The growing integration of vision-language models (VLMs) in medical applications offers promising support for diagnostic reasoning. However, current medical VLMs often face limitations in generalization, transparency, and computational efficiency-barriers that hinder deployment in real-world, resource-constrained settings. To address these challenges, we propose a Reasoning-Aware Reinforcement Learning framework, \textbf{RARL}, that enhances the reasoning capabilities of medical VLMs while remaining efficient and adaptable to low-resource environments. Our approach fine-tunes a lightweight base model, Qwen2-VL-2B-Instruct, using Low-Rank Adaptation and custom reward functions that jointly consider diagnostic accuracy and reasoning quality. Training is performed on a single NVIDIA A100-PCIE-40GB GPU, demonstrating the feasibility of deploying such models in constrained environments. We evaluate the model using an LLM-as-judge framework that scores both correctness and explanation quality. Experimental results show that RARL significantly improves VLM performance in medical image analysis and clinical reasoning, outperforming supervised fine-tuning on reasoning-focused tasks by approximately 7.78%, while requiring fewer computational resources. Additionally, we demonstrate the generalization capabilities of our approach on unseen datasets, achieving around 27% improved performance compared to supervised fine-tuning and about 4% over traditional RL fine-tuning. Our experiments also illustrate that diversity prompting during training and reasoning prompting during inference are crucial for enhancing VLM performance. Our findings highlight the potential of reasoning-guided learning and reasoning prompting to steer medical VLMs toward more transparent, accurate, and resource-efficient clinical decision-making. Code and data are publicly available.

The accurate and timely diagnosis of brain tumors is of paramount clinical significance for effective treatment planning and improved patient outcomes. While deep learning has advanced medical image analysis, concurrently achieving high classification accuracy, robust generalization, and computational efficiency remains a formidable challenge. This is often due to the difficulty in optimally capturing both fine-grained local tumor features and their broader global contextual cues without incurring substantial computational costs. This paper introduces NeXtBrain, a novel hybrid architecture meticulously designed to overcome these limitations. NeXtBrain's core innovations, the NeXt Convolutional Block (NCB) and the NeXt Transformer Block (NTB), synergistically enhance feature learning: NCB leverages Multi-Head Convolutional Attention and a SwiGLU-based MLP to precisely extract subtle local tumor morphologies and detailed textures, while NTB integrates self-attention with convolutional attention and a SwiGLU MLP to effectively model long-range spatial dependencies and global contextual relationships, crucial for differentiating complex tumor characteristics. Evaluated on two publicly available benchmark datasets, Figshare and Kaggle, NeXtBrain was rigorously compared against 17 state-of-the-art (SOTA) models. On Figshare, it achieved 99.78 % accuracy and a 99.77 % F1-score. On Kaggle, it attained 99.78 % accuracy and a 99.81 % F1-score, surpassing leading SOTA ViT, CNN, and hybrid models. Critically, NeXtBrain demonstrates exceptional computational efficiency, achieving these SOTA results with only 23.91 million parameters, requiring just 10.32 GFLOPs, and exhibiting a rapid inference time of 0.007 ms. This efficiency allows it to outperform significantly larger models such as DeiT3-Base with 85.82 M parameters, Swin-Base with 86.75 M parameters in both accuracy and computational demand.

Diffusion-weighted imaging (DWI) is widely applied in tumor diagnosis by measuring the diffusion of water molecules. To increase the sensitivity to tumor identification, faithful high b-value DWI images are expected by setting a stronger strength of gradient field in magnetic resonance imaging (MRI). However, high b-value DWI images are heavily affected by reduced signal-to-noise ratio due to the exponential decay of signal intensity. Thus, removing noise becomes important for high b-value DWI images. Here, we propose a Physics-Informed neural Network for high b-value DWI images Denoising (PIND) by leveraging information from physics-informed loss and prior information from low b-value DWI images with high signal-to-noise ratio. Experiments are conducted on a prostate DWI dataset that has 125 subjects. Compared with the original noisy images, PIND improves the peak signal-to-noise ratio from 31.25 dB to 36.28 dB, and structural similarity index measure from 0.77 to 0.92. Our schemes can save 83% data acquisition time since fewer averages of high b-value DWI images need to be acquired, while maintaining 98% accuracy of the apparent diffusion coefficient value, suggesting its potential effectiveness in preserving essential diffusion characteristics. Reader study by 4 radiologists (3, 6, 13, and 18 years of experience) indicates PIND's promising performance on overall quality, signal-to-noise ratio, artifact suppression, and lesion conspicuity, showing potential for improving clinical DWI applications.

This systematic review and meta-analysis aimed to assess the diagnostic accuracy of radiomics in risk stratification of gastrointestinal stromal tumors (GISTs). It focused on evaluating radiomic models as a non-invasive tool in clinical practice. A comprehensive search was conducted across PubMed, Web of Science, EMBASE, Scopus, and Cochrane Library up to May 17, 2025. Studies involving preoperative imaging and radiomics-based risk stratification of GISTs were included. Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool and Radiomics Quality Score (RQS). Pooled sensitivity, specificity, and area under the curve (AUC) were calculated using bivariate random-effects models. Meta-regression and subgroup analyses were performed to explore heterogeneity. A total of 29 studies were included, with 22 (76 %) based on computed tomography scans, while 2 (7 %) were based on endoscopic ultrasound, 3 (10 %) on magnetic resonance imaging, and 2 (7 %) on ultrasound. Of these, 18 studies provided sufficient data for meta-analysis. Pooled sensitivity, specificity, and AUC for radiomics-based GIST risk stratification were 0.84, 0.86, and 0.90 for training cohorts, and 0.84, 0.80, and 0.89 for validation cohorts. QUADAS-2 indicated some bias due to insufficient pre-specified thresholds. The mean RQS score was 13.14 ± 3.19. Radiomics holds promise for non-invasive GIST risk stratification, particularly with advanced imaging techniques. However, radiomic models are still in the early stages of clinical adoption. Further research is needed to improve diagnostic accuracy and validate their role alongside conventional methods like biopsy or surgery.

Transcatheter heart valve (THV) durability is a critical concern, and its deformation may influence long-term performance. Current assessments rely on CT-based single-phase measurements and require a tedious analysis process, potentially overlooking deformation dynamics throughout the cardiac cycle. A fully automated artificial intelligence-based method was developed to assess THV deformation in post-transcatheter aortic valve implantation (TAVI) 4DCT scans. The approach involves segmenting the THV, extracting orthogonal cross-sections along its axis, fitting ellipses to these cross-sections, and computing eccentricity to analyze deformation over the cardiac cycle. The method was evaluated in 21 TAVI patients with different self-expandable THV models, using one post-TAVI 4DCT series per patient. The THV inflow level exhibited the greatest eccentricity variations (0.35-0.69 among patients with the same THV model at end-diastole). Additionally, eccentricity varied throughout the cardiac cycle (0.23-0.57), highlighting the limitations of single-phase assessments in characterizing THV deformation. This method enables automated THV deformation assessment based on cross-sectional eccentricity. Significant differences were observed at the inflow level, and cyclic variations suggest that full cardiac cycle analysis provides a more comprehensive evaluation than single-phase measurements. This approach may aid in optimizing THV durability and function while preventing related complications.

Artificial intelligence (AI) is rapidly transforming healthcare, but its benefits are not reaching all patients equally. Children remain overlooked with only 17% of FDA-approved medical AI devices labeled for pediatric use. In this work, we demonstrate that this exclusion may stem from a fundamental data gap. Our systematic review of 181 public medical imaging datasets reveals that children represent just under 1% of available data, while the majority of machine learning imaging conference papers we surveyed utilized publicly available data for methods development. Much like systematic biases of other kinds in model development, past studies have demonstrated the manner in which pediatric representation in data used for models intended for the pediatric population is essential for model performance in that population. We add to these findings, showing that adult-trained chest radiograph models exhibit significant age bias when applied to pediatric populations, with higher false positive rates in younger children. This work underscores the urgent need for increased pediatric representation in publicly accessible medical datasets. We provide actionable recommendations for researchers, policymakers, and data curators to address this age equity gap and ensure AI benefits patients of all ages. 1-2 sentence summaryOur analysis reveals a critical healthcare age disparity: children represent less than 1% of public medical imaging datasets. This gap in representation leads to biased predictions across medical image foundation models, with the youngest patients facing the highest risk of misdiagnosis.

BackgroundAccurate histological grading of oral squamous cell carcinoma (OSCC) is critical for prognosis and treatment planning. Current methods lack automation for OSCC detection, subtyping, and differentiation from high-risk pre-malignant conditions like oral submucous fibrosis (OSMF). Further, analysis of whole-slide image (WSI) analysis is time-consuming and variable, limiting consistency. We present a clinically relevant deep learning framework that leverages weakly supervised learning and attention-based multiple instance learning (MIL) to enable automated OSCC grading and early prediction of malignant transformation from OSMF. MethodsWe conducted a multi-institutional retrospective cohort study using a curated dataset of 1,925 whole-slide images (WSIs), including 1,586 OSCC cases stratified into well-, moderately-, and poorly-differentiated subtypes (WD, MD, and PD), 128 normal controls, and 211 OSMF and OSMF with OSCC cases. We developed a two-stage deep learning pipeline named OralPatho. In stage one, an attention-based multiple instance learning (MIL) model was trained to perform binary classification (normal vs OSCC). In stage two, a gated attention mechanism with top-K patch selection was employed to classify the OSCC subtypes. Model performance was assessed using stratified 3-fold cross-validation and external validation on an independent dataset. FindingsThe binary classifier demonstrated robust performance with a mean F1-score exceeding 0.93 across all validation folds. The multiclass model achieved consistent macro-F1 scores of 0.72, 0.70, and 0.68, along with AUCs of 0.79 for WD, 0.71 for MD, and 0.61 for PD OSCC subtypes. Model generalizability was validated using an independent external dataset. Attention maps reliably highlighted clinically relevant histological features, supporting the systems interpretability and diagnostic alignment with expert pathological assessment. InterpretationThis study demonstrates the feasibility of attention-based, weakly supervised learning for accurate OSCC grading from whole-slide images. OralPatho combines high diagnostic performance with real-time interpretability, making it a scalable solution for both advanced pathology labs and resource-limited settings.

Chronic Obstructive Pulmonary Disease (COPD) is a significant public health challenge globally, with Asia facing unique burdens due to varying demographics, healthcare access, and socioeconomic conditions. Recognizing the limitations of pulmonary function tests (PFTs) in early detection and comprehensive evaluation, the Asian Society of Thoracic Radiology (ASTR) presents this recommendations to guide the use of chest computed tomography (CT) in COPD diagnosis and management. This document consolidates evidence from an extensive literature review and surveys across Asia, highlighting the need for standardized CT protocols and practices. Key recommendations include adopting low-dose paired respiratory phase CT scans, utilizing qualitative and quantitative assessments for airway, vascular, and parenchymal evaluation, and emphasizing structured reporting to enhance clinical decision-making. Advanced technologies, including dual-energy CT and artificial intelligence, are proposed to refine diagnosis, monitor disease progression, and guide personalized interventions. These recommendations aim to improve the early detection of COPD, address its heterogeneity, and reduce its socioeconomic impact by establishing consistent and effective imaging practices across the region. This recommendations underscore the pivotal role of chest CT in advancing COPD care in Asia, providing a foundation for future research and practice refinement.

Photon-counting detector CT (PCD-CT) represents a significant advancement in medical imaging, particularly for musculoskeletal (MSK) applications. Its primary innovation lies in enhanced spatial resolution, which facilitates improved detection of small anatomical structures such as trabecular bone, osteophytes, and subchondral cysts. PCD-CT enables high-quality imaging with reduced radiation doses, making it especially beneficial for populations requiring frequent imaging, such as pediatric patients and individuals with multiple myeloma. Additionally, PCD-CT supports advanced applications like bone quality assessment, which correlates well with gold-standard tests, and can aid in diagnosing osteoporosis and assessing fracture risk. Techniques such as spectral shaping and virtual monoenergetic imaging further optimize the technology, minimizing artifacts and enhancing material decomposition. These capabilities extend to conditions like gout and hematologic malignancies, offering improved detection and assessment. The integration of artificial intelligence could enhance PCD-CT's performance by reducing image noise and improving quantitative assessments. Ultimately, PCD-CT's superior resolution, reduced dose protocols, and multi-energy imaging capabilities will likely have a transformative impact on MSK imaging, improving diagnostic accuracy, patient care, and clinical outcomes.

This study aimed to develop and evaluate a graphical user interface (GUI) for the automated segmentation of the hypothalamus and intracranial volume (ICV) in brain MRI scans. The interface was designed to facilitate efficient and accurate segmentation for research applications, with a focus on accessibility and ease of use for end-users. We developed a web-based GUI using the Gradio library integrating deep learning-based segmentation models trained on annotated brain MRI scans. The model utilizes a U-Net architecture to delineate the hypothalamus and ICV. The GUI allows users to upload high-resolution MRI scans, visualize the segmentation results, calculate hypothalamic volume and ICV, and manually correct individual segmentation results. To ensure widespread accessibility, we deployed the interface using ngrok, allowing users to access the tool via a shared link. As an example for the universality of the approach, the tool was applied to a group of 90 patients with Parkinson's disease (PD) and 39 controls. The GUI demonstrated high usability and efficiency in segmenting the hypothalamus and the ICV, with no significant difference in normalized hypothalamic volume observed between PD patients and controls, consistent with previously published findings. The average processing time per patient volume was 18 s for the hypothalamus and 44 s for the ICV segmentation on a 6 GB NVidia GeForce GTX 1060 GPU. The ngrok-based deployment allowed for seamless access across different devices and operating systems, with an average connection time of less than 5 s. The developed GUI provides a powerful and accessible tool for applications in neuroimaging. The combination of the intuitive interface, accurate deep learning-based segmentation, and easy deployment via ngrok addresses the need for user-friendly tools in brain MRI analysis. This approach has the potential to streamline workflows in neuroimaging research.