The standard approach to diagnosing idiopathic pulmonary fibrosis (IPF) includes identifying the usual interstitial pneumonia (UIP) pattern via high resolution computed tomography (HRCT) or lung biopsy and excluding known causes of interstitial lung disease (ILD). However, limitations of manual interpretation of lung imaging, along with other reasons such as lack of relevant knowledge and non-specific symptoms have hindered the timely diagnosis of IPF. This review proposes the definition of early IPF, emphasizes the diagnostic urgency of early IPF, and highlights current diagnostic strategies and future prospects for early IPF. The integration of artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), is revolutionizing the diagnostic procedure of early IPF by standardizing and accelerating the interpretation of thoracic images. Innovative bronchoscopic techniques such as transbronchial lung cryobiopsy (TBLC), genomic classifier, and endobronchial optical coherence tomography (EB-OCT) provide less invasive diagnostic alternatives. In addition, chest auscultation, serum biomarkers, and susceptibility genes are pivotal for the indication of early diagnosis. Ongoing research is essential for refining diagnostic methods and treatment strategies for early IPF.

Artificial intelligence (AI) is transforming medical imaging, with large language models such as ChatGPT-4 emerging as potential tools for automated image interpretation. While AI-driven radiomics has shown promise in diagnostic imaging, the efficacy of ChatGPT-4 in liver ultrasound analysis remains largely unexamined. This study evaluates the capability of ChatGPT-4 in liver ultrasound radiomics, specifically its ability to differentiate fibrosis, steatosis, and normal liver tissue, compared to conventional image analysis software. Seventy grayscale ultrasound images from a preclinical liver disease model, including fibrosis (n=31), fatty liver (n=18), and normal liver (n=21), were analyzed. ChatGPT-4 extracted texture features, which were compared to those obtained using Interactive Data Language (IDL), a traditional image analysis software. One-way ANOVA was used to identify statistically significant features differentiating liver conditions, and logistic regression models were employed to assess diagnostic performance. ChatGPT-4 extracted nine key textural features-echo intensity, heterogeneity, skewness, kurtosis, contrast, homogeneity, dissimilarity, angular second moment, and entropy-all of which significantly differed across liver conditions (p < 0.05). Among individual features, echo intensity achieved the highest F1-score (0.85). When combined, ChatGPT-4 attained 76% accuracy and 83% sensitivity in classifying liver disease. ROC analysis demonstrated strong discriminatory performance, with AUC values of 0.75 for fibrosis, 0.87 for normal liver, and 0.97 for steatosis. Compared to Interactive Data Language (IDL) image analysis software, ChatGPT-4 exhibited slightly lower sensitivity (0.83 vs. 0.89) but showed moderate correlation (R = 0.68, p < 0.0001) with IDL-derived features. However, it significantly outperformed IDL in processing efficiency, reducing analysis time by 40%, highlighting its potential for high throughput radiomic analysis. Despite slightly lower sensitivity than IDL, ChatGPT-4 demonstrated high feasibility for ultrasound radiomics, offering faster processing, high-throughput analysis, and automated multi-image evaluation. These findings support its potential integration into AI-driven imaging workflows, with further refinements needed to enhance feature reproducibility and diagnostic accuracy.

Large language models (LLMs) are increasingly used by physicians for diagnostic support. A key advantage of LLMs is the ability to generate explanations that can help physicians understand the reasoning behind a diagnosis. However, the best-suited format for LLM-generated explanations remains unclear. In this large-scale study, we examined the effect of different formats for LLM explanations on clinical decision-making. For this, we conducted a randomized experiment with radiologists reviewing patient cases with radiological images (N = 2020 assessments). Participants received either no LLM support (control group) or were supported by one of three LLM-generated explanations: (1) a standard output providing the diagnosis without explanation; (2) a differential diagnosis comparing multiple possible diagnoses; or (3) a chain-of-thought explanation offering a detailed reasoning process for the diagnosis. We find that the format of explanations significantly influences diagnostic accuracy. The chain-of-thought explanations yielded the best performance, improving the diagnostic accuracy by 12.2% compared to the control condition without LLM support (P = 0.001). The chain-of-thought explanations are also superior to the standard output without explanation (+7.2%; P = 0.040) and the differential diagnosis format (+9.7%; P = 0.004). We further assessed the robustness of these findings across case difficulty and different physician backgrounds such as general vs. specialized radiologists. Evidently, explaining the reasoning for a diagnosis helps physicians to identify and correct potential errors in LLM predictions and thus improve overall decisions. Altogether, the results highlight the importance of how explanations in medical LLMs are generated to maximize their utility in clinical practice. By designing explanations to support the reasoning processes of physicians, LLMs can improve diagnostic performance and, ultimately, patient outcomes.

Multi-modal medical image fusion (MMIF) is increasingly recognized as an essential technique for enhancing diagnostic precision and facilitating effective clinical decision-making within computer-aided diagnosis systems. MMIF combines data from X-ray, MRI, CT, PET, SPECT, and ultrasound to create detailed, clinically useful images of patient anatomy and pathology. These integrated representations significantly advance diagnostic accuracy, lesion detection, and segmentation. This comprehensive review meticulously surveys the evolution, methodologies, algorithms, current advancements, and clinical applications of MMIF. We present a critical comparative analysis of traditional fusion approaches, including pixel-, feature-, and decision-level methods, and delves into recent advancements driven by deep learning, generative models, and transformer-based architectures. A critical comparative analysis is presented between these conventional methods and contemporary techniques, highlighting differences in robustness, computational efficiency, and interpretability. The article addresses extensive clinical applications across oncology, neurology, and cardiology, demonstrating MMIF's vital role in precision medicine through improved patient-specific therapeutic outcomes. Moreover, the review thoroughly investigates the persistent challenges affecting MMIF's broad adoption, including issues related to data privacy, heterogeneity, computational complexity, interpretability of AI-driven algorithms, and integration within clinical workflows. It also identifies significant future research avenues, such as the integration of explainable AI, adoption of privacy-preserving federated learning frameworks, development of real-time fusion systems, and standardization efforts for regulatory compliance.

Multimodal medical image fusion plays a crucial role in medical diagnosis by integrating complementary information from different modalities to enhance image readability and clinical applicability. However, existing methods mainly follow computer vision standards for feature extraction and fusion strategy formulation, overlooking the rich semantic information inherent in medical images. To address this limitation, we propose a novel semantic-guided medical image fusion approach that, for the first time, incorporates medical prior knowledge into the fusion process. Specifically, we construct a publicly available multimodal medical image-text dataset, upon which text descriptions generated by BiomedGPT are encoded and semantically aligned with image features in a high-dimensional space via a semantic interaction alignment module. During this process, a cross attention based linear transformation automatically maps the relationship between textual and visual features to facilitate comprehensive learning. The aligned features are then embedded into a text-injection module for further feature-level fusion. Unlike traditional methods, we further generate diagnostic reports from the fused images to assess the preservation of medical information. Additionally, we design a medical semantic loss function to enhance the retention of textual cues from the source images. Experimental results on test datasets demonstrate that the proposed method achieves superior performance in both qualitative and quantitative evaluations while preserving more critical medical information.

The Segment Anything Model (SAM) was fine-tuned on the EchoNet-Dynamic dataset and evaluated on external transthoracic echocardiography (TTE) and Point-of-Care Ultrasound (POCUS) datasets from CAMUS (University Hospital of St Etienne) and Mayo Clinic (99 patients: 58 TTE, 41 POCUS). Fine-tuned SAM was superior or comparable to MedSAM. The fine-tuned SAM also outperformed EchoNet and U-Net models, demonstrating strong generalization, especially on apical 2-chamber (A2C) images (fine-tuned SAM vs. EchoNet: CAMUS-A2C: DSC 0.891 {+/-} 0.040 vs. 0.752 {+/-} 0.196, p<0.0001) and POCUS (DSC 0.857 {+/-} 0.047 vs. 0.667 {+/-} 0.279, p<0.0001). Additionally, SAM-enhanced workflow reduced annotation time by 50% (11.6 {+/-} 4.5 sec vs. 5.7 {+/-} 1.7 sec, p<0.0001) while maintaining segmentation quality. We demonstrated an effective strategy for fine-tuning a vision foundation model for enhancing clinical workflow efficiency and supporting human-AI collaboration.

Voice disorders (VD) are often linked to vocal fold structural pathologies (VFSP). Laryngeal imaging plays a vital role in assessing VFSPs and VD in clinical and research settings, but challenges like scarce and imbalanced datasets can limit the generalizability of findings. Denoising Diffusion Probabilistic Models (DDPMs), a subtype of Generative AI, has gained attention for its ability to generate high-quality and realistic synthetic images to address these challenges. This study explores the feasibility of improving VFSP image classification by generating synthetic images using DDPMs. 404 laryngoscopic images depicting VF without and with VFSP were included. DDPMs were used to generate synthetic images to augment the original dataset. Two convolutional neural network architectures, VGG16 and ResNet50, were applied for model training. The models were initially trained only on the original dataset. Then, they were trained on the augmented datasets. Evaluation metrics were analyzed to assess the performance of the models for both binary classification (with/without VFSPs) and multi-class classification (seven specific VFSPs). Realistic and high-quality synthetic images were generated for dataset augmentation. The model first failed to converge when trained only on the original dataset, but they successfully converged and achieved low loss and high accuracy when trained on the augmented datasets. The best performance was gained for both binary and multi-class classification when the models were trained on an augmented dataset. Generating realistic images of VFSP using DDPMs is feasible and can enhance the classification of VFSPs by an AI model and may support VD screening and diagnosis.

The application of AI for predicting critical heart failure endpoints using echocardiography is a promising avenue to improve patient care and treatment planning. However, fully supervised training of deep learning models in medical imaging requires a substantial amount of labelled data, posing significant challenges due to the need for skilled medical professionals to annotate image sequences. Our study addresses this limitation by exploring the potential of self-supervised learning, emphasising interpretability, robustness, and safety as crucial factors in cardiac imaging analysis. We leverage self-supervised learning on a large unlabelled dataset, facilitating the discovery of features applicable to a various downstream tasks. The backbone model not only generates informative features for training smaller models using simple techniques but also produces features that are interpretable by humans. The study employs a modified Self-supervised Transformer with Energy-based Graph Optimisation (STEGO) network on top of self-DIstillation with NO labels (DINO) as a backbone model, pre-trained on diverse medical and non-medical data. This approach facilitates the generation of self-segmented outputs, termed "parcels", which identify distinct anatomical sub-regions of the heart. Our findings highlight the robustness of these self-learned parcels across diverse patient profiles and phases of the cardiac cycle phases. Moreover, these parcels offer high interpretability and effectively encapsulate clinically relevant cardiac substructures. We conduct a comprehensive evaluation of the proposed self-supervised approach on publicly available datasets, demonstrating its adaptability to a wide range of requirements. Our results underscore the potential of self-supervised learning to address labelled data scarcity in medical imaging, offering a path to improve cardiac imaging analysis and enhance the efficiency and interpretability of diagnostic procedures, thus positively impacting patient care and clinical decision-making.

Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image scenarios, real-world clinical applications often involve sequential images, where accurate lesion localization across different modalities and temporal tracking of disease progression (e.g., pre- vs. post-treatment comparison) require fine-grained cross-image semantic alignment and context-aware reasoning. To remedy the underrepresentation of image sequences in existing medical visual grounding benchmarks, we propose MedSG-Bench, the first benchmark tailored for Medical Image Sequences Grounding. It comprises eight VQA-style tasks, formulated into two paradigms of the grounding tasks, including 1) Image Difference Grounding, which focuses on detecting change regions across images, and 2) Image Consistency Grounding, which emphasizes detection of consistent or shared semantics across sequential images. MedSG-Bench covers 76 public datasets, 10 medical imaging modalities, and a wide spectrum of anatomical structures and diseases, totaling 9,630 question-answer pairs. We benchmark both general-purpose MLLMs (e.g., Qwen2.5-VL) and medical-domain specialized MLLMs (e.g., HuatuoGPT-vision), observing that even the advanced models exhibit substantial limitations in medical sequential grounding tasks. To advance this field, we construct MedSG-188K, a large-scale instruction-tuning dataset tailored for sequential visual grounding, and further develop MedSeq-Grounder, an MLLM designed to facilitate future research on fine-grained understanding across medical sequential images. The benchmark, dataset, and model are available at https://huggingface.co/MedSG-Bench

This study evaluates the performance, cost, and processing time of OpenAI's reasoning large language models (LLMs) (o1-preview, o1-mini) and their base models (GPT-4o, GPT-4o-mini) on Japanese radiology board examination questions. A total of 210 questions from the 2022-2023 official board examinations of the Japan Radiological Society were presented to each of the four LLMs. Performance was evaluated by calculating the percentage of correctly answered questions within six predefined radiology subspecialties. The total cost and processing time for each model were also recorded. The McNemar test was used to assess the statistical significance of differences in accuracy between paired model responses. The o1-preview achieved the highest accuracy (85.7%), significantly outperforming GPT-4o (73.3%, P<.001). Similarly, o1-mini (69.5%) performed significantly better than GPT-4o-mini (46.7%, P<.001). Across all radiology subspecialties, o1-preview consistently ranked highest. However, reasoning models incurred substantially higher costs (o1-preview: $17.10, o1-mini: $2.58) compared to their base counterparts (GPT-4o: $0.496, GPT-4o-mini: $0.04), and their processing times were approximately 3.7 and 1.2 times longer, respectively. Reasoning LLMs demonstrated markedly superior performance in answering radiology board exam questions compared to their base models, albeit at a substantially higher cost and increased processing time.