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.

Augmented reality (AR) technology holds significant promise for enhancing surgical navigation in needle-based procedures such as biopsies and ablations. However, most existing AR systems rely on patient-specific markers, which disrupt clinical workflows and require time-consuming preoperative calibrations, thereby hindering operational efficiency and precision. We developed a novel multi-camera AR navigation system that eliminates the need for patient-specific markers by utilizing ceiling-mounted markers mapped to fixed medical imaging devices. A hierarchical optimization framework integrates both marker mapping and multi-camera calibration. Deep learning techniques are employed to enhance marker detection and registration accuracy. Additionally, a vision-based pose compensation method is implemented to mitigate errors caused by patient movement, improving overall positional accuracy. Validation through phantom experiments and simulated clinical scenarios demonstrated an average puncture accuracy of 3.72 ± 1.21 mm. The system reduced needle placement time by 20 s compared to traditional marker-based methods. It also effectively corrected errors induced by patient movement, with a mean positional error of 0.38 pixels and an angular deviation of 0.51 <math xmlns="http://www.w3.org/1998/Math/MathML"><mmultiscripts><mrow></mrow> <mrow></mrow> <mo>∘</mo></mmultiscripts> </math> . These results highlight the system's precision, adaptability, and reliability in realistic surgical conditions. This marker-free AR guidance system significantly streamlines surgical workflows while enhancing needle navigation accuracy. Its simplicity, cost-effectiveness, and adaptability make it an ideal solution for both high- and low-resource clinical environments, offering the potential for improved precision, reduced procedural time, and better patient outcomes.

Neuroimaging plays a crucial role in diagnosing multiple system atrophy and monitoring progressive neurodegeneration in this fatal disease. Advanced MRI techniques and post-processing methods have demonstrated significant volume loss and microstructural changes in brain regions well known to be affected by MSA pathology. These observations can be exploited to support the differential diagnosis of MSA distinguishing it from Parkinson's disease and progressive supranuclear palsy with high sensitivity and specificity. Longitudinal studies reveal aggressive neurodegeneration in MSA, with notable atrophy rates in the cerebellum, pons, and putamen. Radiotracer imaging using PET and SPECT has shown characteristic disease-related patterns, aiding in differential diagnosis and tracking disease progression. Future research should focus on early diagnosis, particularly in prodromal stages, and the development of reliable biomarkers for clinical trials. Combining different neuroimaging modalities and machine learning algorithms can enhance diagnostic precision and provide a comprehensive understanding of MSA pathology.

Solving computer vision problems through machine learning, one often encounters lack of sufficient training data. To mitigate this we propose the use of ensembles of weak learners based on spectral total-variation (STV) features (Gilboa 2014). The features are related to nonlinear eigenfunctions of the total-variation subgradient and can characterize well textures at various scales. It was shown (Burger et-al 2016) that, in the one-dimensional case, orthogonal features are generated, whereas in two-dimensions the features are empirically lowly correlated. Ensemble learning theory advocates the use of lowly correlated weak learners. We thus propose here to design ensembles using learners based on STV features. To show the effectiveness of this paradigm we examine a hard real-world medical imaging problem: the predictive value of computed tomography (CT) data for high uptake in positron emission tomography (PET) for patients suspected of skeletal metastases. The database consists of 457 scans with 1524 unique pairs of registered CT and PET slices. Our approach is compared to deep-learning methods and to Radiomics features, showing STV learners perform best (AUC=0.87), compared to neural nets (AUC=0.75) and Radiomics (AUC=0.79). We observe that fine STV scales in CT images are especially indicative for the presence of high uptake in PET.

The REgistry of Flow and Perfusion Imaging for Artificial INtelligEnce with PET (REFINE PET) was established to aggregate PET and associated computed tomography (CT) images with clinical data from hospitals around the world into one comprehensive research resource. REFINE PET is a multicenter, international registry that contains both clinical and imaging data. The PET scans were processed using QPET software (Cedars-Sinai Medical Center, Los Angeles, CA), while the CT scans were processed using deep learning (DL) to detect coronary artery calcium (CAC). Patients were followed up for the occurrence of major adverse cardiovascular events (MACE), which include death, myocardial infarction, unstable angina, and late revascularization (>90 days from PET). The REFINE PET registry currently contains data for 35,588 patients from 14 sites, with additional patient data and sites anticipated. Comprehensive clinical data (including demographics, medical history, and stress test results) were integrated with more than 2200 imaging variables across 42 categories. The registry is poised to address a broad range of clinical questions, supported by correlating invasive angiography (within 6 months of MPI) in 5972 patients and a total of 9252 major adverse cardiovascular events during a median follow-up of 4.2 years. The REFINE PET registry leverages the integration of clinical, multimodality imaging, and novel quantitative and AI tools to advance the role of PET/CT MPI in diagnosis and risk stratification.

Accurate targeting is critical for the effectiveness of transcranial focused ultrasound (tFUS) neuromodulation. While CT provides accurate skull acoustic properties, its ionizing radiation and poor soft tissue contrast limit clinical applicability. In contrast, MRI offers superior neuroanatomical visualization without radiation exposure but lacks skull property mapping. This study proposes a novel, fully CT free simulation framework that integrates MRI-derived synthetic CT (sCT) with efficient modeling techniques for rapid and precise tFUS targeting. We trained a deep-learning model to generate sCT from T1-weighted MRI and integrated it with both full-wave (k-Wave) and accelerated simulation methods, hybrid angular spectrum (kWASM) and Rayleigh-Sommerfeld ASM (RSASM). Across five skull models, both full-wave and hybrid pipelines using sCT demonstrated sub-millimeter targeting deviation, focal shape consistency (FWHM ~3.3-3.8 mm), and <0.2 normalized pressure error compared to CT-based gold standard. Notably, the kW-ASM and RS-ASM pipelines reduced simulation time from ~3320 s to 187 s and 34 s respectively, achieving ~94% and ~90% time savings. These results confirm that MRI-derived sCT combined with innovative rapid simulation techniques enables fast, accurate, and radiation-free tFUS planning, supporting its feasibility for scalable clinical applications.

Medical image retrieval is a valuable field for supporting clinical decision-making, yet current methods primarily support 2D images and require fully annotated queries, limiting clinical flexibility. To address this, we propose RadiomicsRetrieval, a 3D content-based retrieval framework bridging handcrafted radiomics descriptors with deep learning-based embeddings at the tumor level. Unlike existing 2D approaches, RadiomicsRetrieval fully exploits volumetric data to leverage richer spatial context in medical images. We employ a promptable segmentation model (e.g., SAM) to derive tumor-specific image embeddings, which are aligned with radiomics features extracted from the same tumor via contrastive learning. These representations are further enriched by anatomical positional embedding (APE). As a result, RadiomicsRetrieval enables flexible querying based on shape, location, or partial feature sets. Extensive experiments on both lung CT and brain MRI public datasets demonstrate that radiomics features significantly enhance retrieval specificity, while APE provides global anatomical context essential for location-based searches. Notably, our framework requires only minimal user prompts (e.g., a single point), minimizing segmentation overhead and supporting diverse clinical scenarios. The capability to query using either image embeddings or selected radiomics attributes highlights its adaptability, potentially benefiting diagnosis, treatment planning, and research on large-scale medical imaging repositories. Our code is available at https://github.com/nainye/RadiomicsRetrieval.

BackgroundPositron Emission Tomography (PET) myocardial perfusion imaging (MPI) is a powerful tool for predicting coronary artery disease (CAD). Coronary artery calcium (CAC) provides incremental risk stratification to PET-MPI and enhances diagnostic accuracy. We assessed additive value of CAC score, derived from PET/CT attenuation maps to stress TPD results using the novel 18F-flurpiridaz tracer in detecting significant CAD. Methods and ResultsPatients from 18F-flurpiridaz phase III clinical trial who underwent PET/CT MPI with 18F-flurpiridaz tracer, had available CT attenuation correction (CTAC) scans for CAC scoring, and underwent invasive coronary angiography (ICA) within a 6-month period between 2011 and 2013, were included. Total perfusion deficit (TPD) was quantified automatically, and CAC scores from CTAC scans were assessed using artificial intelligence (AI)-derived segmentation and manual scoring. Obstructive CAD was defined as [&ge;]50% stenosis in Left Main (LM) artery, or 70% or more stenosis in any of the other major epicardial vessels. Prediction performance for CAD was assessed by comparing the area under receiver operating characteristic curve (AUC) for stress TPD alone and in combination with CAC score. Among 498 patients (72% males, median age 63 years) 30.1% had CAD. Incorporating CAC score resulted in a greater AUC: manual scoring (AUC=0.87, 95% Confidence Interval [CI] 0.34-0.90; p=0.015) and AI-based scoring (AUC=0.88, 95%CI 0.85-0.90; p=0.002) compared to stress TPD alone (AUC 0.84, 95% CI 0.80-0.92). ConclusionsCombining automatically derived TPD and CAC score enhances 18F-flurpiridaz PET MPI accuracy in detecting significant CAD, offering a method that can be routinely used with PET/CT scanners without additional scanning or technologist time. CONDENSED ABSTRACTO_ST_ABSBackgroundC_ST_ABSWe assessed the added value of CAC score from hybrid PET/CT CTAC scans combined with stress TPD for detecting significant CAD using novel 18F-flurpiridaz tracer Methods and resultsPatients from the 18F-flurpiridaz phase III clinical trial (n=498, 72% male, median age 63) who underwent PET/CT MPI and ICA within 6-months were included. TPD was quantified automatically, and CAC scores were assessed by AI and manual methods. Adding CAC score to TPD improved AUC for manual (0.87) and AI-based (0.88) scoring versus TPD alone (0.84). ConclusionsCombining TPD and CAC score enhances 18F-flurpiridaz PET MPI accuracy for CAD detection O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=110 SRC="FIGDIR/small/25330013v1_ufig1.gif" ALT="Figure 1"> View larger version (37K): [email protected]@ba93d1org.highwire.dtl.DTLVardef@13eabd9org.highwire.dtl.DTLVardef@1845505_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOGraphical Abstract.C_FLOATNO Overview of the study design. C_FIG

In-context learning (ICL) is emerging as a promising technique for achieving universal medical image segmentation, where a variety of objects of interest across imaging modalities can be segmented using a single model. Nevertheless, its performance is highly sensitive to the alignment between the query image and in-context image-mask pairs. In a clinical scenario, the scarcity of annotated medical images makes it challenging to select optimal in-context pairs, and fine-tuning foundation ICL models on contextual data is infeasible due to computational costs and the risk of catastrophic forgetting. To address this challenge, we propose Cycle Context Verification (CCV), a novel framework that enhances ICL-based medical image segmentation by enabling self-verification of predictions and accordingly enhancing contextual alignment. Specifically, CCV employs a cyclic pipeline in which the model initially generates a segmentation mask for the query image. Subsequently, the roles of the query and an in-context pair are swapped, allowing the model to validate its prediction by predicting the mask of the original in-context image. The accuracy of this secondary prediction serves as an implicit measure of the initial query segmentation. A query-specific prompt is introduced to alter the query image and updated to improve the measure, thereby enhancing the alignment between the query and in-context pairs. We evaluated CCV on seven medical image segmentation datasets using two ICL foundation models, demonstrating its superiority over existing methods. Our results highlight CCV's ability to enhance ICL-based segmentation, making it a robust solution for universal medical image segmentation. The code will be available at https://github.com/ShishuaiHu/CCV.

Semi-supervised medical image segmentation techniques have demonstrated significant potential and effectiveness in clinical diagnosis. The prevailing approaches using the mean-teacher (MT) framework achieve promising image segmentation results. However, due to the unreliability of the pseudo labels generated by the teacher model, existing methods still have some inherent limitations that must be considered and addressed. In this paper, we propose an innovative semi-supervised method for medical image segmentation by combining the heterogeneous complementary correction network and confidence contrastive learning (HC-CCL). Specifically, we develop a triple-branch framework by integrating a heterogeneous complementary correction (HCC) network into the MT framework. HCC serves as an auxiliary branch that corrects prediction errors in the student model and provides complementary information. To improve the capacity for feature learning in our proposed model, we introduce a confidence contrastive learning (CCL) approach with a novel sampling strategy. Furthermore, we develop a momentum style transfer (MST) method to narrow the gap between labeled and unlabeled data distributions. In addition, we introduce a Cutout-style augmentation for unsupervised learning to enhance performance. Three medical image datasets (including left atrial (LA) dataset, NIH pancreas dataset, Brats-2019 dataset) were employed to rigorously evaluate HC-CCL. Quantitative results demonstrate significant performance advantages over existing approaches, achieving state-of-the-art performance across all metrics. The implementation will be released at https://github.com/xxmmss/HC-CCL .