BackgroundManual data curation was necessary to extract radiology reports due to the ambiguities of natural language.PurposeTo develop a fine-tuned large language model that classifies computed tomography (CT)-guided interventional radiology reports into technique categories and to compare its performance with that of the readers.Material and MethodsThis retrospective study included patients who underwent CT-guided interventional radiology between August 2008 and November 2024. Patients were chronologically assigned to the training (n = 1142; 646 men; mean age = 64.1 ± 15.7 years), validation (n = 131; 83 men; mean age = 66.1 ± 16.1 years), and test (n = 332; 196 men; mean age = 66.1 ± 14.8 years) datasets. In establishing a reference standard, reports were manually classified into categories 1 (drainage), 2 (lesion biopsy within fat or soft tissue density tissues), 3 (lung biopsy), and 4 (bone biopsy). The bi-directional encoder representation from the transformers model was fine-tuned with the training dataset, and the model with the best performance in the validation dataset was selected. The performance and required time for classification in the test dataset were compared between the best-performing model and the two readers.ResultsCategories 1/2/3/4 included 309/367/270/196, 30/42/40/19, and 75/124/78/55 patients for the training, validation, and test datasets, respectively. The model demonstrated an accuracy of 0.979 in the test dataset, which was significantly better than that of the readers (0.922-0.940) (<i>P</i> ≤0.012). The model classified reports within a 49.8-53.5-fold shorter time compared to readers.ConclusionThe fine-tuned large language model classified CT-guided interventional radiology reports into four categories demonstrating high accuracy within a remarkably short time.

Virtual dental implant placement in cone-beam computed tomography (CBCT) is a prerequisite for digital implant surgery, carrying clinical significance. However, manual placement is a complex process that should meet clinical essential requirements of restoration orientation, bone adaptation, and anatomical safety. This complexity presents challenges in balancing multiple considerations comprehensively and automating the entire workflow efficiently. This study aims to achieve intelligent virtual dental implant placement through a 3-dimensional (3D) segmentation strategy. Focusing on the missing mandibular first molars, we developed a segmentation module based on nnU-Net to generate the virtual implant from the edentulous region of CBCT and employed an approximation module for mathematical optimization. The generated virtual implant was integrated with the original CBCT to meet clinical requirements. A total of 190 CBCT scans from 4 centers were collected for model development and testing. This tool segmented the virtual implant with a surface Dice coefficient (sDice) of 0.903 and 0.884 on internal and external testing sets. Compared to the ground truth, the average deviations of the implant platform, implant apex, and angle were 0.850 ± 0.554 mm, 1.442 ± 0.539 mm, and 4.927 ± 3.804° on the internal testing set and 0.822 ± 0.353 mm, 1.467 ± 0.560 mm, and 5.517 ± 2.850° on the external testing set, respectively. The 3D segmentation-based artificial intelligence tool demonstrated good performance in predicting both the dimension and position of the virtual implants, showing significant clinical application potential in implant planning.

Retinal fundus imaging is crucial for diagnosing and monitoring eye diseases, which are often linked to systemic health conditions such as diabetes and hypertension. Current deep learning techniques often narrowly focus on segmenting retinal blood vessels, lacking a more comprehensive analysis and characterization of the retinal vascular system. This study fills this gap by proposing a novel, integrated approach that leverages multiple stages to accurately determine vessel paths and extract informative features from them. The segmentation of veins and arteries, achieved through a deep semantic segmentation network, is used by a newly designed algorithm to reconstruct individual vessel paths. The reconstruction process begins at the optic disc, identified by a localization network, and uses a recurrent neural network to predict the vessel paths at various junctions. The different stages of the proposed approach are validated both qualitatively and quantitatively, demonstrating robust performance. The proposed approach enables the extraction of critical features at the individual vessel level, such as vessel tortuosity and diameter. This work lays the foundation for a comprehensive retinal image evaluation, going beyond isolated tasks like vessel segmentation, with significant potential for clinical diagnosis.

Deep learning-based medical image classification techniques are rapidly advancing in medical image analysis, making it crucial to develop accurate and trustworthy models that can be efficiently deployed across diverse clinical scenarios. Concept Bottleneck Models (CBMs), which first predict a set of explainable concepts from images and then perform classification based on these concepts, are increasingly being adopted for explainable medical image classification. However, the inherent explainability of CBMs introduces new challenges when deploying trained models to new environments. Variations in imaging protocols and staining methods may induce concept-level shifts, such as alterations in color distribution and scale. Furthermore, since CBM training requires explicit concept annotations, fine-tuning models solely with image-level labels could compromise concept prediction accuracy and faithfulness - a critical limitation given the high cost of acquiring expert-annotated concept labels in medical domains. To address these challenges, we propose a training-free confusion concept identification strategy. By leveraging minimal new data (e.g., 4 images per class) with only image-level labels, our approach enhances out-of-domain performance without sacrificing source domain accuracy through two key operations: masking misactivated confounding concepts and amplifying under-activated discriminative concepts. The efficacy of our method is validated on both skin and white blood cell images. Our code is available at: https://github.com/riverback/TF-TTI-XMed.

Thyroid cancer is among the most common cancers in the United States. Thyroid nodules are frequently detected through ultrasound (US) imaging, and some require further evaluation via fine-needle aspiration (FNA) biopsy. Despite its effectiveness, FNA often leads to unnecessary biopsies of benign nodules, causing patient discomfort and anxiety. To address this, the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) has been developed to reduce benign biopsies. However, such systems are limited by interobserver variability. Recent deep learning approaches have sought to improve risk stratification, but they often fail to utilize the rich temporal and spatial context provided by US cine clips, which contain dynamic global information and surrounding structural changes across various views. In this work, we propose the Spatio-Temporal Cross Attention for Cine Thyroid Ultrasound Time Series Classification (STACT-Time) model, a novel representation learning framework that integrates imaging features from US cine clips with features from segmentation masks automatically generated by a pretrained model. By leveraging self-attention and cross-attention mechanisms, our model captures the rich temporal and spatial context of US cine clips while enhancing feature representation through segmentation-guided learning. Our model improves malignancy prediction compared to state-of-the-art models, achieving a cross-validation precision of 0.91 (plus or minus 0.02) and an F1 score of 0.89 (plus or minus 0.02). By reducing unnecessary biopsies of benign nodules while maintaining high sensitivity for malignancy detection, our model has the potential to enhance clinical decision-making and improve patient outcomes.

With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tokens for medical image segmentation tasks. Specifically, we propose a simple hybrid structure that integrates a pre-trained, frozen LLM layer within the CNN encoder-decoder segmentation framework (LLM4Seg). Surprisingly, this design improves segmentation performance with a minimal increase in trainable parameters across various modalities, including ultrasound, dermoscopy, polypscopy, and CT scans. Our in-depth analysis reveals the potential of transferring LLM's semantic awareness to enhance segmentation tasks, offering both improved global understanding and better local modeling capabilities. The improvement proves robust across different LLMs, validated using LLaMA and DeepSeek.

Federated learning has significantly advanced distributed training of machine learning models across decentralized data sources. However, existing frameworks often lack comprehensive solutions that combine uncertainty quantification, interpretability, and robustness. To address this, we propose FedNAM+, a federated learning framework that integrates Neural Additive Models (NAMs) with a novel conformal prediction method to enable interpretable and reliable uncertainty estimation. Our method introduces a dynamic level adjustment technique that utilizes gradient-based sensitivity maps to identify key input features influencing predictions. This facilitates both interpretability and pixel-wise uncertainty estimates. Unlike traditional interpretability methods such as LIME and SHAP, which do not provide confidence intervals, FedNAM+ offers visual insights into prediction reliability. We validate our approach through experiments on CT scan, MNIST, and CIFAR datasets, demonstrating high prediction accuracy with minimal loss (e.g., only 0.1% on MNIST), along with transparent uncertainty measures. Visual analysis highlights variable uncertainty intervals, revealing low-confidence regions where model performance can be improved with additional data. Compared to Monte Carlo Dropout, FedNAM+ delivers efficient and global uncertainty estimates with reduced computational overhead, making it particularly suitable for federated learning scenarios. Overall, FedNAM+ provides a robust, interpretable, and computationally efficient framework that enhances trust and transparency in decentralized predictive modeling.

Diseases underlying osteolytic lesions in jaws are characterized by the absorption of bone tissue and are often asymptomatic, delaying their diagnosis. Well-defined lesions (benign cyst-like lesions) and ill-defined lesions (osteomyelitis or malignancy) can be detected early in a panoramic radiograph (PR) by an experienced examiner, but most dentists lack appropriate training. To support dentists, this study aimed to develop and evaluate deep learning models for the detection of osteolytic lesions in PRs. A dataset of 676 PRs (165 well-defined, 181 ill-defined, 330 control) was collected from the Department of Oral and Maxillofacial Surgery at Charité Berlin, Germany. The osteolytic lesions were pixel-wise segmented and labeled as well-defined or ill-defined. Four model architectures for instance segmentation (Mask R-CNN with a Swin-Tiny or ResNet-50 backbone, Mask DINO, and YOLOv5) were employed with five-fold cross-validation. Their effectiveness was evaluated with sensitivity, specificity, F1-score, and AUC and failure cases were shown. Mask R-CNN with a Swin-Tiny backbone was most effective (well-defined F1 = 0.784, AUC = 0.881; ill-defined F1 = 0.904, AUC = 0.971) and the model architectures including vision transformer components were more effective than those without. Model mistakes were observed around the maxillary sinus, at tooth extraction sites, and for radiolucent bands. Promising deep learning models were developed for the detection of osteolytic lesions in PRs, particularly those with vision transformer components (Mask R-CNN with Swin-Tiny and Mask DINO). These results underline the potential of vision transformers for enhancing the automated detection of osteolytic lesions, offering a significant improvement over traditional deep learning models.

LLMs have demonstrated significant potential in Medical Report Generation (MRG), yet their development requires large amounts of medical image-report pairs, which are commonly scattered across multiple centers. Centralizing these data is exceptionally challenging due to privacy regulations, thereby impeding model development and broader adoption of LLM-driven MRG models. To address this challenge, we present FedMRG, the first framework that leverages Federated Learning (FL) to enable privacy-preserving, multi-center development of LLM-driven MRG models, specifically designed to overcome the critical challenge of communication-efficient LLM training under multi-modal data heterogeneity. To start with, our framework tackles the fundamental challenge of communication overhead in FL-LLM tuning by employing low-rank factorization to efficiently decompose parameter updates, significantly reducing gradient transmission costs and making LLM-driven MRG feasible in bandwidth-constrained FL settings. Furthermore, we observed the dual heterogeneity in MRG under the FL scenario: varying image characteristics across medical centers, as well as diverse reporting styles and terminology preferences. To address this, we further enhance FedMRG with (1) client-aware contrastive learning in the MRG encoder, coupled with diagnosis-driven prompts, which capture both globally generalizable and locally distinctive features while maintaining diagnostic accuracy; and (2) a dual-adapter mutual boosting mechanism in the MRG decoder that harmonizes generic and specialized adapters to address variations in reporting styles and terminology. Through extensive evaluation of our established FL-MRG benchmark, we demonstrate the generalizability and adaptability of FedMRG, underscoring its potential in harnessing multi-center data and generating clinically accurate reports while maintaining communication efficiency.

Artificial intelligence (AI) is becoming increasingly popular in medicine. The current study aims to investigate whether an AI-based chatbot, such as ChatGPT, could be a valid tool for assisting in decision-making when assessing mandibular third molars before extractions. Panoramic radiographs were collected from a publicly available library. Mandibular third molars were assessed by position and depth. Two specialists evaluated each case regarding the need for CBCT referral, followed by introducing all cases to ChatGPT under a uniform script to decide the need for further CBCT radiographs. The process was performed first without any guidelines, Second, after introducing the guidelines presented by Rood et al. (1990), and third, with additional test cases. ChatGPT and a specialist's decision were compared and analyzed using Cohen's kappa test and the Cochrane-Mantel--Haenszel test to consider the effect of different tooth positions. All analyses were made under a 95% confidence level. The study evaluated 184 molars. Without any guidelines, ChatGPT correlated with the specialist in 49% of cases, with no statistically significant agreement (kappa < 0.1), followed by 70% and 91% with moderate (kappa = 0.39) and near-perfect (kappa = 0.81) agreement, respectively, after the second and third rounds (p < 0.05). The high correlation between the specialist and the chatbot was preserved when analyzed by the different tooth locations and positions (p < 0.01). ChatGPT has shown the ability to analyze third molars prior to surgical interventions using accepted guidelines with substantial correlation to specialists.