The aim of this study was to evaluate GPT-4o's multimodal reasoning ability to review panoramic radiograph (PR) and verify its radiologic findings, while exploring the role of prompt engineering in enhancing its performance. The study included 230 PRs from West China Hospital of Stomatology in 2024, which were interpreted to generate the PR findings. A total of 300 instances of interpretation errors, were manually inserted into the PR findings. The ablation study was conducted to assess whether GPT-4o can perform reasoning on PR under a zero-shot prompt. Prompt engineering was employed to enhance the reasoning capabilities of GPT-4o in identifying interpretation errors with PRs. The prompt strategies included chain-of-thought, self-consistency, in-context learning, multimodal in-context learning, and their systematic integration into a meta-prompt. Recall, accuracy, and F1 score were employed to evaluate the outputs. Subsequently, the localization capability of GPT-4o and its influence on reasoning capability were evaluated. In the ablation study, GPT-4o's recall increased significantly from 2.67 to 43.33% upon acquiring PRs (P < 0.001). GPT-4o with the meta prompt demonstrated improvements in recall (43.33% vs. 52.67%, P = 0.022), accuracy (39.95% vs. 68.75%, P < 0.001), and F1 score (0.42 vs. 0.60, P < 0.001) compared to the zero-shot prompt and other prompt strategies. The localization accuracy of GPT-4o was 45.67% (137 out of 300, 95% CI: 40.00 to 51.34). A significant correlation was observed between its localization accuracy and reasoning capability under the meta prompt (φ coefficient = 0.33, p < 0.001). The model's recall increased by 5.49% (P = 0.031) by providing accurate localization cues within the meta prompt. GPT-4o demonstrated a certain degree of multimodal capability for PR, with performance enhancement through prompt engineering. Nevertheless, its performance remains inadequate for clinical requirements. Future efforts will be necessary to identify additional factors influencing the model's reasoning capability or to develop more advanced models. Evaluating GPT-4o's capability to interpret and reason through PRs and exploring potential methods to enhance its performance before clinical application in assisting radiological assessments.

Distinguishing among neuroinflammatory demyelinating diseases of the central nervous system can present a significant diagnostic challenge due to substantial overlap in clinical presentations and imaging features. Collaboration between specialists, novel antibody testing, and dedicated magnetic resonance imaging protocols have helped to narrow the diagnostic gap, but challenging cases remain. Machine learning algorithms have proven to be able to identify subtle patterns that escape even the most experienced human eye. Indeed, machine learning and the subfield of radiomics have demonstrated exponential growth and improvement in diagnosis capacity within the past decade. The sometimes daunting diagnostic overlap of various demyelinating processes thus provides a unique opportunity: can the elite pattern recognition powers of machine learning close the gap in making the correct diagnosis? This review specifically focuses on neuroinflammatory demyelinating diseases, exploring the role of artificial intelligence in the detection, diagnosis, and differentiation of the most common pathologies: multiple sclerosis (MS), neuromyelitis optica spectrum disorder (NMOSD), acute disseminated encephalomyelitis (ADEM), Sjogren's syndrome, MOG antibody-associated disorder (MOGAD), and neuropsychiatric systemic lupus erythematosus (NPSLE). Understanding how these tools enhance diagnostic precision may lead to earlier intervention, improved outcomes, and optimized management strategies.

Bone marrow adipose tissue, as a distinct adipose subtype, has been implicated in the pathophysiology of skeletal, metabolic, and hematopoietic disorders. To identify its underlying genetic factors, we utilized a deep learning algorithm capable of quantifying bone marrow fat fraction (BMFF) in the vertebrae and proximal femur using magnetic resonance imaging data of over 38,000 UK Biobank participants. Genome-wide association analyses uncovered 373 significant BMFF-associated variants (P-value < 5 × 10^-9), with enrichment in bone remodeling, metabolism, and hematopoiesis pathway. Furthermore, genetic correlation highlighted a significant association between BMFF and skeletal disease. In about 300,000 individuals, polygenic risk scores derived from three proximal femur BMFF were significantly associated with increased osteoporosis risk. Notably, Mendelian randomization analyses revealed a causal link between proximal femur BMFF and osteoporosis. Here, we show critical insights into the genetic determinants of BMFF and offer perspectives on the biological mechanisms driving osteoporosis development.

Multi-Modal Medical Image Fusion (MMMIF) has become increasingly important in clinical applications, as it enables the integration of complementary information from different imaging modalities to support more accurate diagnosis and treatment planning. The primary objective of Medical Image Fusion (MIF) is to generate a fused image that retains the most informative features from the Source Images (SI), thereby enhancing the reliability of clinical decision-making systems. However, due to inherent limitations in individual imaging modalities-such as poor spatial resolution in functional images or low contrast in anatomical scans-fused images can suffer from information degradation or distortion. To address these limitations, this study proposes a novel fusion framework that integrates the Non-Subsampled Shearlet Transform (NSST) with a Convolutional Neural Network (CNN) for effective sub-band enhancement and image reconstruction. Initially, each source image is decomposed into Low-Frequency Coefficients (LFC) and multiple High-Frequency Coefficients (HFC) using NSST. The proposed Concurrent Denoising and Enhancement Network (CDEN) is then applied to these sub-bands to suppress noise and enhance critical structural details. The enhanced LFCs are fused using an AlexNet-based activity-level fusion model, while the enhanced HFCs are combined using a Pulse Coupled Neural Network (PCNN) guided by a Novel Sum-Modified Laplacian (NSML) metric. Finally, the fused image is reconstructed via Inverse-NSST (I-NSST). Experimental results prove that the proposed method outperforms existing fusion algorithms, achieving approximately 16.5% higher performance in terms of the QAB/F (edge preservation) metric, along with strong results across both subjective visual assessments and objective quality indices.

Breast cancer, the most prevalent cancer among women globally, is classified into molecular subtypes (luminal, HER2-enriched, and triple-negative) to guide treatment and prognosis. Traditional subtyping methods, such as gene profiling and immunohistochemistry, are invasive and limited by intratumoural heterogeneity. MRI radiomics analysis offers a non-invasive alternative by extracting quantitative imaging features, yet its application in diverse, multi-ethnic populations remains underexplored. This study aimed to identify predictive radiomic features from multiple MRI sequences to classify breast cancer subtypes, compare the performance of four MRI sequences, and determine the optimal machine learning (ML) model for this task. A total of 162 retrospective breast cancer MRI cases were semi-automatically segmented, and 256 radiomic features were extracted. A multimodal ML framework integrating random forest and recursive feature elimination was developed to identify the most predictive features based on the area under the receiver operating characteristic curve (AUROC). Key predictive features included age, tumour size, margin characteristics, and intensity patterns within the tumour. Among MRI sequences, inversion recovery and T1 post-contrast performed best for subtyping. In addition, texture-based ML models effectively emulated visual assessment, demonstrating the potential of radiomics in non-invasive breast cancer subtyping. With the top ten features, the AUROC values are 0.735, 0.630, and 0.747 for luminal, HER2-enriched, and triple-negative, respectively. These findings highlight the role of MRI-based texture features and advanced ML in enhancing breast cancer diagnosis, offering a non-invasive tool for personalised treatment planning while complementing existing clinical workflows.

Tumor-infiltrating lymphocytes (TILs) are key immune biomarkers associated with prognosis and treatment response in early-stage breast cancer (BC), particularly in the triple-negative subtype. This study aimed to evaluate whether [18F]FDG PET/CT imaging and routine cell blood count (CBC)-derived biomarkers can serve as non-invasive surrogates for TILs, using machine-learning models. We retrospectively analyzed 358 patients with biopsy-proven early-stage invasive BC who underwent pre-treatment [18F]FDG PET/CT imaging. PET-derived biomarkers were extracted from the primary tumor, lymph nodes, and lymphoid organs (spleen and bone marrow). CBC-derived biomarkers included neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR). TILs were assessed histologically and categorized as low (0-10%), intermediate (11-59%), or high (≥ 60%). Correlations were assessed using Spearman's rank coefficient, and classification and regression models were built using several machine-learning algorithms. Tumor SUVmax and tumor SUVmean showed the highest correlation with TIL levels (ρ = 0.29 and 0.30 respectively, p < 0.001 for both), but overall associations between TILs and PET or CBC-derived biomarkers were weak. No CBC-derived biomarker showed significant correlation or discriminative performance. Machine-learning models failed to predict TIL levels with satisfactory accuracy (maximum balanced accuracy = 0.66). Lymphoid organ metrics (SLR, BLR) and CBC-derived parameters did not significantly enhance predictive value. In this study, neither [18F]FDG PET/CT nor routine CBC-derived biomarkers reliably predict TILs levels in early-stage BC. This observation was made in presence of potential scanner-related variability and for a restricted set of usual PET metrics. Future models should incorporate more targeted imaging approaches, such as immunoPET, to non-invasively assess immune infiltration with higher specificity and improve personalized treatment strategies.

Artificial intelligence (AI) applications hold great promise for improving accuracy and efficiency in medical imaging diagnostics. However, despite the expected benefit of AI applications, widespread adoption of the technology is progressing slower than expected due to technological, organizational, and regulatory obstacles, and user-related barriers, with physicians playing a central role in adopting AI applications. This study aims to provide guidance on enabling physicians to make an informed adoption decision regarding AI applications by identifying and discussing measures to address key barriers from physicians' perspectives. We used a 2-step qualitative research approach. First, we conducted a structured literature review by screening 865 papers to identify potential enabling measures. Second, we interviewed 14 experts to evaluate the literature-based measures and enriched them. By analyzing the literature and interview transcripts, we revealed 11 measures, categorized into Enabling Adoption Decision Measures (eg, educating physicians, preparing future physicians, and providing transparency) and Supporting Adoption Measures (eg, implementation guidelines and AI marketplaces). These measures aim to inform physicians' decisions and support the adoption process. This study provides a comprehensive overview of measures to enable physicians to make an informed adoption decision on AI applications in medical imaging diagnostics. Thereby, we are the first to give specific recommendations on how to realize the potential of AI applications in medical imaging diagnostics from a user perspective.

This study aimed to systematically review the current performance of large language models (LLMs) in dento-maxillofacial radiology (DMFR). Five electronic databases were used to identify studies that developed, fine-tuned, or evaluated LLMs for DMFR-related tasks. Data extracted included study purpose, LLM type, images/text source, applied language, dataset characteristics, input and output, performance outcomes, evaluation methods, and reference standards. Customized assessment criteria adapted from the TRIPOD-LLM reporting guideline were used to evaluate the risk-of-bias in the included studies specifically regarding the clarity of dataset origin, the robustness of performance evaluation methods, and the validity of the reference standards. The initial search yielded 1621 titles, and nineteen studies were included. These studies investigated the use of LLMs for tasks including the production and answering of DMFR-related qualification exams and educational questions (n = 8), diagnosis and treatment recommendations (n = 7), and radiology report generation and patient communication (n = 4). LLMs demonstrated varied performance in diagnosing dental conditions, with accuracy ranging from 37-92.5% and expert ratings for differential diagnosis and treatment planning between 3.6-4.7 on a 5-point scale. For DMFR-related qualification exams and board-style questions, LLMs achieved correctness rates between 33.3-86.1%. Automated radiology report generation showed moderate performance with accuracy ranging from 70.4-81.3%. LLMs demonstrate promising potential in DMFR, particularly for diagnostic, educational, and report generation tasks. However, their current accuracy, completeness, and consistency remain variable. Further development, validation, and standardization are needed before LLMs can be reliably integrated as supportive tools in clinical workflows and educational settings.

In this review, a comprehensive overview of the current state of artificial intelligence (AI) research in Inflammatory Bowel Disease (IBD) diagnostics in the domains of endoscopy, radiology and histology is presented. Moreover, key considerations for development of AI algorithms in medical image analysis are discussed. AI presents a potential breakthrough in real-time, objective and rapid endoscopic assessment, with implications for predicting disease progression. It is anticipated that, by harmonising multimodal data, AI will transform patient care through early diagnosis, accurate patient profiling and therapeutic response prediction. The ability of AI in cross-sectional medical imaging to improve diagnostic accuracy, automate and enable objective assessment of disease activity and predict clinical outcomes highlights its transformative potential. AI models have consistently outperformed traditional methods of image interpretation, particularly in complex areas such as differentiating IBD subtypes, identifying disease progression and complications. The use of AI in histology is a particularly dynamic research field. Implementation of AI algorithms in clinical practice is still lagging, a major hurdle being the lack of a digital workflow in many pathology institutes. Adoption is likely to start with implementation of automatic disease activity scoring. Beyond matching pathologist performance, algorithms may teach us more about IBD pathophysiology. While AI is set to substantially advance IBD diagnostics, various challenges such as heterogeneous datasets, retrospective designs and assessment of different endpoints must be addressed. Implementation of novel standards of reporting may drive an increase in research quality and overcome these obstacles.

We aimed to quantify hepatic vessel volumes across chronic liver disease stages and healthy controls using deep learning-based magnetic resonance imaging (MRI) analysis, and assess correlations with biomarkers for liver (dys)function and fibrosis/portal hypertension. We assessed retrospectively healthy controls, non-advanced and advanced chronic liver disease (ACLD) patients using a 3D U-Net model for hepatic vessel segmentation on portal venous phase gadoxetic acid-enhanced 3-T MRI. Total (TVVR), hepatic (HVVR), and intrahepatic portal vein-to-volume ratios (PVVR) were compared between groups and correlated with: albumin-bilirubin (ALBI) and "model for end-stage liver disease-sodium" (MELD-Na) score) and fibrosis/portal hypertension (Fibrosis-4 (FIB-4) Score, liver stiffness measurement (LSM), hepatic venous pressure gradient (HVPG), platelet count (PLT), and spleen volume. We included 197 subjects, aged 54.9 ± 13.8 years (mean ± standard deviation), 111 males (56.3%): 35 healthy controls, 44 non-ACLD, and 118 ACLD patients. TVVR and HVVR were highest in controls (3.9; 2.1), intermediate in non-ACLD (2.8; 1.7), and lowest in ACLD patients (2.3; 1.0) (p ≤ 0.001). PVVR was reduced in both non-ACLD and ACLD patients (both 1.2) compared to controls (1.7) (p ≤ 0.001), but showed no difference between CLD groups (p = 0.999). HVVR significantly correlated indirectly with FIB-4, ALBI, MELD-Na, LSM, and spleen volume (ρ ranging from -0.27 to -0.40), and directly with PLT (ρ = 0.36). TVVR and PVVR showed similar but weaker correlations. Deep learning-based hepatic vessel volumetry demonstrated differences between healthy liver and chronic liver disease stages and shows correlations with established markers of disease severity. Hepatic vessel volumetry demonstrates differences between healthy liver and chronic liver disease stages, potentially serving as a non-invasive imaging biomarker. Deep learning-based vessel analysis can provide automated quantification of hepatic vascular changes across healthy liver and chronic liver disease stages. Automated quantification of hepatic vasculature shows significantly reduced hepatic vascular volume in advanced chronic liver disease compared to non-advanced disease and healthy liver. Decreased hepatic vascular volume, particularly in the hepatic venous system, correlates with markers of liver dysfunction, fibrosis, and portal hypertension.