High-resolution CT (HR-CT) cannot image trabecular bone due to insufficient spatial resolution. Ultra-high-resolution CT may be a valuable alternative. We aimed to describe the accuracy of Canon Medical HR, super-high-resolution (SHR), and ultra-high-resolution (UHR)-CT in measuring trabecular bone microarchitectural parameters using micro-CT as a reference. Sixteen cadaveric distal tibial epiphyses were enrolled in this pre-clinical study. Images were acquired with HR-CT (i.e., 0.5 mm slice thickness/512² matrix) and SHR-CT (i.e., 0.25 mm slice thickness and 1024² matrix) with and without deep learning reconstruction (DLR) and UHR-CT (i.e., 0.25 mm slice thickness/2048² matrix) without DLR. Trabecular bone parameters were compared. Trabecular thickness was closest with UHR-CT but remained 1.37 times that of micro-CT (P < 0.001). With SHR-CT without and with DLR, it was 1.75 and 1.79 times that of micro-CT, respectively (P < 0.001), and 3.58 and 3.68 times that of micro-CT with HR-CT without and with DLR, respectively (P < 0.001). Trabecular separation was 0.7 times that of micro-CT with UHR-CT (P < 0.001), 0.93 and 0.94 times that of micro-CT with SHR-CT without and with DLR (P = 0.36 and 0.79, respectively), and 1.52 and 1.36 times that of micro-CT with HR-CT without and with DLR (P < 0.001). Bone volume/total volume was overestimated (i.e., 1.66 to 1.92 times that of micro-CT) by all techniques (P < 0.001). However, HR-CT values were superior to UHR-CT values (P = 0.03 and 0.01, without and with DLR, respectively). UHR and SHR-CT were the closest techniques to micro-CT and surpassed HR-CT.

Medical image analysis using deep learning algorithms has become a basis of modern healthcare, enabling early detection, diagnosis, treatment planning, and disease monitoring. However, sharing sensitive raw medical data with third parties for analysis raises significant privacy concerns. This paper presents a privacy-preserving machine learning (PPML) framework using a Fully Connected Neural Network (FCNN) for secure medical image analysis using the MedMNIST dataset. The proposed PPML framework leverages a torus-based fully homomorphic encryption (TFHE) to ensure data privacy during inference, maintain patient confidentiality, and ensure compliance with privacy regulations. The FCNN model is trained in a plaintext environment for FHE compatibility using Quantization-Aware Training to optimize weights and activations. The quantized FCNN model is then validated under FHE constraints through simulation and compiled into an FHE-compatible circuit for encrypted inference on sensitive data. The proposed framework is evaluated on the MedMNIST datasets to assess its accuracy and inference time in both plaintext and encrypted environments. Experimental results reveal that the PPML framework achieves a prediction accuracy of 88.2% in the plaintext setting and 87.5% during encrypted inference, with an average inference time of 150 milliseconds per image. This shows that FCNN models paired with TFHE-based encryption achieve high prediction accuracy on MedMNIST datasets with minimal performance degradation compared to unencrypted inference.

Brain tumors (BT) can cause fatal outcomes by affecting body functions, making precise early detection via magnetic resonance imaging (MRI) examinations critical. The complex variations found in cells of BT may pose challenges in identifying the type of tumor and selecting the most suitable treatment strategy, potentially resulting in different assessments by doctors. As a result, in recent years, AI-powered diagnostic systems have been created to accurately and efficiently identify different types of BT using MRI images. Notably, state-of-the-art deep learning architectures, which have demonstrated efficacy in diverse domains, are now being employed effectively for classifying of brain MRI images. This research presents a hybrid model that integrates spatial attention mechanism (SAM) with ConvNeXt to classify three types of BT: meningioma, pituitary, and glioma. The hybrid model integrates ConvNeXt to enhance the receptive field, capturing information from a broader spatial context, crucial for recognizing tumor patterns spanning multiple pixels. SAM is applied after ConvNeXt, enabling the network to selectively focus on informative regions, thereby improving the model's ability to distinguish BT types and capture complex spatial relationships. Tested on BSF and Figshare datasets, the proposed model achieves a remarkable accuracy of 99.39% and 98.86%, respectively, outperforming the results of recent studies by achieving these results in fewer training periods. This hybrid model marks a major step forward in the automatic classification of BT, demonstrating superior performance in accuracy with efficient training.

The purpose of this study was to create and validate an ultrasound-based graph convolutional network (US-based GCN) model for the prediction of axillary lymph node metastasis (ALNM) in patients with breast cancer. A total of 820 eligible patients with breast cancer who underwent preoperative breast ultrasonography (US) between April 2016 and June 2022 were retrospectively enrolled. The training cohort consisted of 621 patients, whereas validation cohort 1 included 112 patients, and validation cohort 2 included 87 patients. A US-based GCN model was built using US deep learning features. In validation cohort 1, the US-based GCN model performed satisfactorily, with an AUC of 0.88 and an accuracy of 0.76. In validation cohort 2, the US-based GCN model performed satisfactorily, with an AUC of 0.84 and an accuracy of 0.75. This approach has the potential to help guide optimal ALNM management in breast cancer patients, particularly by preventing overtreatment. In conclusion, we developed a US-based GCN model to assess the ALN status of breast cancer patients prior to surgery. The US-based GCN model can provide a possible noninvasive method for detecting ALNM and aid in clinical decision-making. High-level evidence for clinical use in later studies is anticipated to be obtained through prospective studies.

The advent of anti-amyloid therapies (AATs) for Alzheimer's disease (AD) has elevated the importance of MRI surveillance for amyloidrelated imaging abnormalities (ARIA) such as microhemorrhages and siderosis (ARIA-H) and edema (ARIA-E). We report a literature review and early quality assurance experience with an FDA-cleared assistive AI tool intended for detection of ARIA in MRI clinical workflows. The AI system improved sensitivity for detection of subtle ARIA-E and ARIA-H lesions but at the cost of a reduction in specificity. We propose a tiered workflow combining protocol harmonization and expert interpretation with AI overlay review. AI-assisted ARIA detection is a paradigm shift that offers great promise to enhance patient safety as disease-modifying therapies for AD gain broader clinical use; however, some pitfalls need to be considered.ABBREVIATIONS: AAT＝ anti-amyloid therapy; ARIA＝ amyloid-related imaging abnormalities, ARIA-H = amyloid-related imaging abnormality-hemorrhage, ARIA-E = amyloid-related imaging abnormality-edema.

Recent prospective studies have shown that AI may be integrated in double-reader settings to increase cancer detection. The ScreenTrustCAD study was conducted at the breast radiology department at the Capio S:t Göran Hospital where AI is now implemented in clinical practice. This study reports on how the hospital prepared by exploring risks from an enterprise risk management perspective, i.e., applying a holistic and proactive perspective, and developed risk mitigation actions. The study was conducted as an integral part of the preparations before implementing AI in a breast imaging department. Collaborative ideation sessions were conducted with personnel at the hospital, either directly or indirectly involved with AI, to identify risks. Two external experts with competencies in cybersecurity, machine learning, and the ethical aspects of AI, were interviewed as a complement. The risks identified were analyzed according to an Enterprise Risk Management framework, adopted for healthcare, that assumes risks to be emerging from eight different domains. Finally, appropriate risk mitigation actions were identified and discussed. Twenty-three risks were identified covering seven of eight risk domains, in turn generating 51 suggested risk mitigation actions. Not only does the study indicate the emergence of patient safety risks, but it also shows that there are operational, strategic, financial, human capital, legal, and technological risks. The risks with most suggested mitigation actions were ‘Radiographers unable to answer difficult questions from patients’, ‘Increased risk that patient-reported symptoms are missed by the single radiologist’, ‘Increased pressure on the single reader knowing they are the only radiologist to catch a mistake by AI’, and ‘The performance of the AI algorithm might deteriorate’. Before a clinical integration of AI, hospitals should expand, identify, and address risks beyond immediate patient safety by applying comprehensive and proactive risk management. The online version contains supplementary material available at 10.1186/s12913-025-13176-9.

Automated cardiac interpretation in resource-constrained settings (RCS) is often hindered by poor-quality echocardiographic imaging, limiting the effectiveness of downstream diagnostic models. While super-resolution (SR) techniques have shown promise in enhancing magnetic resonance imaging (MRI) and computed tomography (CT) scans, their application to echocardiography-a widely accessible but noise-prone modality-remains underexplored. In this work, we investigate the potential of deep learning-based SR to improve classification accuracy on low-quality 2D echocardiograms. Using the publicly available CAMUS dataset, we stratify samples by image quality and evaluate two clinically relevant tasks of varying complexity: a relatively simple Two-Chamber vs. Four-Chamber (2CH vs. 4CH) view classification and a more complex End-Diastole vs. End-Systole (ED vs. ES) phase classification. We apply two widely used SR models-Super-Resolution Generative Adversarial Network (SRGAN) and Super-Resolution Residual Network (SRResNet), to enhance poor-quality images and observe significant gains in performance metric-particularly with SRResNet, which also offers computational efficiency. Our findings demonstrate that SR can effectively recover diagnostic value in degraded echo scans, making it a viable tool for AI-assisted care in RCS, achieving more with less.

Safety-critical applications, such as autonomous driving and medical image analysis, require extensive multimodal data for rigorous testing. Synthetic data methods are gaining prominence due to the cost and complexity of gathering real-world data, but they demand a high degree of realism and controllability to be useful. This work introduces two novel methods for synthetic data generation in autonomous driving and medical image analysis, namely MObI and AnydoorMed, respectively. MObI is a first-of-its-kind framework for Multimodal Object Inpainting that leverages a diffusion model to produce realistic and controllable object inpaintings across perceptual modalities, demonstrated simultaneously for camera and lidar. Given a single reference RGB image, MObI enables seamless object insertion into existing multimodal scenes at a specified 3D location, guided by a bounding box, while maintaining semantic consistency and multimodal coherence. Unlike traditional inpainting methods that rely solely on edit masks, this approach uses 3D bounding box conditioning to ensure accurate spatial positioning and realistic scaling. AnydoorMed extends this paradigm to the medical imaging domain, focusing on reference-guided inpainting for mammography scans. It leverages a diffusion-based model to inpaint anomalies with impressive detail preservation, maintaining the reference anomaly's structural integrity while semantically blending it with the surrounding tissue. Together, these methods demonstrate that foundation models for reference-guided inpainting in natural images can be readily adapted to diverse perceptual modalities, paving the way for the next generation of systems capable of constructing highly realistic, controllable and multimodal counterfactual scenarios.

This study aims to enhance the accuracy and efficiency of MRI-based brain tumor diagnosis by leveraging deep learning (DL) techniques applied to multichannel MRI inputs. MRI data were collected from 203 subjects, including 100 normal cases and 103 cases with 13 distinct brain tumor types. Non-contrast T1-weighted (T1w) and T2-weighted (T2w) images were combined with their average to form RGB three-channel inputs, enriching the representation for model training. Several convolutional neural network (CNN) architectures were evaluated for tumor classification, while fully convolutional networks (FCNs) were employed for tumor segmentation. Standard preprocessing, normalization, and training procedures were rigorously followed. The RGB fusion of T1w, T2w, and their average significantly enhanced model performance. The classification task achieved a top accuracy of 98.3% using the Darknet53 model, and segmentation attained a mean Dice score of 0.937 with ResNet50. These results demonstrate the effectiveness of multichannel input fusion and model selection in improving brain tumor analysis. While not yet integrated into clinical workflows, this approach holds promise for future development of DL-assisted decision-support tools in radiological practice.

This study aims at establishing a validation framework for an explainable radiomics-based model, specifically targeting classification of histopathological subtypes in non-small cell lung cancer (NSCLC) patients. We developed an explainable radiomics pipeline using open-access CT images from the cancer imaging archive (TCIA). Our approach incorporates three key prongs: SHAP-based feature selection for explainability within the radiomics pipeline, a technical validation of the explainable technique using high energy physics (HEP) data, and a biological validation using RNA-sequencing data and clinical observations. Our radiomic model achieved an accuracy of 0.84 in the classification of the histological subtype. The technical validation performed on the HEP domain over 150 numerically equivalent datasets, maintaining consistent sample size and class imbalance, confirmed the reliability of SHAP-based input features. Biological analysis found significant correlations between gene expression and CT-based radiomic features. In particular, gene MUC21 achieved the highest correlation with the radiomic feature describing the10th percentile of voxel intensities (r = 0.46, p < 0.05). This study presents a validation framework for explainable CT-based radiomics in lung cancer, combining HEP-driven technical validation with biological validation to enhance interpretability, reliability, and clinical relevance of XAI models.