This study aimed to develop an artificial intelligence (AI) model for automatically detecting Hounsfield unit (HU) values at the L1 vertebra in preoperative thoracolumbar CT scans. This model serves as a screening tool for osteoporosis in patients undergoing spine surgery, offering an alternative to traditional bone mineral density measurement methods like dual-energy x-ray absorptiometry. The authors utilized two CT scan datasets, comprising 501 images, which were split into training, validation, and test subsets. The nnU-Net framework was used for segmentation, followed by an algorithm to calculate HU values from the L1 vertebra. The model's performance was validated against manual HU calculations by expert raters on 56 CT scans. Statistical measures included the Dice coefficient, Pearson correlation coefficient, intraclass correlation coefficient (ICC), and Bland-Altman plots to assess the agreement between AI and human-derived HU measurements. The AI model achieved a high Dice coefficient of 0.91 for vertebral segmentation. The Pearson correlation coefficient between AI-derived HU and human-derived HU values was 0.96, indicating strong agreement. ICC values for interrater reliability were 0.95 and 0.94 for raters 1 and 2, respectively. The mean difference between AI and human HU values was 7.0 HU, with limits of agreement ranging from -21.1 to 35.2 HU. A paired t-test showed no significant difference between AI and human measurements (p = 0.21). The AI model demonstrated strong agreement with human experts in measuring HU values, validating its potential as a reliable tool for automated osteoporosis screening in spine surgery patients. This approach can enhance preoperative risk assessment and perioperative bone health optimization. Future research should focus on external validation and inclusion of diverse patient demographics to ensure broader applicability.

We aimed to evaluate the diagnostic performance of artificial intelligence (AI) in detecting coronary artery stenosis and calcified plaque on CT angiography (CTA), comparing its diagnostic performance with that of radiologists. A thorough search of the literature was performed using PubMed, Web of Science, and Embase, focusing on studies published until October 2024. Studies were included if they evaluated AI models in detecting coronary artery stenosis and calcified plaque on CTA. A bivariate random-effects model was employed to determine combined sensitivity and specificity. Study heterogeneity was assessed using I² statistics. The risk of bias was assessed using the revised quality assessment of diagnostic accuracy studies-2 tool, and the evidence level was graded using the Grading of Recommendations Assessment, Development and Evalutiuon (GRADE) system. Out of 1071 initially identified studies, 17 studies with 5560 patients and images were ultimately included for the final analysis. For coronary artery stenosis ≥50%, AI showed a sensitivity of 0.92 (95% CI: 0.88-0.95), specificity of 0.87 (95% CI: 0.80-0.92), and AUC of 0.96 (95% CI: 0.94-0.97), outperforming radiologists with sensitivity of 0.85 (95% CI: 0.67-0.94), specificity of 0.84 (95% CI: 0.62-0.94), and AUC of 0.91 (95% CI: 0.89-0.93). For stenosis ≥70%, AI achieved a sensitivity of 0.88 (95% CI: 0.70-0.96), specificity of 0.96 (95% CI: 0.90-0.99), and AUC of 0.98 (95% CI: 0.96-0.99). In calcified plaque detection, AI demonstrated a sensitivity of 0.93 (95% CI: 0.84-0.97), specificity of 0.94 (95% CI: 0.88-0.96), and AUC of 0.98 (95% CI: 0.96-0.99)." AI-based CT demonstrated superior diagnostic performance compared to clinicians in identifying ≥50% stenosis in coronary arteries and showed excellent diagnostic performance in recognizing ≥70% coronary artery stenosis and calcified plaque. However, limitations include retrospective study designs and heterogeneity in CTA technologies. Further external validation through prospective, multicenter trials is required to confirm these findings. The original findings of this research are included in the article. For additional inquiries, please contact the corresponding authors.

Chest computed tomography (CT) radiomics can be utilized for categorical predictions; however, models predicting pulmonary function indices directly are lacking. This study aimed to develop machine-learning-based regression models to predict pulmonary function using chest CT radiomics. This retrospective study enrolled patients who underwent chest CT and pulmonary function tests between January 2018 and April 2024. Machine-learning regression models were constructed and validated to predict pulmonary function indices, including forced vital capacity (FVC) and forced expiratory volume in 1 s (FEV₁). The models incorporated radiomics of the whole lung and clinical features. Model performance was evaluated using mean absolute error, mean squared error, root mean squared error, concordance correlation coefficient (CCC), and R-squared (R²) value and compared to spirometry results. Individual explanations of the models' decisions were analyzed using an explainable approach based on SHapley Additive exPlanations. In total, 1585 cases were included in the analysis, with 102 of them being external cases. Across the training, validation, test, and external test sets, the combined model consistently achieved the best performance in the regression task for predicting FVC (e.g. external test set: CCC, 0.745 [95% confidence interval 0.642-0.818]; R², 0.601 [0.453-0.707]) and FEV₁ (e.g. external test set: CCC, 0.744 [0.633-0.824]; R², 0.527 [0.298-0.675]). Age, sex, and emphysema were important factors for both FVC and FEV₁, while distinct radiomics features contributed to each. Whole-lung-based radiomics features can be used to construct regression models to improve pulmonary function prediction.

Diagnosing Parkinson's disease (PD) typically relies on clinical evaluations, often detecting it in advanced stages. Recently, artificial intelligence has increasingly been applied to imaging for neurodegenerative disorders. This study aims to develop a diagnostic prediction model using T1-weighted magnetic resonance imaging (T1-MRI) data from the caudate and putamen in individuals with early-stage PD. This retrospective case-control study included 69 early-stage PD patients and 22 controls, recruited through the Parkinson's Progression Markers Initiative. T1-MRI scans were acquired using a 3-tesla system. 432 radiomic features were extracted from images of the segmented caudate and putâmen in an automated way. Feature selection was performed using Pearson's correlation and recursive feature elimination to identify the most relevant variables. Three machine learning algorithms-random forest (RF), support vector machine and logistic regression-were evaluated for diagnostic prediction effectiveness using a cross-validation method. The Shapley Additive Explanations technique identified the most significant features distinguishing between the groups. The metrics used to evaluate the performance were discrimination, expressed in area under the ROC curve (AUC), sensitivity and specificity; and calibration, expressed as accuracy. The RF algorithm showed superior performance with an average accuracy of 92.85%, precision of 100.00%, sensitivity of 86.66%, specificity of 96.65% and AUC of 0.93. The three most influential features were contrast, elongation, and gray-level non-uniformity, all from the putamen. Machine learning-based models can differentiate early-stage PD from controls using T1-weighted MRI radiomic features.

Prostate imaging reporting and data systems (PI-RADS) experiences considerable variability in inter-reader performance. Artificial Intelligence (AI) algorithms were suggested to provide comparable performance to PI-RADS for assessing prostate cancer (PCa) risk, albeit tested in highly selected cohorts. This study aimed to assess an AI algorithm for PCa detection in a clinical practice setting and simulate integration of the AI model with PI-RADS for assessment of indeterminate PI-RADS 3 lesions. This retrospective cohort study externally validated a biparametric MRI-based AI model for PCa detection in a consecutive cohort of patients who underwent prostate MRI and subsequently targeted and systematic prostate biopsy at a urology clinic between January 2022 and March 2024. Radiologist interpretations followed PI-RADS v2.1, and biopsies were conducted per PI-RADS scores. The previously developed AI model provided lesion segmentations and cancer probability maps which were compared to biopsy results. Additionally, we conducted a simulation to adjust biopsy thresholds for index PI-RADS category 3 studies, where AI predictions within these studies upgraded them to PI-RADS category 4. Among 144 patients with a median age of 70 years and PSA density of 0.17ng/mL/cc, AI's sensitivity for detection of PCa (86.6%) and clinically significant PCa (csPCa, 88.4%) was comparable to radiologists (85.7%, p=0.84, and 89.5%, p=0.80, respectively). The simulation combining radiologist and AI evaluations improved clinically significant PCa sensitivity by 5.8% (p=0.025). The combination of AI, PI-RADS and PSA density provided the best diagnostic performance for csPCa (area under the curve [AUC]=0.76). The AI algorithm demonstrated comparable PCa detection rates to PI-RADS. The combination of AI with radiologist interpretation improved sensitivity and could be instrumental in assessment of low-risk and indeterminate PI-RADS lesions. The role of AI in PCa screening remains to be further elucidated.

Cognitive decline is common in End-Stage Renal Disease (ESRD) patients, yet its neural mechanisms are poorly understood. This study investigates structural and functional brain network reconfiguration in ESRD patients transitioning to Mild Cognitive Impairment (MCI) and evaluates its potential for predicting MCI risk. We enrolled 90 ESRD patients with 2-year follow-up, categorized as MCI converters (MCI_C, n=48) and non-converters (MCI_NC, n=42). Brain networks were constructed using baseline rs-fMRI and high angular resolution diffusion imaging, focusing on regional structural-functional coupling (SFC). A Support Vector Machine (SVM) model was used to identify brain regions associated with cognitive decline. Mediation analysis was conducted to explore the relationship between kidney function, brain network reconfiguration, and cognition. MCI_C patients showed decreased network efficiency in the structural network and compensatory changes in the functional network. Machine learning models using multimodal network features predicted MCI with high accuracy (AUC=0.928 for training set, AUC=0.903 for test set). SHAP analysis indicated that reduced hippocampal SFC was the most significant predictor of MCI_C. Mediation analysis revealed that altered brain network topology, particularly hippocampal SFC, mediated the relationship between kidney dysfunction and cognitive decline. This study provides new insights into the link between kidney function and cognition, offering potential clinical applications for structural and functional MRI biomarkers.

Colorectal cancer remains a major global health challenge, emphasizing the need for advanced diagnostic tools that enable early and accurate detection. Photoacoustic (PA) spectroscopy, a hybrid technique combining optical absorption with acoustic resolution, is emerging as a powerful tool in cancer diagnostics. It detects biochemical changes in biomolecules within the tumor microenvironment, aiding early identification of malignancies. Integration with modalities, such as ultrasound (US), photoacoustic microscopy (PAM), and nanoparticle-enhanced imaging, enables detailed mapping of tissue structure, vascularity, and molecular markers. When combined with endoscopy and machine learning (ML) for data analysis, PA technology offers real-time, minimally invasive, and highly accurate detection of colorectal tumors. This approach supports tumor classification, therapy monitoring, and detecting features like hypoxia and tumor-associated bacteria. Recent studies integrating machine learning with PA imaging have demonstrated high diagnostic accuracy, achieving area under the curve (AUC) values up to 0.96 and classification accuracies exceeding 89%, highlighting its potential for precise, noninvasive colorectal cancer detection. Continued advancements in nanoparticle design, molecular targeting, and ML analytics position PA as a key tool for personalized colorectal cancer management.

This systematic review aimed to assess the performance of artificial intelligence (AI) in the evaluation of maxillary sinus mucosal alterations in imaging examinations compared to human analysis. Studies that presented radiographic images for the diagnosis of paranasal sinus diseases, as well as control groups for AI, were included. Articles that performed tests on animals, presented other conditions, surgical methods, did not present data on the diagnosis of MS or on the outcomes of interest (area under the curve, sensitivity, specificity, and accuracy), compared the outcome only among different AIs were excluded. Searches were conducted in 5 electronic databases and a gray literature. The risk of bias (RB) was assessed using the QUADAS-2 and the certainty of evidence by GRADE. Six studies were included. The type of study considered was retrospective observational; with serious RB, and a considerable heterogeneity in methodologies. The IA presents similar results to humans, however, imprecision was assessed as serious for the outcomes and the certainty of evidence was classified as very low according to the GRADE approach. Furthermore, a dose-response effect was determined, as specialists demonstrate greater mastery of the diagnosis of MS when compared to resident professionals or general clinicians. Considering the outcomes, the AI represents a complementary tool for assessing maxillary mucosal alterations, especially considering professionals with less experience. Finally, performance analysis and definition of comparison parameters should be encouraged considering future research perspectives. AI is a potential complementary tool for assessing maxillary sinus mucosal alterations, however studies are still lacking methodological standardization.

To develop and validate a computed tomography (CT) radiomics-based interpretable machine learning (ML) model for predicting 5-year recurrence-free survival (RFS) in non-metastatic clear cell renal cell carcinoma (ccRCC). 559 patients with non-metastatic ccRCCs were retrospectively enrolled from eight independent institutes between March 2013 and January 2019, and were assigned to the primary set (n=271), external test set 1 (n=216), and external test set 2 (n=72). 1316 Radiomics features were extracted via "Pyradiomics." The least absolute shrinkage and selection operator algorithm was used for feature selection and Rad-Score construction. Patients were stratified into low and high 5-year recurrence risk groups based on Rad-Score, followed by Kaplan-Meier analyses. Five ML models integrating Rad-Score and clinicopathological risk factors were compared. Models' performances were evaluated via the discrimination, calibration, and decision curve analysis. The most robust ML model was interpreted using the SHapley Additive exPlanation (SHAP) method. 13 radiomic features were filtered to produce the Rad-Score, which predicted 5-year RFS with area under the receiver operating characteristic curve (AUCs) of 0.734-0.836. Kaplan-Meier analysis showed significant survival differences based on Rad-Score (all Log-Rank p values <0.05). The random forest model outperformed other models, obtaining AUCs of 0.826 [95% confidential interval (CI): 0.766-0.879] and 0.799 (95% CI: 0.670-0.899) in the external test set 1 and 2, respectively. The SHAP analysis suggested positive associations between contributing factors and 5-year RFS status in non-metastatic ccRCC. CT radiomics-based interpretable ML model can effectively predict 5-year RFS in non-metastatic ccRCC patients, distinguishing between low and high 5-year recurrence risks.

The classification of renal cell carcinoma (RCC) histological subtypes plays a crucial role in clinical diagnosis. However, traditional image normalization methods often struggle with discrepancies arising from differences in imaging parameters, scanning devices, and multi-center data, which can impact model robustness and generalizability. This study included 1628 patients with pathologically confirmed RCC who underwent nephrectomy across eight cohorts. These were divided into a training set, a validation set, external test dataset 1, and external test dataset 2. We proposed an "Aortic Enhancement Normalization" (AEN) method based on the lesion-to-aorta enhancement ratio and developed an automated lesion segmentation model along with a multi-scale CT feature extractor. Several machine learning algorithms, including Random Forest, LightGBM, CatBoost, and XGBoost, were used to build classification models and compare the performance of the AEN and traditional approaches for evaluating histological subtypes (clear cell renal cell carcinoma [ccRCC] vs. non-ccRCC). Additionally, we employed SHAP analysis to further enhance the transparency and interpretability of the model's decisions. The experimental results demonstrated that the AEN method outperformed the traditional normalization method across all four algorithms. Specifically, in the XGBoost model, the AEN method significantly improved performance in both internal and external validation sets, achieving AUROC values of 0.89, 0.81, and 0.80, highlighting its superior performance and strong generalizability. SHAP analysis revealed that multi-scale CT features played a critical role in the model's decision-making process. The proposed AEN method effectively reduces the impact of imaging parameter differences, significantly improving the robustness and generalizability of histological subtype (ccRCC vs. non-ccRCC) models. This approach provides new insights for multi-center data analysis and demonstrates promising clinical applicability.