Medical Imagings are considered one of the crucial diagnostic tools for different bones-related diseases, especially bones fractures. This paper investigates the robustness of pre-trained deep learning models for classifying bone fractures in X-ray images and seeks to address global healthcare disparity through the lens of technology. Three deep learning models have been tested under varying simulated equipment quality conditions. ResNet50, VGG16 and EfficientNetv2 are the three pre-trained architectures which are compared. These models were used to perform bone fracture classification as images were progressively degraded using noise. This paper specifically empirically studies how the noise can affect the bone fractures detection and how the pre-trained models performance can be changes due to the noise that affect the quality of the X-ray images. This paper aims to help replicate real world challenges experienced by medical imaging technicians across the world. Thus, this paper establishes a methodological framework for assessing AI model degradation using transfer learning and controlled noise augmentation. The findings provide practical insight into how robust and generalizable different pre-trained deep learning powered computer vision models can be when used in different contexts.

Cognitive impairment is a key contributor to disability and poor outcomes in schizophrenia, yet it is not adequately addressed by currently available treatments. Thus, it is important to search for preventable or treatable risk factors for cognitive impairment. Here, we hypothesized that obesity-related neurostructural alterations will be associated with worse cognitive outcomes in people with first episode of psychosis (FEP). This observational study presents cross-sectional data from the Early-Stage Schizophrenia Outcome project. We acquired T1-weighted 3D MRI scans in 440 participants with FEP at the time of the first hospitalization and in 257 controls. Metabolic assessments included body mass index (BMI), waist-to-hip ratio (WHR), serum concentrations of triglycerides, cholesterol, glucose, insulin, and hs-CRP. We chose machine learning-derived brain age gap estimate (BrainAGE) as our measure of neurostructural changes and assessed attention, working memory and verbal learning using Digit Span and the Auditory Verbal Learning Test. Among obesity/metabolic markers, only WHR significantly predicted both, higher BrainAGE (t(281)=2.53, p=0.012) and worse verbal learning (t(290) = -2.51, P = .026). The association between FEP and verbal learning was partially mediated by BrainAGE (average causal mediated effects, ACME = -0.04 [-0.10, -0.01], P = .022) and the higher BrainAGE in FEP was partially mediated by higher WHR (ACME = 0.08 [0.02, 0.15], P = .006). Central obesity-related brain alterations were linked with worse cognitive performance already early in the course of psychosis. These structure-function links suggest that preventing or treating central obesity could target brain and cognitive impairments in FEP.

The exponential growth of medical imaging has created significant challenges in data storage, transmission, and management for healthcare systems. In this vein, efficient compression becomes increasingly important. Unlike natural image compression, medical image compression prioritizes preserving diagnostic details and structural integrity, imposing stricter quality requirements and demanding fast, memory-efficient algorithms that balance computational complexity with clinically acceptable reconstruction quality. Meanwhile, the medical imaging family includes a plethora of modalities, each possessing different requirements. For example, 2D medical image (e.g., X-rays, histopathological images) compression focuses on exploiting intra-slice spatial redundancy, while volumetric medical image faces require handling intra-slice and inter-slice spatial correlations, and 4D dynamic imaging (e.g., time-series CT/MRI, 4D ultrasound) additionally demands processing temporal correlations between consecutive time frames. Traditional compression methods, grounded in mathematical transforms and information theory principles, provide solid theoretical foundations, predictable performance, and high standardization levels, with extensive validation in clinical environments. In contrast, deep learning-based approaches demonstrate remarkable adaptive learning capabilities and can capture complex statistical characteristics and semantic information within medical images. This comprehensive survey establishes a two-facet taxonomy based on data structure (2D vs 3D/4D) and technical approaches (traditional vs learning-based), thereby systematically presenting the complete technological evolution, analyzing the unique technical challenges, and prospecting future directions in medical image compression.

Radiographic images are a cornerstone of medical diagnostics in orthopaedics, with anatomical landmark detection serving as a crucial intermediate step for information extraction. General-purpose foundational segmentation models, such as SAM (Segment Anything Model), do not support landmark segmentation out of the box and require prompts to function. However, in medical imaging, the prompts for landmarks are highly specific. Since SAM has not been trained to recognize such landmarks, it cannot generate accurate landmark segmentations for diagnostic purposes. Even MedSAM, a medically adapted variant of SAM, has been trained to identify larger anatomical structures, such as organs and their parts, and lacks the fine-grained precision required for orthopaedic pelvic landmarks. To address this limitation, we propose leveraging another general-purpose, non-foundational model: YOLO. YOLO excels in object detection and can provide bounding boxes that serve as input prompts for SAM. While YOLO is efficient at detection, it is significantly outperformed by SAM in segmenting complex structures. In combination, these two models form a reliable pipeline capable of segmenting not only a small pilot set of eight anatomical landmarks but also an expanded set of 72 landmarks and 16 regions with complex outlines, such as the femoral cortical bone and the pelvic inlet. By using YOLO-generated bounding boxes to guide SAM, we trained the hybrid model to accurately segment orthopaedic pelvic radiographs. Our results show that the proposed combination of YOLO and SAM yields excellent performance in detecting anatomical landmarks and intricate outlines in orthopaedic pelvic radiographs.

The Segment Anything Model (SAM) has revolutionized image segmentation through its innovative prompt-based approach, yet the critical role of prompt engineering in its success remains underexplored. This paper presents the first comprehensive survey focusing specifically on prompt engineering techniques for SAM and its variants. We systematically organize and analyze the rapidly growing body of work in this emerging field, covering fundamental methodologies, practical applications, and key challenges. Our review reveals how prompt engineering has evolved from simple geometric inputs to sophisticated multimodal approaches, enabling SAM's adaptation across diverse domains including medical imaging and remote sensing. We identify unique challenges in prompt optimization and discuss promising research directions. This survey fills an important gap in the literature by providing a structured framework for understanding and advancing prompt engineering in foundation models for segmentation.

State space models (SSMs) reduce the quadratic complexity of transformers by leveraging linear recurrence. Recently, VMamba has emerged as a strong SSM-based vision backbone, yet remains bottlenecked by spatial redundancy in its four-directional scan. We propose QuarterMap, a post-training activation pruning method that removes redundant spatial activations before scanning and restores dimensions via nearest-neighbor upsampling. Our method improves throughput without retraining. On ImageNet-1K, QuarterMap achieves up to 11% speedup on VMamba with less than 0.9% accuracy drop, and yields similar gains on ADE20K segmentation. Beyond VMamba, we validate QuarterMap on MedMamba, a domain-specific model that shares the same four-directional scanning structure, where it consistently improves throughput while preserving accuracy across multiple medical imaging tasks. Compared to token merging methods like ToMe, QuarterMap is tailored for SSMs and avoids costly merge-unmerge operations. Our method offers a plug-and-play tool for deployment-time efficiency without compromising transferability.

Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a tendency to generate incorrect responses with high confidence. As clinicians may rely on a model's stated confidence to gauge the reliability of its predictions, it is especially important that when a model expresses high confidence, it is also highly accurate. We introduce Prompt4Trust, the first reinforcement learning (RL) framework for prompt augmentation targeting confidence calibration in MLLMs. A lightweight LLM is trained to produce context-aware auxiliary prompts that guide a downstream task MLLM to generate responses in which the expressed confidence more accurately reflects predictive accuracy. Unlike conventional calibration techniques, Prompt4Trust specifically prioritizes aspects of calibration most critical for safe and trustworthy clinical decision-making. Beyond improvements driven by this clinically motivated calibration objective, our proposed method also improves task accuracy, achieving state-of-the-art medical visual question answering (VQA) performance on the PMC-VQA benchmark, which is composed of multiple-choice questions spanning diverse medical imaging modalities. Moreover, our framework trained with a small downstream task MLLM showed promising zero-shot generalization to larger MLLMs in our experiments, suggesting the potential for scalable calibration without the associated computational costs. This work demonstrates the potential of automated yet human-aligned prompt engineering for improving the the trustworthiness of MLLMs in safety critical settings. Our codebase can be found at https://github.com/xingbpshen/prompt4trust.

Pulmonary nodules seen by computed tomography (CT) can be benign or malignant, and early detection is important for optimal management. The existing manual methods of identifying nodules have limitations, such as being time-consuming and erroneous. This study aims to develop an Artificial Intelligence (AI) diagnostic scheme that improves the performance of identifying and categorizing pulmonary nodules using CT scans. The proposed deep learning framework used convolutional neural networks, and the image database totaled 1,056 3D-DICOM CT images. The framework was initially preprocessing, including lung segmentation, nodule detection, and classification. Nodule detection was done using the Retina-UNet model, while the features were classified using a Support Vector Machine (SVM). Performance measures, including accreditation, sensitivity, specificity, and the AUROC, were used to evaluate the model's performance during training and validation. Overall, the developed AI model received an AUROC of 0.9058. The diagnostic accuracy was 90.58%, with an overall positive predictive value of 89% and an overall negative predictive value of 86%. The algorithm effectively handled the CT images at the preprocessing stage, and the deep learning model performed well in detecting and classifying nodules. The application of the new diagnostic framework based on AI algorithms increased the accuracy of the diagnosis compared with the traditional approach. It also provides high reliability for detecting pulmonary nodules and classifying the lesions, thus minimizing intra-observer differences and improving the clinical outcome. In perspective, the advancements may include increasing the size of the annotated data-set and fine-tuning the model due to detection issues of non-solitary nodules.

Increased spinal curvature is one of the most recognizable aging traits in the human population. However, despite high prevalence, the etiology of this condition remains poorly understood. To gain better insight into the physiological, biochemical, and genetic risk factors involved, we developed a novel machine learning method to automatically derive thoracic kyphosis and lumbar lordosis angles from dual-energy X-ray absorptiometry (DXA) scans in the UK Biobank Imaging cohort. We carry out genome-wide association and epidemiological association studies to identify genetic and physiological risk factors for both traits. In 41,212 participants, we find that on average males and females gain 2.42° in kyphotic and 1.48° in lordotic angle per decade of life. Increased spinal curvature shows a strong association with decreased muscle mass and bone mineral density. Adiposity demonstrates opposing associations, with decreased kyphosis and increased lordosis. Using Mendelian randomization, we show that genes fundamental to the maintenance of musculoskeletal function (COL11A1, PTHLH, ETFA, TWIST1) and cellular homeostasis such as RNA transcription and DNA repair (RAD9A, MMS22L, HIF1A, RAB28) are likely involved in increased spinal curvature. Our findings reveal a complex interplay between genetics, musculoskeletal health, and age-related changes in spinal curvature, suggesting potential drivers of this universal aging trait.

Accurate and comprehensive interpretation of pulmonary embolism (PE) from Computed Tomography Pulmonary Angiography (CTPA) scans remains a clinical challenge due to the limited specificity and structure of existing AI tools. We propose an agent-based framework that integrates Vision-Language Models (VLMs) for detecting 32 PE-related abnormalities and Large Language Models (LLMs) for structured report generation. Trained on over 69,000 CTPA studies from 24,890 patients across Brown University Health (BUH), Johns Hopkins University (JHU), and the INSPECT dataset from Stanford, the model demonstrates strong performance in abnormality classification and report generation. For abnormality classification, it achieved AUROC scores of 0.788 (BUH), 0.754 (INSPECT), and 0.710 (JHU), with corresponding BERT-F1 scores of 0.891, 0.829, and 0.842. The abnormality-guided reporting strategy consistently outperformed the organ-based and holistic captioning baselines. For survival prediction, a multimodal fusion model that incorporates imaging, clinical variables, diagnostic outputs, and generated reports achieved concordance indices of 0.863 (BUH) and 0.731 (JHU), outperforming traditional PESI scores. This framework provides a clinically meaningful and interpretable solution for end-to-end PE diagnosis, structured reporting, and outcome prediction.