Deep learning has been widely used in research on sparse-view computed tomography (CT) image reconstruction. While sufficient training data can lead to high accuracy, collecting medical images is often challenging due to legal or ethical concerns, making it necessary to develop methods that perform well with limited data. To address this issue, we explored the use of nonmedical images for pre-training. Therefore, in this study, we investigated whether fractal images could improve the quality of sparse-view CT images, even with a reduced number of medical images. Fractal images generated by an iterated function system (IFS) were used for nonmedical images, and medical images were obtained from the CHAOS dataset. Sinograms were then generated using 36 projections in sparse-view and the images were reconstructed by filtered back-projection (FBP). FBPConvNet and WNet (first module: learning fractal images, second module: testing medical images, and third module: learning output) were used as networks. The effectiveness of pre-training was then investigated for each network. The quality of the reconstructed images was evaluated using two indices: structural similarity (SSIM) and peak signal-to-noise ratio (PSNR). The network parameters pre-trained with fractal images showed reduced artifacts compared to the network trained exclusively with medical images, resulting in improved SSIM. WNet outperformed FBPConvNet in terms of PSNR. Pre-training WNet with fractal images produced the best image quality, and the number of medical images required for main-training was reduced from 5000 to 1000 (80% reduction). Using fractal images for network training can reduce the number of medical images required for artifact reduction in sparse-view CT. Therefore, fractal images can improve accuracy even with a limited amount of training data in deep learning.

Hepatocellular carcinoma (HCC) is an aggressive cancer with limited biomarkers for predicting immunotherapy response. Recent advancements in large language models (LLMs) like GPT-4, GPT-4o, and Gemini offer the potential for enhancing clinical decision-making through multimodal data analysis. However, their effectiveness in predicting immunotherapy response, especially compared to human experts, remains unclear. This study assessed the performance of GPT-4, GPT-4o, and Gemini in predicting immunotherapy response in unresectable HCC, compared to radiologists and oncologists of varying expertise. A retrospective analysis of 186 patients with unresectable HCC utilized multimodal data (clinical and CT images). LLMs were evaluated with zero-shot prompting and two strategies: the 'voting method' and the 'OR rule method' for improved sensitivity. Performance metrics included accuracy, sensitivity, area under the curve (AUC), and agreement across LLMs and physicians.GPT-4o, using the 'OR rule method,' achieved 65% accuracy and 47% sensitivity, comparable to intermediate physicians but lower than senior physicians (accuracy: 72%, p = 0.045; sensitivity: 70%, p < 0.0001). Gemini-GPT, combining GPT-4, GPT-4o, and Gemini, achieved an AUC of 0.69, similar to senior physicians (AUC: 0.72, p = 0.35), with 68% accuracy, outperforming junior and intermediate physicians while remaining comparable to senior physicians (p = 0.78). However, its sensitivity (58%) was lower than senior physicians (p = 0.0097). LLMs demonstrated higher inter-model agreement (κ = 0.59-0.70) than inter-physician agreement, especially among junior physicians (κ = 0.15). This study highlights the potential of LLMs, particularly Gemini-GPT, as valuable tools in predicting immunotherapy response for HCC.

CBCT has become an essential tool in orthodontics, although its use must remain judicious and evidence-based. This study provides an updated analysis of international recommendations concerning the use of CBCT in orthodontics, with a particular focus on clinical indications, radiation dose reduction, and recent technological advancements. A systematic review of guidelines published between 2015 and 2025 was conducted following the PRISMA methodology. Inclusion criteria comprised official directives from recognized scientific societies and clinical studies evaluating low dose protocols in orthodontics. The analysis of the 19 retained recommendations reveals a consensus regarding the primary indications for CBCT in orthodontics, particularly for impacted teeth, skeletal anomalies, periodontal and upper airways assessment. Dose optimization and the integration of artificial intelligence emerge as major advancements, enabling significant radiation reduction while preserving diagnostic accuracy. The development of low dose protocols and advanced reconstruction algorithms presents promising perspectives for safer and more efficient imaging, increasingly replacing conventional 2D radiographic techniques. However, an international harmonization of recommendations for these new imaging sequences is imperative to standardize clinical practices and enhance patient radioprotection.

The aim of this study was to develop and validate CT venous phase image-based radiomics to predict BRAF gene mutation status in preoperative colorectal cancer patients. In this study, 301 patients with pathologically confirmed colorectal cancer were retrospectively enrolled, comprising 225 from Centre I (73 mutant and 152 wild-type) and 76 from Centre II (36 mutant and 40 wild-type). The Centre I cohort was randomly divided into a training set (n = 158) and an internal validation set (n = 67) in a 7:3 ratio, while Centre II served as an independent external validation set (n = 76). The whole tumor region of interest was segmented, and radiomics characteristics were extracted. To explore whether tumor expansion could improve the performance of the study objectives, the tumor contour was extended by 3 mm in this study. Finally, a t-test, Pearson correlation, and LASSO regression were used to screen out features strongly associated with BRAF mutations. Based on these features, six classifiers-Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost)-were constructed. The model performance and clinical utility were evaluated using receiver operating characteristic (ROC) curves, decision curve analysis, accuracy, sensitivity, and specificity. Gender was an independent predictor of BRAF mutations. The unexpanded RF model, constructed using 11 imaging histologic features, demonstrated the best predictive performance. For the training cohort, it achieved an AUC of 0.814 (95% CI 0.732-0.895), an accuracy of 0.810, and a sensitivity of 0.620. For the internal validation cohort, it achieved an AUC of 0.798 (95% CI 0.690-0.907), an accuracy of 0.761, and a sensitivity of 0.609. For the external validation cohort, it achieved an AUC of 0.737 (95% CI 0.616-0.847), an accuracy of 0.658, and a sensitivity of 0.667. A machine learning model based on CT radiomics can effectively predict BRAF mutations in patients with colorectal cancer. The unexpanded RF model demonstrated optimal predictive performance.

To investigate the clinical efficiency of an AI-based metal artefact correction algorithm (AI-MAC), for reducing dental metal artefacts in head and neck CT, compared to conventional interpolation-based MAC. We retrospectively collected 41 patients with non-removal dental hardware who underwent non-contrast head and neck CT prior to radiotherapy. All images were reconstructed with standard reconstruction algorithm (SRA), and were additionally processed with both conventional MAC and AI-MAC. The image quality of SRA, MAC and AI-MAC were compared by qualitative scoring on a 5-point scale, with scores ≥ 3 considered interpretable. This was followed by a quantitative evaluation, including signal-to-noise ratio (SNR) and artefact index (Idxartefact). Organ contouring accuracy was quantified via calculating the dice similarity coefficient (DSC) and hausdorff distance (HD) for oral cavity and teeth, using the clinically accepted contouring as reference. Moreover, the treatment planning dose distribution for oral cavity was assessed. AI-MAC yielded superior qualitative image quality as well as quantitative metrics, including SNR and Idxartefact, to SRA and MAC. The image interpretability significantly improved from 41.46% for SRA and 56.10% for MAC to 92.68% for AI-MAC (p < 0.05). Compared to SRA and MAC, the best DSC and HD for both oral cavity and teeth were obtained on AI-MAC (all p < 0.05). No significant differences for dose distribution were found among the three image sets. AI-MAC outperforms conventional MAC in metal artefact reduction, achieving superior image quality with high image interpretability for patients with dental hardware undergoing head and neck CT. Furthermore, the use of AI-MAC improves the accuracy of organ contouring while providing consistent dose calculation against metal artefacts in radiotherapy. AI-MAC is a novel deep learning-based technique for reducing metal artefacts on CT. This in-vivo study first demonstrated its capability of reducing metal artefacts while preserving organ visualization, as compared with conventional MAC.

To compare the diagnostic performance of three proprietary large language models (LLMs)-Claude, GPT, and Gemini-in structuring free-text Japanese radiology reports for intracranial hemorrhage and skull fractures, and to assess the impact of three different prompting approaches on model accuracy. In this retrospective study, head CT reports from the Japan Medical Imaging Database between 2018 and 2023 were collected. Two board-certified radiologists established the ground truth regarding intracranial hemorrhage and skull fractures through independent review and consensus. Each radiology report was analyzed by three LLMs using three prompting strategies-Standard, Chain of Thought, and Self Consistency prompting. Diagnostic performance (accuracy, precision, recall, and F1-score) was calculated for each LLM-prompt combination and compared using McNemar's tests with Bonferroni correction. Misclassified cases underwent qualitative error analysis. A total of 3949 head CT reports from 3949 patients (mean age 59 ± 25 years, 56.2% male) were enrolled. Across all institutions, 856 patients (21.6%) had intracranial hemorrhage and 264 patients (6.6%) had skull fractures. All nine LLM-prompt combinations achieved very high accuracy. Claude demonstrated significantly higher accuracy for intracranial hemorrhage than GPT and Gemini, and also outperformed Gemini for skull fractures (p < 0.0001). Gemini's performance improved notably with Chain of Thought prompting. Error analysis revealed common challenges including ambiguous phrases and findings unrelated to intracranial hemorrhage or skull fractures, underscoring the importance of careful prompt design. All three proprietary LLMs exhibited strong performance in structuring free-text head CT reports for intracranial hemorrhage and skull fractures. While the choice of prompting method influenced accuracy, all models demonstrated robust potential for clinical and research applications. Future work should refine the prompts and validate these approaches in prospective, multilingual settings.

The application of artificial intelligence (AI) technology has realized the transformation of people's production and lifestyle, and also promoted the rapid development of the medical field. At present, the application of intelligence in the medical field is increasing. Using its advanced methods and technologies of AI, this paper aims to realize the integration of medical imaging-aided diagnosis system and AI, which is helpful to analyze and solve the loopholes and errors of traditional artificial diagnosis in the diagnosis of pulmonary nodules. Drawing on the principles and rules of image segmentation methods, the construction and optimization of a medical image-aided diagnosis system is carried out to realize the precision of the diagnosis system in the diagnosis of pulmonary nodules. In the diagnosis of pulmonary nodules carried out by traditional artificial and medical imaging-assisted diagnosis systems, 231 nodules with pathology or no change in follow-up for more than two years were also tested in 200 cases. The results showed that the AI software detected a total of 881 true nodules with a sensitivity of 99.10% (881/889). The radiologists detected 385 true nodules with a sensitivity of 43.31% (385/889). The sensitivity of AI software in detecting non-calcified nodules was significantly higher than that of radiologists (99.01% vs 43.30%, P < 0.001), and the difference was statistically significant.

To explore whether a CT-based AI framework, leveraging multi-scale features, can offer a non-invasive approach to accurately predict pathological grade and Ki67 index in clear cell renal cell carcinoma (ccRCC). In this multicenter retrospective study, a total of 1073 pathologically confirmed ccRCC patients from seven cohorts were split into internal cohorts (training and validation sets) and an external test set. The AI framework comprised an image processor, a 3D-kidney and tumor segmentation model by 3D-UNet, a multi-scale features extractor built upon unsupervised learning, and a multi-task classifier utilizing XGBoost. A quantitative model interpretation technique, known as SHapley Additive exPlanations (SHAP), was employed to explore the contribution of multi-scale features. The 3D-UNet model showed excellent performance in segmenting both the kidney and tumor regions, with Dice coefficients exceeding 0.92. The proposed multi-scale features model exhibited strong predictive capability for pathological grading and Ki67 index, with AUROC values of 0.84 and 0.87, respectively, in the internal validation set, and 0.82 and 0.82, respectively, in the external test set. The SHAP results demonstrated that features from radiomics, the 3D Auto-Encoder, and dimensionality reduction all made significant contributions to both prediction tasks. The proposed AI framework, leveraging multi-scale features, accurately predicts the pathological grade and Ki67 index of ccRCC. The CT-based AI framework leveraging multi-scale features offers a promising avenue for accurately predicting the pathological grade and Ki67 index of ccRCC preoperatively, indicating a direction for non-invasive assessment. Non-invasively determining pathological grade and Ki67 index in ccRCC could guide treatment decisions. The AI framework integrates segmentation, classification, and model interpretation, enabling fully automated analysis. The AI framework enables non-invasive preoperative detection of high-risk tumors, assisting clinical decision-making.

Diagnosis of peritoneal invasion, lymph node metastasis, and hepatic metastasis is crucial in the decision-making process of ovarian tumor treatment. This study aimed to test the feasibility of low-dose abdominopelvic CT with an artificial intelligence iterative reconstruction (AIIR) for diagnosing peritoneal invasion, lymph node metastasis, and hepatic metastasis in pre-operative imaging of ovarian tumor. This study prospectively enrolled 88 patients with pathology-confirmed ovarian tumors, where routine-dose CT at portal venous phase (120 kVp/ref. 200 mAs) with hybrid iterative reconstruction (HIR) was followed by a low-dose scan (120 kVp/ref. 40 mAs) with AIIR. The performance of diagnosing peritoneal invasion and lymph node metastasis was assessed using receiver operating characteristic (ROC) analysis with pathological results serving as the reference. The hepatic parenchymal metastases were diagnosed and signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured. The perihepatic structures were also scored on the clarity of porta hepatis, gallbladder fossa and intersegmental fissure. The effective dose of low-dose CT was 79.8% lower than that of routine-dose scan (2.64 ± 0.46 vs. 13.04 ± 2.25 mSv, p < 0.001). The low-dose AIIR showed similar area under the ROC curve (AUC) with routine-dose HIR for diagnosing both peritoneal invasion (0.961 vs. 0.960, p = 0.734) and lymph node metastasis (0.711 vs. 0.715, p = 0.355). The 10 hepatic parenchymal metastases were all accurately diagnosed on the two image sets. The low-dose AIIR exhibited higher SNR and CNR for hepatic parenchymal metastases and superior clarity for perihepatic structures. In low-dose pre-operative CT of ovarian tumor, AIIR delivers similar diagnostic accuracy for peritoneal invasion, lymph node metastasis, and hepatic metastasis, as compared to routine-dose abdominopelvic CT. It is feasible and diagnostically safe to apply up to 80% dose reduction in CT imaging of ovarian tumor by using AIIR.

To evaluate the possibility of performing renal vessel reconstruction on non-enhanced CT images using deep learning models. 177 patients' CT scans in the non-enhanced phase, arterial phase and venous phase were chosen. These data were randomly divided into the training set (n = 120), validation set (n = 20) and test set (n = 37). In training set and validation set, a radiologist marked out the right renal arteries and veins on non-enhanced CT phase images using contrast phases as references. Trained deep learning models were tested and evaluated on the test set. A radiologist performed renal vessel reconstruction on the test set without the contrast phase reference, and the results were used for comparison. Reconstruction using the arterial phase and venous phase was used as the gold standard. Without the contrast phase reference, both radiologist and model could accurately identify artery and vein main trunk. The accuracy was 91.9% vs. 97.3% (model vs. radiologist) in artery and 91.9% vs. 100% in vein, the difference was insignificant. The model had difficulty identify accessory arteries, the accuracy was significantly lower than radiologist (44.4% vs. 77.8%, p = 0.044). The model also had lower accuracy in accessory veins, but the difference was insignificant (64.3% vs. 85.7%, p = 0.094). Deep learning models could accurately recognize the right renal artery and vein main trunk, and accuracy was comparable to that of radiologists. Although the current model still had difficulty recognizing small accessory vessels, further training and model optimization would solve these problems.