantitatively, with mathematical models incorporating histological, oncological, immunohistochemical, and laboratory parameters, followed by biostatistical analysis. <i>Results:</i> Of 392 lesions evaluated, the majority were metastases in the liver, lymph nodes, and bones. Mathematical models estimated somatostatin receptor expression accurately (70-83%) based on clinical parameters alone. Key factors included tumor origin, oncological treatments, and the immunohistochemical marker CK7. Associations were found between age, grade, disease extent, and markers (CEA, CA19-9, AFP). <i>Conclusions:</i> Our findings suggest that [^99mTc]Tc-EDDA/HYNIC-TOC SPECT/CT effectively evaluates somatostatin receptor expression in NENs. Certain immunohistochemical and laboratory parameters, beyond recognized factors, show potential prognostic value, supporting individualized treatment strategies.