The objective of this study was to explore the potential of machine-learning techniques in the automatic identification and classification of brain metastases from a radiomic perspective, aiming to improve the accuracy of tumor volume assessment for radiotherapy. By using various machine-learning algorithms, including random forest, support vector machine, gradient boosting machine, XGBoost, decision tree, artificial neural network, k-nearest neighbors, LightGBM, and CatBoost algorithms, a stacking ensemble model was developed to classify gross tumor volume (GTV), brainstem, and normal brain tissue based on radiomic features. Multiple evaluation metrics, including the specificity, sensitivity, negative predictive value, positive predictive value, accuracy, Matthews correlation coefficient, and the Youden index, were used to assess the model’s performance. The stacked ensemble model integrated the strengths of the nine base models and consistently outperformed individual base models in classifying GTV (area under the curve [AUC] = 0.928), brainstem (AUC = 0.932), and normal brain tissue (AUC = 0.942). Among the base models, the support vector machine model demonstrated the best performance in the three classifications (AUC = 0.922, 0.909, and 0.928). The higher performance of the stacked ensemble model highlighted the low performance of other models, including the decision tree (AUC = 0.709, 0.706, 0.804) and k-nearest neighbors (AUC = 0.721, 0.663, 0.729) models in certain contexts, such as when faced with high-dimensional feature spaces. While machine learning shows significant promise in medical image analysis, relying solely on a single model may lead to suboptimal results. By combining the strengths of various algorithms, the stacking ensemble model offers a better solution for the classification of brain metastases based on radiomic features.

Objective: Surface‐guided radiation therapy (SGRT, AlignRT) was used to analyze motion during stereotactic body radiotherapy (SBRT) in lung cancer patients and to explore the margin of the planning target volume (PTV).Methods: The residual errors of the AlignRT were evaluated based on grayscale cone‐beam computed tomography registration results before each treatment. AlignRT log file was used to analyze the correlation between the frequency and longest duration of errors larger than 2 mm and lasting longer than 2 s and maximum error with age and treatment duration. The displacement value at the end of treatment, the average displacement value, and the 95% probability density displacement interval were defined as intrafraction errors, and PTV1, PTV2, PTV3 were calculated by Van Herk formula or Z score analysis. Organ dosimetric differences were compared after the experience‐based margin was replaced with PTV3.Results: The interfraction residual errors were Vrt₀, 0.06 ± 0.18 cm; Lng₀, ‐0.03 ± 0.19 cm; Lat₀, 0.02 ± 0.15 cm; Pitch₀, 0.23 ± 0.7°; Roll₀, 0.1 ± 0.69°; Rtn₀, ‐0.02 ± 0.79°. The frequency, longest duration and maximum error in vertical direction were correlated with treatment duration (r = 0.404, 0.353, 0.283, p < 0.05, respectively). In the longitudinal direction, the frequency was correlated with age and treatment duration (r = 0.376, 0.283, p < 0.05, respectively), maximum error was correlated with age (r = 0.4, P < 0.05). Vertical, longitudinal, lateral margins of PTV1, PTV2, PTV3 were 2 mm, 4 mm, 2 mm; 2 mm, 2 mm, 2 mm, 3 mm, 5 mm, 3 mm, respectively. After replacing the original PTV, mean lung dose (MLD), 2‐cm³ chest wall dose (CD), lung V₂₀ decreased by 0.2 Gy, 2.1 Gy, 0.5%, respectively (p < 0.05).Conclusion: AlignRT can be used for interfraction setup and monitoring intrafraction motion. It is more reasonable to use upper and lower limits of the 95% probability density interval as an intrafraction error.

Brain metastases are common complications in patients with cancer and significantly affect prognosis and treatment strategies. The accurate segmentation of brain metastases is crucial for effective radiation therapy planning. However, in resource-limited areas, the unavailability of MRI imaging is a significant challenge that necessitates the development of reliable segmentation models for computed tomography images (CT). This study aimed to develop and evaluate a Diffusion-CSPAM-U-Net model for the segmentation of brain metastases on CT images and thereby provide a robust tool for radiation oncologists in regions where magnetic resonance imaging (MRI) is not accessible. The proposed Diffusion-CSPAM-U-Net model integrates diffusion models with channel-spatial-positional attention mechanisms to enhance the segmentation performance. The model was trained and validated on a dataset consisting of CT images from two centers (n = 205) and (n = 45). Performance metrics, including the Dice similarity coefficient (DSC), intersection over union (IoU), accuracy, sensitivity, and specificity, were calculated. Additionally, this study compared models proposed for brain metastases of different sizes with those proposed in other studies. The diffusion-CSPAM-U-Net model achieved promising results on the external validation set. Overall average DSC of 79.3% ± 13.3%, IoU of 69.2% ± 13.3%, accuracy of 95.5% ± 11.8%, sensitivity of 80.3% ± 12.1%, specificity of 93.8% ± 14.0%, and HD of 5.606 ± 0.990 mm were measured. These results demonstrate favorable improvements over existing models. The diffusion-CSPAM-U-Net model showed promising results in segmenting brain metastases in CT images, particularly in terms of sensitivity and accuracy. The proposed diffusion-CSPAM-U-Net model provides an effective tool for radiation oncologists for the segmentation of brain metastases in CT images.

This study aimed to develop an automated classification framework for distinguishing between cervical cancer tumor and normal uterine tissue, leveraging CT images for radiomics feature extraction. We retrospectively analyzed CT images from 117 cervical cancer patients. To distinguish between cancerous and healthy tissue, we segmented gross tumor volume and normal uterine tissue as distinct regions of interest (ROIs) using manual segmentation techniques. Key radiomic parameters were extracted from these ROIs. To bolster model's predictive capability, the data was stratified into train data (70%) and validation data (30%). During feature selection phase, we applied Least Absolute Shrinkage and Selection Operator regression algorithm to identify most relevant features. Subsequently, we built classification models using five state-of-the-art machine learning algorithms: Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), and Decision Tree (DT). Ultimately, the performance of each model was evaluated. Through stringent feature selection process, we identified 18 pivotal radiomic features for classification of cervical cancer and normal uterine tissue. When applied to test data, all five models achieved excellent performance, with area under the curve (AUC) values ranging from 0.8866 to 0.9190 (SVM: 0.9144, RF: 0.9078, KNN: 0.9051, DT: 0.8866, XGBoost: 0.9190), all surpassing threshold of 0.8. In terms of test data, all five models had high sensitivity; accuracy of SVM, RF, and XGBoost models was comparable; and specificity of five models was similar. XGBoost model outperformed the others in terms of diagnostic accuracy, achieving an AUC of 0.8737 (95% CI: 0.8198-0.9277) for train data and 0.9190 (95% CI: 0.8525-0.9854) for test data. Our findings underscore the potential of CT radiomics combined with machine learning algorithms for accurately classifying cervical cancer tumors and normal uterine tissue with high recognition capabilities. This approach holds significant promise for clinical diagnostics.

Accurate delineation of Gross Tumor Volume (GTV) in lung cancer is critical for effective radiotherapy and surgical planning. However, segmentation of GTV in high-resolution CT images remains challenging, particularly when tumors are small or have indistinct boundaries. We propose D-S-Net, a novel dual-stage strategy to enhance both the accuracy and efficiency of lung cancer GTV segmentation. In the first stage, a simplified detection network is used to locate candidate regions in high-resolution (512×512) CT slices, reducing input size and computational demand. In the second stage, a modified U-Net variant is applied to perform fine segmentation within the detected regions. The architecture incorporates a spatial attention mechanism and employs a combined loss function (binary cross-entropy and Dice loss) to address class imbalance. On the lung cancer GTV dataset, D-S-Net achieved a Dice coefficient of 78.52%, representing an improvement of 5.49% over SwinU-Net and outperforming several mainstream models. On the second dataset, D-S-Net reached a Dice coefficient of 86.56%, surpassing the second-best model by 13.19%. Ablation studies demonstrated that the detection stage, spatial attention, and combined loss function effectively improved performance, while computational complexity analysis confirmed the model’s efficiency. The proposed D-S-Net offers a robust and efficient solution for the segmentation of lung cancer GTV in CT images. Its dual-stage design and attention-based enhancements contribute to both accuracy and computational gains, highlighting its potential for clinical applications in radiotherapy planning.

Background: Kidney cancer remains a significant challenge in oncology, with accurate prognostic assessment being crucial for postoperative management. While radiomics has shown promise in cancer prognosis, there is limited research on comprehensive models that effectively integrate radiomic features with clinical parameters for kidney cancer survival prediction. Objective: This study aimed to develop and validate a comprehensive computed tomography (CT) radiomics-based nomogram for predicting overall survival in postoperative patients with kidney cancer by integrating radiomic features with clinical parameters. Methods: Radiomic features were extracted from regions of interest in CT images of 207 postoperative patients with kidney cancer. The eigenvalue data of all radiomic features were processed using z score standardization and the R software package GLMNet. We integrated survival time, survival status, and radiomic features and screened these features using the least absolute shrinkage and selection operator–Cox regression method. We conducted 10-fold cross-validation to obtain an optimal model of 5 radiomic features. Multivariate Cox regression hazard models were established to analyze patients’ overall survival. The predictive ability of the nomogram (receiver operating characteristic curve and calibration curve) was evaluated using bootstrap resampling validation. Patients were divided into high- and low-risk groups based on the radiomic risk score cutoff value, and the Kaplan-Meier method was conducted to identify established models’ forecasting ability. Five radiomic features were screened for predictive model construction. Results: This retrospective analysis was conducted from April 2024 to July 2024 using data from The Cancer Imaging Archive public database. The final cohort included 207 patients (3 excluded from the initial 210) who underwent nephrectomy for kidney cancer. The median follow-up time was 33 (IQR 11-47) months. The receiver operating characteristic curve and area under the curve showed that the predictive model performed well. The calibration curve of nomogram and radiomic features in the cohort study set indicated an overall net benefit. Kaplan-Meier curves indicated that overall survival time was dramatically shorter in the high-risk group. Conclusions: Our radiomics nomogram successfully integrates CT-derived radiomic features with clinical variables for kidney cancer survival prediction, demonstrating good prognostic capability and offering a noninvasive, quantitative tool for personalized postoperative management and clinical decision-making.