Musculoskeletal ultrasound is a key tool in rheumatology for diagnosing and managing inflammatory arthritis. Traditional ultrasound systems, while effective, can be cumbersome and costly, limiting their use in many clinical settings. Handheld ultrasound (HHUS) devices, which are portable, affordable, and user-friendly, have emerged as a promising alternative. This review explores the role of HHUS in rheumatology, specifically evaluating its impact on diagnostic accuracy, ease of use, and utility in screening for inflammatory arthritis. The review also addresses key challenges, such as image quality, storage and data security, and the potential for integrating artificial intelligence to improve device performance. We compare HHUS devices to cart-based ultrasound machines, discuss their advantages and limitations, and examine the potential for widespread adoption. Our findings suggest that HHUS devices can effectively support musculoskeletal assessments and offer significant benefits in resource-limited settings. However, proper training, standardized protocols, and continued technological advancements are essential for optimizing their use in clinical practice.

Purpose The limited availability of bronchoscopy images makes image synthesis particularly interesting for training deep learning models. Robust image translation across different domains-virtual bronchoscopy, phantom as well as in vivo and ex vivo image data-is pivotal for clinical applications. Methods This paper proposes BronchoGAN introducing anatomical constraints for image-to-image translation being integrated into a conditional GAN. In particular, we force bronchial orifices to match across input and output images. We further propose to use foundation model-generated depth images as intermediate representation ensuring robustness across a variety of input domains establishing models with substantially less reliance on individual training datasets. Moreover, our intermediate depth image representation allows to easily construct paired image data for training. Results Our experiments showed that input images from different domains (e.g., virtual bronchoscopy, phantoms) can be successfully translated to images mimicking realistic human airway appearance. We demonstrated that anatomical settings (i.e., bronchial orifices) can be robustly preserved with our approach which is shown qualitatively and quantitatively by means of improved FID, SSIM and dice coefficients scores. Our anatomical constraints enabled an improvement in the Dice coefficient of up to 0.43 for synthetic images. Conclusion Through foundation models for intermediate depth representations and bronchial orifice segmentation integrated as anatomical constraints into conditional GANs, we are able to robustly translate images from different bronchoscopy input domains. BronchoGAN allows to incorporate public CT scan data (virtual bronchoscopy) in order to generate large-scale bronchoscopy image datasets with realistic appearance. BronchoGAN enables to bridge the gap of missing public bronchoscopy images.

Laser interstitial thermal therapy (LiTT) has emerged as a minimally invasive, MRI-guided treatment of brain tumors that are otherwise considered inoperable because of their location or the patient's poor surgical candidacy. By directing thermal energy at neoplastic lesions while minimizing damage to surrounding healthy tissue, LiTT offers promising therapeutic outcomes for both newly diagnosed and recurrent tumors. However, challenges such as postprocedural edema, unpredictable heat diffusion near blood vessels and ventricles in real time underscore the need for improved planning and monitoring. Incorporating artificial intelligence (AI) presents a viable solution to many of these obstacles. AI has already demonstrated effectiveness in optimizing surgical trajectories, predicting seizure-free outcomes in epilepsy cases, and generating heat distribution maps to guide real-time ablation. This technology could be similarly deployed in neurosurgical oncology to identify patients most likely to benefit from LiTT, refine trajectory planning, and predict tissue-specific heat responses. Despite promising initial studies, further research is needed to establish the robust data sets and clinical trials necessary to develop and validate AI-driven LiTT protocols. Such advancements have the potential to bolster LiTT's efficacy, minimize complications, and ultimately transform the neurosurgical management of primary and metastatic brain tumors.

Understanding medical ultrasound imaging remains a long-standing challenge due to significant visual variability caused by differences in imaging and acquisition parameters. Recent advancements in large language models (LLMs) have been used to automatically generate terminology-rich summaries orientated to clinicians with sufficient physiological knowledge. Nevertheless, the increasing demand for improved ultrasound interpretability and basic scanning guidance among non-expert users, e.g., in point-of-care settings, has not yet been explored. In this study, we first introduce the scene graph (SG) for ultrasound images to explain image content to ordinary and provide guidance for ultrasound scanning. The ultrasound SG is first computed using a transformer-based one-stage method, eliminating the need for explicit object detection. To generate a graspable image explanation for ordinary, the user query is then used to further refine the abstract SG representation through LLMs. Additionally, the predicted SG is explored for its potential in guiding ultrasound scanning toward missing anatomies within the current imaging view, assisting ordinary users in achieving more standardized and complete anatomical exploration. The effectiveness of this SG-based image explanation and scanning guidance has been validated on images from the left and right neck regions, including the carotid and thyroid, across five volunteers. The results demonstrate the potential of the method to maximally democratize ultrasound by enhancing its interpretability and usability for ordinaries.

Early detection through screening is critical for reducing gastric cancer (GC) mortality. However, in most high-prevalence regions, large-scale screening remains challenging due to limited resources, low compliance and suboptimal detection rate of upper endoscopic screening. Therefore, there is an urgent need for more efficient screening protocols. Noncontrast computed tomography (CT), routinely performed for clinical purposes, presents a promising avenue for large-scale designed or opportunistic screening. Here we developed the Gastric Cancer Risk Assessment Procedure with Artificial Intelligence (GRAPE), leveraging noncontrast CT and deep learning to identify GC. Our study comprised three phases. First, we developed GRAPE using a cohort from 2 centers in China (3,470 GC and 3,250 non-GC cases) and validated its performance on an internal validation set (1,298 cases, area under curve = 0.970) and an independent external cohort from 16 centers (18,160 cases, area under curve = 0.927). Subgroup analysis showed that the detection rate of GRAPE increased with advancing T stage but was independent of tumor location. Next, we compared the interpretations of GRAPE with those of radiologists and assessed its potential in assisting diagnostic interpretation. Reader studies demonstrated that GRAPE significantly outperformed radiologists, improving sensitivity by 21.8% and specificity by 14.0%, particularly in early-stage GC. Finally, we evaluated GRAPE in real-world opportunistic screening using 78,593 consecutive noncontrast CT scans from a comprehensive cancer center and 2 independent regional hospitals. GRAPE identified persons at high risk with GC detection rates of 24.5% and 17.7% in 2 regional hospitals, with 23.2% and 26.8% of detected cases in T1/T2 stage. Additionally, GRAPE detected GC cases that radiologists had initially missed, enabling earlier diagnosis of GC during follow-up for other diseases. In conclusion, GRAPE demonstrates strong potential for large-scale GC screening, offering a feasible and effective approach for early detection. ClinicalTrials.gov registration: NCT06614179 .

Understanding medical ultrasound imaging remains a long-standing challenge due to significant visual variability caused by differences in imaging and acquisition parameters. Recent advancements in large language models (LLMs) have been used to automatically generate terminology-rich summaries orientated to clinicians with sufficient physiological knowledge. Nevertheless, the increasing demand for improved ultrasound interpretability and basic scanning guidance among non-expert users, e.g., in point-of-care settings, has not yet been explored. In this study, we first introduce the scene graph (SG) for ultrasound images to explain image content to ordinary and provide guidance for ultrasound scanning. The ultrasound SG is first computed using a transformer-based one-stage method, eliminating the need for explicit object detection. To generate a graspable image explanation for ordinary, the user query is then used to further refine the abstract SG representation through LLMs. Additionally, the predicted SG is explored for its potential in guiding ultrasound scanning toward missing anatomies within the current imaging view, assisting ordinary users in achieving more standardized and complete anatomical exploration. The effectiveness of this SG-based image explanation and scanning guidance has been validated on images from the left and right neck regions, including the carotid and thyroid, across five volunteers. The results demonstrate the potential of the method to maximally democratize ultrasound by enhancing its interpretability and usability for ordinaries.

Brain ultrasound is a popular point-of-care test that helps visualize brain structures. This review highlights recent developments in brain ultrasonography. There is a need to keep pace with the ongoing technological advancements and establishing standardized quality criteria for improving its utility in clinical practice. Newer automated indices derived from transcranial Doppler help establish its role as a noninvasive monitor of intracranial pressure and diagnosing vasospasm/delayed cerebral ischemia. A novel robotic transcranial Doppler system equipped with artificial intelligence allows real-time continuous neuromonitoring. Intraoperative ultrasound assists neurosurgeons in real-time localization of brain lesions and helps in assessing the extent of resection, thereby enhancing surgical precision and safety. Optic nerve sheath diameter point-of-care ultrasonography is an effective means of diagnosing raised intracranial pressure, triaging, and prognostication. The quality criteria checklist can help standardize this technique. Newer advancements like focused ultrasound, contrast-enhanced ultrasound, and functional ultrasound have also been discussed. Brain ultrasound continues to be a critical bedside tool in neurologically injured patients. With the advent of technological advancements, its utility has widened and its capabilities have expanded, making it more accurate and versatile in clinical practice.

BackgroundGenerative Pre-trained Transformer 4 (GPT-4) has demonstrated strong performance in standardized medical examinations but has limitations in real-world clinical settings. The newly released multimodal GPT-4o model, which integrates text and image inputs to enhance diagnostic capabilities, and the multimodal o1 model, which incorporates advanced reasoning, may address these limitations. ObjectiveThis study aimed to compare the performance of GPT-4o and o1 against clinicians in real-world clinical case challenges. MethodsThis retrospective, cross-sectional study used Medscape case challenge questions from May 2011 to June 2024 (n = 1,426). Each case included text and images of patient history, physical examination findings, diagnostic test results, and imaging studies. Clinicians were required to choose one answer from among multiple options, with the most frequent response defined as the clinicians decision. Data-based decisions were made using GPT models (3.5 Turbo, 4 Turbo, 4 Omni, and o1) to interpret the text and images, followed by a process to provide a formatted answer. We compared the performances of the clinicians and GPT models using Mixed-effects logistic regression analysis. ResultsOf the 1,426 questions, clinicians achieved an overall accuracy of 85.0%, whereas GPT-4o and o1 demonstrated higher accuracies of 88.4% and 94.3% (mean difference 3.4%; P = .005 and mean difference 9.3%; P < .001), respectively. In the multimodal performance analysis, which included cases involving images (n = 917), GPT-4o achieved an accuracy of 88.3%, and o1 achieved 93.9%, both significantly outperforming clinicians (mean difference 4.2%; P = .005 and mean difference 9.8%; P < .001). o1 showed the highest accuracy across all question categories, achieving 92.6% in diagnosis (mean difference 14.5%; P < .001), 97.0% in disease characteristics (mean difference 7.2%; P < .001), 92.6% in examination (mean difference 7.3%; P = .002), and 94.8% in treatment (mean difference 4.3%; P = .005), consistently outperforming clinicians. In terms of medical specialty, o1 achieved 93.6% accuracy in internal medicine (mean difference 10.3%; P < .001), 96.6% in major surgery (mean difference 9.2%; P = .030), 97.3% in psychiatry (mean difference 10.6%; P = .030), and 95.4% in minor specialties (mean difference 10.0%; P < .001), significantly surpassing clinicians. Across five trials, GPT-4o and o1 provided the correct answer 5/5 times in 86.2% and 90.7% of the cases, respectively. ConclusionsThe GPT-4o and o1 models achieved higher accuracy than clinicians in clinical case challenge questions, particularly in disease diagnosis. The GPT-4o and o1 could serve as valuable tools to assist healthcare professionals in clinical settings.

Existing foundation models for neuroimaging are often prohibitively large and data-intensive. We introduce BrainSymphony, a lightweight, parameter-efficient foundation model that achieves state-of-the-art performance while being pre-trained on significantly smaller public datasets. BrainSymphony's strong multimodal architecture processes functional MRI data through parallel spatial and temporal transformer streams, which are then efficiently distilled into a unified representation by a Perceiver module. Concurrently, it models structural connectivity from diffusion MRI using a novel signed graph transformer to encode the brain's anatomical structure. These powerful, modality-specific representations are then integrated via an adaptive fusion gate. Despite its compact design, our model consistently outperforms larger models on a diverse range of downstream benchmarks, including classification, prediction, and unsupervised network identification tasks. Furthermore, our model revealed novel insights into brain dynamics using attention maps on a unique external psilocybin neuroimaging dataset (pre- and post-administration). BrainSymphony establishes that architecturally-aware, multimodal models can surpass their larger counterparts, paving the way for more accessible and powerful research in computational neuroscience.

Extracting clinical entities from unstructured medical documents is critical for improving clinical decision support and documentation workflows. This study examines the performance of various encoder and decoder models trained for Named Entity Recognition (NER) of clinical parameters in pathology and radiology reports, highlighting the applicability of Large Language Models (LLMs) for this task. Three NER methods were evaluated: (1) flat NER using transformer-based models, (2) nested NER with a multi-task learning setup, and (3) instruction-based NER utilizing LLMs. A dataset of 2013 pathology reports and 413 radiology reports, annotated by medical students, was used for training and testing. The performance of encoder-based NER models (flat and nested) was superior to that of LLM-based approaches. The best-performing flat NER models achieved F1-scores of 0.87-0.88 on pathology reports and up to 0.78 on radiology reports, while nested NER models performed slightly lower. In contrast, multiple LLMs, despite achieving high precision, yielded significantly lower F1-scores (ranging from 0.18 to 0.30) due to poor recall. A contributing factor appears to be that these LLMs produce fewer but more accurate entities, suggesting they become overly conservative when generating outputs. LLMs in their current form are unsuitable for comprehensive entity extraction tasks in clinical domains, particularly when faced with a high number of entity types per document, though instructing them to return more entities in subsequent refinements may improve recall. Additionally, their computational overhead does not provide proportional performance gains. Encoder-based NER models, particularly those pre-trained on biomedical data, remain the preferred choice for extracting information from unstructured medical documents.