With the growing capabilities of language models like ChatGPT to process text and images, this study evaluated their accuracy in detecting supernumerary teeth on periapical radiographs. A customized GPT-4V model (CGPT-4V) was also developed to assess whether domain-specific training could improve diagnostic performance compared to standard GPT-4V and GPT-4o models. One hundred eighty periapical radiographs (90 with and 90 without supernumerary teeth) were evaluated using GPT-4 V, GPT-4o, and a fine-tuned CGPT-4V model. Each image was assessed separately with the standardized prompt "Are there any supernumerary teeth in the radiograph above?" to avoid contextual bias. Three dental experts scored the responses using a three-point Likert scale for positive cases and a binary scale for negatives. Chi-square tests and ROC analysis were used to compare model performances (p < 0.05). Among the three models, CGPT-4 V exhibited the highest accuracy, detecting supernumerary teeth correctly in 91% of cases, compared to 77% for GPT-4o and 63% for GPT-4V. The CGPT-4V model also demonstrated a significantly lower false positive rate (16%) than GPT-4V (42%). A statistically significant difference was found between CGPT-4V and GPT-4o (p < 0.001), while no significant difference was observed between GPT-4V and CGPT-4V or between GPT-4V and GPT-4o. Additionally, CGPT-4V successfully identified multiple supernumerary teeth in radiographs where present. These findings highlight the diagnostic potential of customized GPT models in dental radiology. Future research should focus on multicenter validation, seamless clinical integration, and cost-effectiveness to support real-world implementation.

Fast Healthcare Interoperability Resources (FHIR) is a widely used standard for storing and exchanging health care data. At the same time, image-based artificial intelligence (AI) models for quantifying relevant body structures and organs from routine computed tomography (CT)/magnetic resonance imaging scans have emerged. The missing link, simultaneously a needed step in advancing personalized medicine, is the incorporation of measurements delivered by AI models into an interoperable and standardized format. Incorporating image-based measurements and biomarkers into FHIR profiles can standardize data exchange, enabling timely, personalized treatment decisions and improving the precision and efficiency of patient care. This study aims to present the synergistic incorporation of CT-derived body organ and composition measurements with FHIR, delineating an initial paradigm for storing image-based biomarkers. This study integrated the results of the Body and Organ Analysis (BOA) model into FHIR profiles to enhance the interoperability of image-based biomarkers in radiology. The BOA model was selected as an exemplary AI model due to its ability to provide detailed body composition and organ measurements from CT scans. The FHIR profiles were developed based on 2 primary observation types: Body Composition Analysis (BCA Observation) for quantitative body composition metrics and Body Structure Observation for organ measurements. These profiles were structured to interoperate with a specially designed Diagnostic Report profile, which references the associated Imaging Study, ensuring a standardized linkage between image data and derived biomarkers. To ensure interoperability, all labels were mapped to SNOMED CT (Systematized Nomenclature of Medicine - Clinical Terms) or RadLex terminologies using specific value sets. The profiles were developed using FHIR Shorthand (FSH) and SUSHI, enabling efficient definition and implementation guide generation, ensuring consistency and maintainability. In this study, 4 BOA profiles, namely, Body Composition Analysis Observation, Body Structure Volume Observation, Diagnostic Report, and Imaging Study, have been presented. These FHIR profiles, which cover 104 anatomical landmarks, 8 body regions, and 8 tissues, enable the interoperable usage of the results of AI segmentation models, providing a direct link between image studies, series, and measurements. The BOA profiles provide a foundational framework for integrating AI-derived imaging biomarkers into FHIR, bridging the gap between advanced imaging analytics and standardized health care data exchange. By enabling structured, interoperable representation of body composition and organ measurements, these profiles facilitate seamless integration into clinical and research workflows, supporting improved data accessibility and interoperability. Their adaptability allows for extension to other imaging modalities and AI models, fostering a more standardized and scalable approach to using imaging biomarkers in precision medicine. This work represents a step toward enhancing the integration of AI-driven insights into digital health ecosystems, ultimately contributing to more data-driven, personalized, and efficient patient care.

Medical image segmentation is critical for disease diagnosis, treatment planning, and prognosis assessment, yet the complexity and diversity of medical images pose significant challenges to accurate segmentation. While Convolutional Neural Networks capture local features and Vision Transformers excel in the global context, both struggle with efficient long-range dependency modeling. Inspired by Mamba's State Space Modeling efficiency, we propose ÆMMamba, a novel multi-scale feature extraction framework built on the Mamba backbone network. AÆMMamba integrates several innovative modules: the Efficient Fusion Bridge (EFB) module, which employs a bidirectional state-space model and attention mechanisms to fuse multi-scale features; the Edge-Aware Module (EAM), which enhances low-level edge representation using Sobel-based edge extraction; and the Boundary Sensitive Decoder (BSD), which leverages inverse attention and residual convolutional layers to handle cross-level complex boundaries. ÆMMamba achieves state-of-the-art performance across 8 medical segmentation datasets. On polyp segmentation datasets (Kvasir, ClinicDB, ColonDB, EndoScene, ETIS), it records the highest mDice and mIoU scores, outperforming methods like MADGNet and Swin-UMamba, with a standout mDice of 72.22 on ETIS, the most challenging dataset in this domain. For lung and breast segmentation, ÆMMamba surpasses competitors such as H2Former and SwinUnet, achieving Dice scores of 84.24 on BUSI and 79.83 on COVID-19 Lung. And on the LGG brain MRI dataset, ÆMMamba attains an mDice of 87.25 and an mIoU of 79.31, outperforming all compared methods. The source code will be released at https://github.com/xingbod/eMMamba.

Invasive coronary angiography (ICA) is the gold standard in the diagnosis of coronary artery disease (CAD). Being invasive, it carries rare but serious risks including myocardial infarction, stroke, major bleeding, and death. A large proportion of elective outpatients undergoing ICA have nonobstructive CAD, highlighting the suboptimal use of this test. Coronary computed tomographic angiography (CCTA) is a noninvasive option that provides similar information with less risk and is recommended as a first-line test for patients with low-to-intermediate risk of CAD. Leveraging artificial intelligence (AI) to appropriately direct patients to ICA or CCTA based on the predicted probability of disease may improve the efficiency and safety of diagnostic pathways. he CarDIA-AI (Coronary computed tomographic angiography to optimize the Diagnostic yield of Invasive Angiography for low-risk patients screened with Artificial Intelligence) study aims to evaluate whether AI-based risk assessment for obstructive CAD implemented within a centralized triage process can optimize the use of ICA in outpatients referred for nonurgent ICA. CarDIA-AI is a pragmatic, open-label, superior randomized controlled trial involving 2 Canadian cardiac centers. A total of 252 adults referred for elective outpatient ICA will be randomized 1:1 to usual care (directly proceeding to ICA) or to triage using an AI-based decision support tool. The AI-based decision support tool was developed using referral information from over 37,000 patients and uses a light gradient boosting machine model to predict the probability of obstructive CAD based on 42 clinically relevant predictors, including patient referral information, demographic characteristics, risk factors, and medical history. Participants in the intervention arm will have their ICA referral forms and medical charts reviewed, and select details entered into the decision support tool, which recommends CCTA or ICA based on the patient's predicted probability of obstructive CAD. All patients will receive the selected imaging modality within 6 weeks of referral and will be subsequently followed for 90 days. The primary outcome is the proportion of normal or nonobstructive CAD diagnosed via ICA and will be assessed using a 2-sided z test to compare the patients referred for cardiac investigation with normal or nonobstructive CAD diagnosed through ICA between the intervention and control groups. Secondary outcomes include the number of angiograms avoided and the diagnostic yield of ICA. Recruitment began on January 9, 2025, and is expected to conclude in mid to late 2025. As of April 14, 2025, we have enrolled 81 participants. Data analysis will begin once data collection is completed. We expect to submit the results for publication in 2026. CarDIA-AI will be the first randomized controlled trial using AI to optimize patient selection for CCTA versus ICA, potentially improving diagnostic efficiency, avoiding unnecessary complications of ICA, and improving health care resource usage. ClinicalTrials.gov NCT06648239; https://clinicaltrials.gov/study/NCT06648239/. DERR1-10.2196/71726.

We developed an artificial intelligence system (AIS) using multi-view multi-level convolutional neural networks for breast cancer detection, diagnosis, and BI-RADS categorization support in mammography. Twenty-four thousand eight hundred sixty-six breasts from 12,433 Asian women between August 2012 and December 2018 were enrolled. The study consisted of three parts: (1) evaluation of AIS performance in malignancy diagnosis; (2) stratified analysis of BI-RADS 3-4 subgroups with AIS; and (3) reassessment of BI-RADS 0 breasts with AIS assistance. We further evaluate AIS by conducting a counterbalance-designed AI-assisted study, where ten radiologists read 1302 cases with/without AIS assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and F1 score were measured. The AIS yielded AUC values of 0.995, 0.933, and 0.947 for malignancy diagnosis in the validation set, testing set 1, and testing set 2, respectively. Within BI-RADS 3-4 subgroups with pathological results, AIS downgraded 83.1% of false-positives into benign groups, and upgraded 54.1% of false-negatives into malignant groups. AIS also successfully assisted radiologists in identifying 7 out of 43 malignancies initially diagnosed with BI-RADS 0, with a specificity of 96.7%. In the counterbalance-designed AI-assisted study, the average AUC across ten readers significantly improved with AIS assistance (p = 0.001). AIS can accurately detect and diagnose breast cancer on mammography and further serve as a supportive tool for BI-RADS categorization. An AI risk assessment tool employing deep learning algorithms was developed and validated for enhancing breast cancer diagnosis from mammograms, to improve risk stratification accuracy, particularly in patients with dense breasts, and serve as a decision support aid for radiologists. The false positive and negative rates of mammography diagnosis remain high. The AIS can yield a high AUC for malignancy diagnosis. The AIS is important in stratifying BI-RADS categorization.

To perform a systematic review on the impact of deep learning (DL)-based triage for reducing diagnostic delays and improving patient outcomes in peer-reviewed and pre-print publications. A search was conducted of primary research studies focused on DL-based worklist optimization for diagnostic imaging triage published on multiple databases from January 2018 until July 2024. Extracted data included study design, dataset characteristics, workflow metrics including report turnaround time and time-to-treatment, and patient outcome differences. Further analysis between clinical settings and integration modality was investigated using nonparametric statistics. Risk of bias was assessed with the risk of bias in non-randomized studies-of interventions (ROBINS-I) checklist. A total of 38 studies from 20 publications, involving 138,423 images, were analyzed. Workflow interventions concerned pulmonary embolism (n = 8), stroke (n = 3), intracranial hemorrhage (n = 12), and chest conditions (n = 15). Patients in the post DL-triage group had shorter median report turnaround times: a mean difference of 12.3 min (IQR: -25.7, -7.6) for pulmonary embolism, 20.5 min (IQR: -32.1, -9.3) for stroke, 4.3 min (IQR: -8.6, 1.3) for intracranial hemorrhage and 29.7 min (IQR: -2947.7, -18.3) for chest diseases. Sub-group analysis revealed that reductions varied per clinical environment and relative prevalence rates but were the highest when algorithms actively stratified and reordered the radiological worklist, with reductions of -43.7% in report turnaround time compared to -7.6% from widget-based systems (p < 0.01). DL-based triage systems had comparable report turnaround time improvements, especially in outpatient and high-prevalence settings, suggesting that AI-based triage holds promise in alleviating radiology workloads. Question Can DL-based triage address lengthening imaging report turnaround times and improve patient outcomes across distinct clinical environments? Findings DL-based triage improved report turnaround time across disease groups, with higher reductions reported in high-prevalence or lower acuity settings. Clinical relevance DL-based workflow prioritization is a reliable tool for reducing diagnostic imaging delay for time-sensitive disease across clinical settings. However, further research and reliable metrics are needed to provide specific recommendations with regards to false-negative examinations and multi-condition prioritization.

<i>"Just Accepted" papers have undergone full peer review and have been accepted for publication in <i>Radiology: Artificial Intelligence</i>. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content.</i> Purpose To develop a deep learning segmentation model that can segment abdominal organs on CT and MR images with high accuracy and generalization ability. Materials and Methods In this study, an extended nnU-Net model was trained for abdominal organ segmentation. A domain randomization method in both the image and feature space was developed to improve the generalization ability under cross-site and cross-modality settings on public prostate MRI and abdominal CT and MRI datasets. The prostate MRI dataset contains data from multiple health care institutions with domain shifts. The abdominal CT and MRI dataset is structured for cross-modality evaluation, training on one modality (eg, MRI) and testing on the other (eg, CT). This domain randomization method was then used to train a segmentation model with enhanced generalization ability on the abdominal multiorgan segmentation challenge (AMOS) dataset to improve abdominal CT and MR multiorgan segmentation, and the model was compared with two commonly used segmentation algorithms (TotalSegmentator and MRSegmentator). Model performance was evaluated using the Dice similarity coefficient (DSC). Results The proposed domain randomization method showed improved generalization ability on the cross-site and cross-modality datasets compared with the state-of-the-art methods. The segmentation model using this method outperformed two other publicly available segmentation models on data from unseen test domains (Average DSC: 0.88 versus 0.79; <i>P</i> < .001 and 0.88 versus 0.76; <i>P</i> < .001). Conclusion The combination of image and feature domain randomizations improved the accuracy and generalization ability of deep learning-based abdominal segmentation on CT and MR images. © RSNA, 2025.

Our objective is to develop and validate a deep learning radiomics nomogram (DLRN) based on preoperative ultrasound images and clinical features, for predicting the malignancy of thyroid nodules with indeterminate cytology (Bethesda III). Between June 2017 and June 2022, we conducted a retrospective study on 194 patients with surgically confirmed indeterminate cytology (Bethesda III) in our hospital. The training and internal validation cohorts were comprised of 155 and 39 patients, in a 7:3 ratio. To facilitate external validation, we selected an additional 80 patients from each of the remaining two medical centers. Utilizing preoperative ultrasound data, we obtained imaging markers that encompass both deep learning and manually radiomic features. After feature selection, we developed a comprehensive diagnostic model to evaluate the predictive value for Bethesda III benign and malignant cases. The model's diagnostic accuracy, calibration, and clinical applicability were systematically assessed. The results showed that the prediction model, which integrated 512 DTL features extracted from the pre-trained Resnet34 network, ultrasound radiomics, and clinical features, exhibited superior stability in distinguishing between benign and malignant indeterminate thyroid nodules (Bethesda Class III). In the validation set, the AUC was 0.92 (95% CI: 0.831-1.000), and the accuracy, sensitivity, specificity, precision, and recall were 0.897, 0.882, 0.909, 0.882, and 0.882, respectively. The comprehensive multidimensional data model based on deep transfer learning, ultrasound radiomics features, and clinical characteristics can effectively distinguish the benign and malignant indeterminate thyroid nodules (Bethesda Class III), providing valuable guidance for treatment selection in patients with indeterminate thyroid nodules (Bethesda Class III).

Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single images, we propose VET-DINO, a framework that leverages a unique characteristic of medical imaging: the availability of multiple standardized views from the same study. Using a series of clinical veterinary radiographs from the same patient study, we enable models to learn view-invariant anatomical structures and develop an implied 3D understanding from 2D projections. We demonstrate our approach on a dataset of 5 million veterinary radiographs from 668,000 canine studies. Through extensive experimentation, including view synthesis and downstream task performance, we show that learning from real multi-view pairs leads to superior anatomical understanding compared to purely synthetic augmentations. VET-DINO achieves state-of-the-art performance on various veterinary imaging tasks. Our work establishes a new paradigm for self-supervised learning in medical imaging that leverages domain-specific properties rather than merely adapting natural image techniques.

Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.