Evaluate an Artificial Intelligence (AI) system in breast screening through stratified results across age, breast density, ethnicity and screening centres, from different UK regions. A large-scale retrospective study evaluating two variations of using AI as an independent second reader in double reading was executed. Stratifications were conducted for clinical and operational metrics. Data from 306 839 mammography cases screened between 2017 and 2021 were used and included three different UK regions.The impact on safety and effectiveness was assessed using clinical metrics: cancer detection rate and positive predictive value, stratified according to age, breast density and ethnicity. Operational impact was assessed through reading workload and recall rate, measured overall and per centre.Non-inferiority was tested for AI workflows compared with human double reading, and when passed, superiority was tested. AI interval cancer (IC) flag rate was assessed to estimate additional cancer detection opportunity with AI that cannot be assessed retrospectively. The AI workflows passed non-inferiority or superiority tests for every metric across all subgroups, with workload savings between 38.3% and 43.7%. The AI standalone flagged 41.2% of ICs overall, ranging between 33.3% and 46.8% across subgroups, with the highest detection rate for dense breasts. Human double reading and AI workflows showed the same performance disparities across subgroups. The AI integrations maintained or improved performance at all metrics for all subgroups while achieving significant workload reduction. Moreover, complementing these integrations with AI as an additional reader can improve cancer detection. The granularity of assessment showed that screening with the AI-system integrations was as safe as standard double reading across heterogeneous populations.

Positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (18F-FDG PET-CT) is a multi-modality medical imaging technique widely used for screening and diagnosis of lesions and tumors, in which, CT can provide detailed anatomical structures, while PET can show metabolic activities. Nevertheless, it has disadvantages such as long scanning time, high cost, and relatively high radiation doses.

Purpose: We propose a deep learning model for the whole-body CT-to-PET synthesis task, generating high-quality synthetic PET images that are comparable to real ones in both clinical relevance and diagnostic value.

Material: We collect 102 pairs of 3D CT and PET scans, which are sliced into 27,240 pairs of 2D CT and PET images ( training: 21,855 pairs, validation: 2,810, testing: 2,575 pairs).

Methods: We propose a Transformer-enhanced Generative Adversarial Network (GAN) for whole-body CT-to-PET synthesis task. The CPGAN model uses residual blocks and Fully Connected Transformer Residual (FCTR) blocks to capture both local features and global contextual information. A customized loss function incorporating structural consistency is designed to improve the quality of synthesized PET images.

Results: Both quantitative and qualitative evaluation results demonstrate effectiveness of the CPGAN model. The mean and standard variance of NRMSE,PSNR and SSIM values on test set are (16.90 ± 12.27) × 10-4, 28.71 ± 2.67 and 0.926 ± 0.033, respectively, outperforming other seven state-of-the-art models. Three radiologists independently and blindly evaluated and gave subjective scores to 100 randomly chosen PET images (50 real and 50 synthetic). By Wilcoxon signed rank test, there are no statistical differences between the synthetic PET images and the real ones.

Conclusions: Despite the inherent limitations of CT images to directly reflect biological information of metabolic tissues, CPGAN model effectively synthesizes satisfying PET images from CT scans, which has potential in reducing the reliance on actual PET-CT scans.

Introduction: Timely identification of intracranial hemorrhage (ICH) subtypes on non-contrast computed tomography is critical for prognosis prediction and therapeutic decision-making, yet remains challenging due to low contrast and blurring boundaries. This study evaluates the performance of zero-shot multi-modal large language models (MLLMs) compared to traditional deep learning methods in ICH binary classification and subtyping. Methods: We utilized a dataset provided by RSNA, comprising 192 NCCT volumes. The study compares various MLLMs, including GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet V2, with conventional deep learning models, including ResNet50 and Vision Transformer. Carefully crafted prompts were used to guide MLLMs in tasks such as ICH presence, subtype classification, localization, and volume estimation. Results: The results indicate that in the ICH binary classification task, traditional deep learning models outperform MLLMs comprehensively. For subtype classification, MLLMs also exhibit inferior performance compared to traditional deep learning models, with Gemini 2.0 Flash achieving an macro-averaged precision of 0.41 and a macro-averaged F1 score of 0.31. Conclusion: While MLLMs excel in interactive capabilities, their overall accuracy in ICH subtyping is inferior to deep networks. However, MLLMs enhance interpretability through language interactions, indicating potential in medical imaging analysis. Future efforts will focus on model refinement and developing more precise MLLMs to improve performance in three-dimensional medical image processing.

Currently, cervical anesthesia is performed using three main approaches: superficial cervical plexus block, deep cervical plexus block, and intermediate plexus nerve block. However, each technique carries inherent risks and demands significant clinical expertise. Ultrasound imaging, known for its real-time visualization capabilities and accessibility, is widely used in both diagnostic and interventional procedures. Nevertheless, accurate segmentation of small and irregularly shaped structures such as the cervical and brachial plexuses remains challenging due to image noise, complex anatomical morphology, and limited annotated training data. This study introduces DEMAC-Net-a dual-encoder, multiattention collaborative network-to significantly improve the segmentation accuracy of these neural structures. By precisely identifying the cervical nerve pathway (CNP) and adjacent anatomical tissues, DEMAC-Net aims to assist clinicians, especially those less experienced, in effectively guiding anesthesia procedures and accurately identifying optimal needle insertion points. Consequently, this improvement is expected to enhance clinical safety, reduce procedural risks, and streamline decision-making efficiency during ultrasound-guided regional anesthesia. DEMAC-Net combines a dual-encoder architecture with the Spatial Understanding Convolution Kernel (SUCK) and the Spatial-Channel Attention Module (SCAM) to extract multi-scale features effectively. Additionally, a Global Attention Gate (GAG) and inter-layer fusion modules refine relevant features while suppressing noise. A novel dataset, Neck Ultrasound Dataset (NUSD), was introduced, containing 1,500 annotated ultrasound images across seven anatomical regions. Extensive experiments were conducted on both NUSD and the BUSI public dataset, comparing DEMAC-Net to state-of-the-art models using metrics such as Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). On the NUSD dataset, DEMAC-Net achieved a mean DSC of 93.3%, outperforming existing models. For external validation on the BUSI dataset, it demonstrated superior generalization, achieving a DSC of 87.2% and a mean IoU of 77.4%, surpassing other advanced methods. Notably, DEMAC-Net displayed consistent segmentation stability across all tested structures. The proposed DEMAC-Net significantly improves segmentation accuracy for small nerves and complex anatomical structures in ultrasound images, outperforming existing methods in terms of accuracy and computational efficiency. This framework holds great potential for enhancing ultrasound-guided procedures, such as peripheral nerve blocks, by providing more precise anatomical localization, ultimately improving clinical outcomes.

Out-of-distribution (OOD) detection is essential for ensuring the reliability of deep learning models in medical imaging applications. This work is motivated by the observation that class activation maps (CAMs) for in-distribution (ID) data typically emphasize regions that are highly relevant to the model's predictions, whereas OOD data often lacks such focused activations. By masking input images with inverted CAMs, the feature representations of ID data undergo more substantial changes compared to those of OOD data, offering a robust criterion for differentiation. In this paper, we introduce a novel unsupervised OOD detection framework, Multi-Exit Class Activation Map (MECAM), which leverages multi-exit CAMs and feature masking. By utilizing mult-exit networks that combine CAMs from varying resolutions and depths, our method captures both global and local feature representations, thereby enhancing the robustness of OOD detection. We evaluate MECAM on multiple ID datasets, including ISIC19 and PathMNIST, and test its performance against three medical OOD datasets, RSNA Pneumonia, COVID-19, and HeadCT, and one natural image OOD dataset, iSUN. Comprehensive comparisons with state-of-the-art OOD detection methods validate the effectiveness of our approach. Our findings emphasize the potential of multi-exit networks and feature masking for advancing unsupervised OOD detection in medical imaging, paving the way for more reliable and interpretable models in clinical practice.

Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models.

Glioma is one of the most lethal types of brain tumors, accounting for approximately 33% of all diagnosed brain tumor cases. Accurate segmentation and classification are crucial for precise glioma characterization, emphasizing early detection of malignancy, effective treatment planning, and prevention of tumor progression. Magnetic Resonance Imaging (MRI) serves as a non-invasive imaging modality that allows detailed examination of gliomas without exposure to ionizing radiation. However, manual analysis of MRI scans is impractical, time-consuming, subjective, and requires specialized expertise from radiologists. To address this, computer-aided diagnosis (CAD) systems have greatly evolved as powerful tools to support neuro-oncologists in the brain cancer screening process. In this work, we present a glioma classification framework based on 3D multi-modal MRI segmentation using the CNN models SegResNet and Swin UNETR which incorporates transformer mechanisms for enhancing segmentation performance. MRI images undergo preprocessing with a Gaussian filter and skull stripping to improve tissue localization. Key textural features are then extracted from segmented tumor regions using Gabor Transform, Discrete Wavelet Transform (DWT), and deep features from ResNet50. These features are fused, normalized, and classified using a Support Vector Machine (SVM) to distinguish between Low-Grade Glioma (LGG) and High-Grade Glioma (HGG). Extensive experiments on benchmark datasets, including BRATS2020 and BRATS2023, demonstrate the effectiveness of the proposed approach. Our model achieved Dice scores of 0.815 for Tumor Core, 0.909 for Whole Tumor, and 0.829 for Enhancing Tumor. Concerning classification, the framework attained 97% accuracy, 94% precision, 96% recall, and a 95% F1-score. These results highlight the potential of the proposed framework to provide reliable support for radiologists in the early detection and classification of gliomas.

Pancreatic cystic neoplasms (PCNs) are a complex group of lesions with a spectrum of malignancy. Accurate differentiation of PCN types is crucial for patient management, as misdiagnosis can result in unnecessary surgeries or treatment delays, affecting the quality of life. The significance of developing a non-invasive, accurate diagnostic model is underscored by the need to improve patient outcomes and reduce the impact of these conditions. We developed a machine learning model capable of accurately identifying different types of PCNs in a non-invasive manner, by using a dataset comprising 449 MRI and 568 CT scans from adult patients, spanning from 2009 to 2022. The study's results indicate that our multimodal machine learning algorithm, which integrates both clinical and imaging data, significantly outperforms single-source data algorithms. Specifically, it demonstrated state-of-the-art performance in classifying PCN types, achieving an average accuracy of 91.2%, precision of 91.7%, sensitivity of 88.9%, and specificity of 96.5%. Remarkably, for patients with mucinous cystic neoplasms (MCNs), regardless of undergoing MRI or CT imaging, the model achieved a 100% prediction accuracy rate. It indicates that our non-invasive multimodal machine learning model offers strong support for the early screening of MCNs, and represents a significant advancement in PCN diagnosis for improving clinical practice and patient outcomes. We also achieved the best results on an additional pancreatic cancer dataset, which further proves the generality of our model.

Accurate multi-modal medical image translation requires ha-rmonizing global anatomical semantics and local structural fidelity, a challenge complicated by intermodality information loss and structural distortion. We propose ABS-Mamba, a novel architecture integrating the Segment Anything Model 2 (SAM2) for organ-aware semantic representation, specialized convolutional neural networks (CNNs) for preserving modality-specific edge and texture details, and Mamba's selective state-space modeling for efficient long- and short-range feature dependencies. Structurally, our dual-resolution framework leverages SAM2's image encoder to capture organ-scale semantics from high-resolution inputs, while a parallel CNNs branch extracts fine-grained local features. The Robust Feature Fusion Network (RFFN) integrates these epresentations, and the Bidirectional Mamba Residual Network (BMRN) models spatial dependencies using spiral scanning and bidirectional state-space dynamics. A three-stage skip fusion decoder enhances edge and texture fidelity. We employ Efficient Low-Rank Adaptation (LoRA+) fine-tuning to enable precise domain specialization while maintaining the foundational capabilities of the pre-trained components. Extensive experimental validation on the SynthRAD2023 and BraTS2019 datasets demonstrates that ABS-Mamba outperforms state-of-the-art methods, delivering high-fidelity cross-modal synthesis that preserves anatomical semantics and structural details to enhance diagnostic accuracy in clinical applications. The code is available at https://github.com/gatina-yone/ABS-Mamba

PurposeAccurate cancer subtyping is crucial for effective treatment; however, it presents challenges due to overlapping morphology and variability among pathologists. Although deep learning (DL) methods have shown potential, their application to gigapixel whole slide images (WSIs) is often hindered by high computational demands and the need for efficient, context-aware feature aggregation. This study introduces LiteMIL, a computationally efficient transformer-based multiple instance learning (MIL) network combined with Phikon, a pathology-tuned self-supervised feature extractor, for robust and scalable cancer subtyping on WSIs. MethodsInitially, patches were extracted from TCGA-THYM dataset (242 WSIs, six subtypes) and subsequently fed in real-time to Phikon for feature extraction. To train MILs, features were arranged into uniform bags using a chunking strategy that maintains tissue context while increasing training data. LiteMIL utilizes a learnable query vector within an optimized multi-head attention module for effective feature aggregation. The models performance was evaluated against established MIL methods on the Thymic Dataset and three additional TCGA datasets (breast, lung, and kidney cancer). ResultsLiteMIL achieved 0.89 {+/-} 0.01 F1 score and 0.99 AUC on Thymic dataset, outperforming other MILs. LiteMIL demonstrated strong generalizability across the external datasets, scoring the best on breast and kidney cancer datasets. Compared to TransMIL, LiteMIL significantly reduces training time and GPU memory usage. Ablation studies confirmed the critical role of the learnable query and layer normalization in enhancing performance and stability. ConclusionLiteMIL offers a resource-efficient, robust solution. Its streamlined architecture, combined with the compact Phikon features, makes it suitable for integrating into routine histopathological workflows, particularly in resource-limited settings.