Generating high-fidelity dental radiographs is essential for training diagnostic models. Despite the development of numerous methods for other medical data, generative approaches in dental radiology remain unexplored. Due to the intricate tooth structures and specialized terminology, these methods often yield ambiguous tooth regions and incorrect dental concepts when applied to dentistry. In this paper, we take the first attempt to investigate diffusion-based teeth X-ray image generation and propose ToothMaker, a novel framework specifically designed for the dental domain. Firstly, to synthesize X-ray images that possess accurate tooth structures and realistic radiological styles simultaneously, we design control-disentangled fine-tuning (CDFT) strategy. Specifically, we present two separate controllers to handle style and layout control respectively, and introduce a gradient-based decoupling method that optimizes each using their corresponding disentangled gradients. Secondly, to enhance model's understanding of dental terminology, we propose prior-disentangled guidance module (PDGM), enabling precise synthesis of dental concepts. It utilizes large language model to decompose dental terminology into a series of meta-knowledge elements and performs interactions and refinements through hypergraph neural network. These elements are then fed into the network to guide the generation of dental concepts. Extensive experiments demonstrate the high fidelity and diversity of the images synthesized by our approach. By incorporating the generated data, we achieve substantial performance improvements on downstream segmentation and visual question answering tasks, indicating that our method can greatly reduce the reliance on manually annotated data. Code will be public available at https://github.com/CUHK-AIM-Group/ToothMaker.

AI is rapidly transforming abdominal radiology. This scoping review mapped current applications across segmentation, detection, classification, prediction, and workflow optimization based on 432 studies published between 2019 and 2024. Most studies focused on CT imaging, with fewer involving MRI, ultrasound, or X-ray. Segmentation models (e.g., U-Net) performed well in liver and pancreatic imaging (Dice coefficient 0.65-0.90). Classification models (e.g., ResNet, DenseNet) were commonly used for diagnostic labeling, with reported sensitivities ranging from 52 to 100% and specificities from 40.7 to 99%. A small number of studies employed true object detection models (e.g., YOLOv3, YOLOv7, Mask R-CNN) capable of spatial lesion localization, marking an emerging trend toward localization-based AI. Predictive models demonstrated AUCs between 0.62 and 0.99 but often lacked interpretability and external validation. Workflow optimization studies reported improved efficiency (e.g., reduced report turnaround and scan repetition), though standardized benchmarks were often missing. Major gaps identified include limited real-world validation, underuse of non-CT modalities, and unclear regulatory pathways. Successful clinical integration will require robust validation, practical implementation, and interdisciplinary collaboration.

This study aimed to develop a fully automated 3D multi-modal deep learning model using preoperative ¹⁸F-FDG PET/CT to predict the T-stage of colorectal cancer (CRC) and evaluate its clinical utility. A retrospective cohort of 474 CRC patients was included, with 400 patients for internal cohort and 74 patients for external cohort. Patients were classified into early T-stage (T1-T2) and advanced T-stage (T3-T4) groups. Automatic segmentation of the volume of interest (VOI) was achieved based on TotalSegmentator. A 3D ResNet18-based deep learning model integrated with a cross-multi-head attention mechanism was developed. Five models (CT + PET + Clinic (CPC), CT + PET (CP), PET (P), CT (C), Clinic) and two radiologists' assessment were compared. Performance was evaluated using Area Under the Curve (AUC). Grad-CAM was employed to provide visual interpretability of decision-critical regions. The automated segmentation achieved Dice scores of 0.884 (CT) and 0.888 (PET). The CPC and CP models achieved superior performance, with AUCs of 0.869 and 0.869 in the internal validation cohort, respectively, outperforming single-modality models (P: 0.832; C: 0.809; Clinic: 0.728) and the radiologists (AUC: 0.627, P < 0.05 for all models vs. radiologists, except for the Clinical model). External validation exhibited a similar trend, with AUCs of 0.814, 0.812, 0.763, 0.714, 0.663 and 0.704, respectively. Grad-CAM visualization highlighted tumor-centric regions for early T-stage and peri-tumoral tissue infiltration for advanced T-stage. The fully automated multimodal, fusing PET/CT with cross-multi-head-attention, improved T-stage prediction in CRC, surpassing the single-modality models and radiologists, offering a time-efficient tool to aid clinical decision-making.

The lower image contrast of megavoltage computed tomography (MVCT), which corresponds to kilovoltage computed tomography (kVCT), can inhibit accurate dosimetric assessments. This study proposes a deep learning approach, specifically the pix2pix network, to generate high-quality synthetic kVCT (skVCT) images from MVCT data. The model was trained on a dataset of 25 paired patient images and evaluated on a test set of 15 paired images. We performed visual inspections to assess the quality of the generated skVCT images and calculated the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Dosimetric equivalence was evaluated by comparing the gamma pass rates of treatment plans derived from skVCT and kVCT images. Results showed that skVCT images exhibited significantly higher quality than MVCT images, with PSNR and SSIM values of 31.9 ± 1.1 dB and 94.8% ± 1.3%, respectively, compared to 26.8 ± 1.7 dB and 89.5% ± 1.5% for MVCT-to-kVCT comparisons. Furthermore, treatment plans based on skVCT images achieved excellent gamma pass rates of 99.78 ± 0.14% and 99.82 ± 0.20% for 2 mm/2% and 3 mm/3% criteria, respectively, comparable to those obtained from kVCT-based plans (99.70 ± 0.31% and 99.79 ± 1.32%). This study demonstrates the potential of pix2pix models for generating high-quality skVCT images, which could significantly enhance Adaptive Radiation Therapy (ART).

Elevated intracranial pressure (ICP) is a serious condition that demands prompt diagnosis to avoid significant neurological injury or even death. Although invasive techniques remain the "gold standard" for ICP measuring, they are time-consuming and pose risks of complications. Various noninvasive methods have been suggested, but their experimental status limits their use in emergency situations. On the other hand, although artificial intelligence has rapidly evolved, it has not yet fully harnessed fast-acquisition modalities such as computed tomography (CT) scans to evaluate ICP. This is likely due to the lack of available annotated data sets. In this article, we present research that addresses this gap by training four distinct deep learning models on a custom data set, enhanced with demographical and Glasgow Coma Scale (GCS) values. A key innovation of our study is the incorporation of demographical data and GCS values as additional channels of the scans. The models were trained and validated on a custom data set consisting of paired CT brain scans (n = 578) with corresponding ICP values, supplemented by GCS scores and demographical data. The algorithm addresses a binary classification problem by predicting whether ICP levels exceed a predetermined threshold of 15 mm Hg. The top-performing models achieved an area under the curve of 88.3% and a recall of 81.8%. An algorithm that enhances the transparency of the model's decisions was used to provide insights into where the models focus when generating outcomes, both for the best and lowest-performing models. This study demonstrates the potential of AI-based models to evaluate ICP levels from brain CT scans with high recall. Although promising, further improvements are necessary in the future to validate these findings and improve clinical applicability.

Clinical information associated with chest X-ray images, such as view position, patient age and gender, plays a crucial role in image interpretation, as it influences the visibility of anatomical structures and pathologies. However, most classification models using the ChestX-ray14 dataset relied solely on image data, disregarding the impact of these clinical variables. This study aims to investigate which clinical variable affects image characteristics and assess its impact on classification performance. To explore the relationships between clinical variables and image characteristics, unsupervised clustering was applied to group images based on their similarities. Afterwards, a statistical analysis was then conducted on each cluster to examine their clinical composition, by analyzing the distribution of age, gender, and view position. An attention-based CNN model was developed separately for each value of the clinical variable with the greatest influence on image characteristics to assess its impact on lung disease classification. The analysis identified view position as the most influential variable affecting image characteristics. Accounting for this, the proposed approach achieved a weighted area under the curve (AUC) of 0.8176 for pneumonia classification, surpassing the base model (without considering view position) by 1.65% and outperforming previous studies by 6.76%. Furthermore, it demonstrated improved performance across all 14 diseases in the ChestX-ray14 dataset. The findings highlight the importance of considering view position when developing classification models for chest X-ray analysis. Accounting for this characteristic allows for more precise disease identification, demonstrating potential for broader clinical application in lung disease evaluation.

Deep learning (DL) models have achieved remarkable performance in musculoskeletal (MSK) medical imaging research, yet their clinical integration remains hindered by their black-box nature and the absence of reliable confidence measures. Uncertainty quantification (UQ) seeks to bridge this gap by providing each DL prediction with a calibrated estimate of uncertainty, thereby fostering clinician trust and safer deployment. We conducted a targeted narrative review, performing expert-driven searches in PubMed, Scopus, and arXiv and mining references from relevant publications in MSK imaging utilizing UQ, and a thematic synthesis was used to derive a cohesive taxonomy of UQ methodologies. UQ approaches encompass multi-pass methods (e.g., test-time augmentation, Monte Carlo dropout, and model ensembling) that infer uncertainty from variability across repeated inferences; single-pass methods (e.g., conformal prediction, and evidential deep learning) that augment each individual prediction with uncertainty metrics; and other techniques that leverage auxiliary information, such as inter-rater variability, hidden-layer activations, or generative reconstruction errors, to estimate confidence. Applications in MSK imaging, include highlighting uncertain areas in cartilage segmentation and identifying uncertain predictions in joint implant design detections; downstream applications include enhanced clinical utility and more efficient data annotation pipelines. Embedding UQ into DL workflows is essential for translating high-performance models into clinical practice. Future research should prioritize robust out-of-distribution handling, computational efficiency, and standardized evaluation metrics to accelerate the adoption of trustworthy AI in MSK medicine. Not applicable.

ObjectiveDetecting and accurately diagnosing rib fractures in chest radiographs is a challenging and time-consuming task for radiologists. This study presents a novel deep learning system designed to automate the detection and segmentation of rib fractures in chest radiographs.MethodsThe proposed method combines CenterNet with HRNet v2 for precise fracture region identification and HRNet-W48 with contextual representation to enhance rib segmentation. A dataset consisting of 1006 chest radiographs from a tertiary hospital in Korea was used, with a split of 7:2:1 for training, validation, and testing.ResultsThe rib fracture detection component achieved a sensitivity of 0.7171, indicating its effectiveness in identifying fractures. Additionally, the rib segmentation performance was measured by a dice score of 0.86, demonstrating its accuracy in delineating rib structures. Visual assessment results further highlight the model's capability to pinpoint fractures and segment ribs accurately.ConclusionThis innovative approach holds promise for improving rib fracture detection and rib segmentation, offering potential benefits in clinical practice for more efficient and accurate diagnosis in the field of medical image analysis.

Incorrectly placed endotracheal tubes (ETTs) can lead to serious clinical harm. Studies have demonstrated the potential for artificial intelligence (AI)-led algorithms to detect ETT placement on chest X-Ray (CXR) images, however their effect on clinician accuracy remains unexplored. This study measured the impact of an AI-assisted ETT detection algorithm on the ability of clinical staff to correctly identify ETT misplacement on CXR images. Four hundred CXRs of intubated adult patients were retrospectively sourced from the John Radcliffe Hospital (Oxford) and two other UK NHS hospitals. Images were de-identified and selected from a range of clinical settings, including the intensive care unit (ICU) and emergency department (ED). Each image was independently reported by a panel of thoracic radiologists, whose consensus classification of ETT placement (correct, too low [distal], or too high [proximal]) served as the reference standard for the study. Correct ETT position was defined as the tip located 3-7 cm above the carina, in line with established guidelines. Eighteen clinical readers of varying seniority from six clinical specialties were recruited across four NHS hospitals. Readers viewed the dataset using an online platform and recorded a blinded classification of ETT position for each image. After a four-week washout period, this was repeated with assistance from an AI-assisted image interpretation tool. Reader accuracy, reported confidence, and timings were measured during each study phase. 14,400 image interpretations were undertaken. Pooled accuracy for tube placement classification improved from 73.6 to 77.4% (p = 0.002). Accuracy for identification of critically misplaced tubes increased from 79.3 to 89.0% (p = 0.001). Reader confidence improved with AI assistance, with no change in mean interpretation time at 36 s per image. Use of assistive AI technology improved accuracy and confidence in interpreting ETT placement on CXR, especially for identification of critically misplaced tubes. AI assistance may potentially provide a useful adjunct to support clinicians in identifying misplaced ETTs on CXR.

This study aimed to develop an interpretable machine learning model integrating delayed-phase contrast-enhanced CT radiomics with clinical features for noninvasive prediction of pathological grading in appendiceal pseudomyxoma peritonei (PMP), using Shapley Additive Explanations (SHAP) for model interpretation. This retrospective study analyzed 158 pathologically confirmed PMP cases (85 low-grade, 73 high-grade) from January 4, 2015 to April 30, 2024. Comprehensive clinical data including demographic characteristics, serum tumor markers (CEA, CA19-9, CA125, D-dimer, CA-724, CA-242), and CT-peritoneal cancer index (CT-PCI) were collected. Radiomics features were extracted from preoperative contrast-enhanced CT scans using standardized protocols. After rigorous feature selection and five-fold cross-validation, we developed three predictive models: clinical-only, radiomics-only, and a combined clinical-radiomics model using logistic regression. Model performance was evaluated through ROC analysis (AUC), Delong test, decision curve analysis (DCA), and Brier score, with SHAP values providing interpretability. The combined model demonstrated superior performance, achieving AUCs of 0.91 (95%CI:0.86-0.95) and 0.88 (95%CI:0.82-0.93) in training and testing sets respectively, significantly outperforming standalone models (P < 0.05). DCA confirmed greater clinical utility across most threshold probabilities, with favorable Brier scores (training:0.124; testing:0.142) indicating excellent calibration. SHAP analysis identified the top predictive features: wavelet-LHH_glcm_InverseVariance (radiomics), original_shape_Elongation (radiomics), and CA-199 (clinical). Our SHAP-interpretable combined model provides an accurate, noninvasive tool for PMP grading, facilitating personalized treatment decisions. The integration of radiomics and clinical data demonstrates superior predictive performance compared to conventional approaches, with potential to improve patient outcomes.