Dosimetric comparison of helical tomotherapy and volumetric modulated arc therapy in hippocampal avoidance whole-brain radiotherapy.

OBJECTIVE: This study aimed to discuss the dosimetric advantages of helical tomotherapy (HT) and volumetric modulated arc therapy (VMAT) technology in hippocampal avoidance whole-brain radiotherapy and provide references for clinical selection of ideal radiotherapy technology. METHODS: A total of 20 patients with hippocampal avoidance whole-brain radiotherapy were chosen randomly. Computed tomography (CT) and MRI scanning images were input into the treatment planning system (TPS). After the CT and enhanced magnetic resonance T1 weighted images were fused and registered, the same radiation therapy physician was invited to outline the tumor target volume. PTV-HS refers to the whole brain subtracted by 5 mm outward expansion of the hippocampus (HP). The prescribed dose was 30 Gy/10 fractions. HT and VMAT plans were designed for each patient in accordance with PTV. Under the premise that the 95% isodose curve covers the PTV, dose-volume histogram was applied to evaluate the PTV, conformal index (CI), heterogeneity index (HI), maximum dose (Dmax), mean dose (Dmean), minimum dose (Dmin) and absorbed doses of organs at risk (OARs) in HT and VMAT plans. Paired t-test was performed to compare the differences between two radiation therapy plans, and p  <  0.05 was considered statistically significant. RESULTS: These two plans had no significant difference in PTV-HS (max, min, and mean). However, the HI and CI of the HT plan were significantly better than those of the VMAT plan, showing statistically significant difference (p < 0.05). The HT plan was significantly superior to the VMAT plan in terms of the Dmax, Dmin, and Dmean of HP, left and right eye lens, left and right eye, and spinal cord, showing statistically significant difference (p < 0.05). The HT plan was also better than the VMAT plan in terms of the Dmax of the left optic nerve. However, the two plans showed no obvious differences in terms of the absorbed doses of the right optic nerve and brainstem, without statistical significance. CONCLUSIONS: Compared with the VMAT plan of hippocampal avoidance, HT technology has significant dosimetric advantages. HT plans significantly decreased the radiation dose and radiation volume of OARs surrounding the target area (e.g., surrounding eye lens and eye, especially hippocampal avoidance area) while increasing the CI and HI of PTV dose in whole brain radiotherapy (WBRT) greatly, thus enabling the decrease in the incidence rate of radioactive nerve function impairment.

[68Ga]Ga-FAPI PET for the evaluation of digestive system tumors: systematic review and meta-analysis.

PURPOSE: Digestive system tumors are a group of tumors with high incidence in the world nowadays. The assessment of digestive system tumor metastasis by conventional imaging seems to be unsatisfactory. [68Ga]Ga-FAPI, which has emerged in recent years, seems to be able to evaluate digestive system tumor metastasis. We aimed to summarize the current evidence of [68Ga]Ga-FAPI PET/CT or PET/MR for the assessment of primary tumors, lymph node metastases, and distant metastases in digestive system tumors. Besides, we also aimed to perform a meta-analysis of the sensitivity of [68Ga]Ga-FAPI PET diagnosis to discriminate between digestive system tumors, primary lesions, and non-primary lesions (lymph node metastases and distant metastases). MATERIALS AND METHODS: PubMed, MEDLINE and Cochrane Library databases were searched from the beginning of the database build to August 12, 2022. All studies undergoing [68Ga]Ga-FAPI PET for the evaluation of digestive tumors were included in the screening and review. Screening and full text review was performed by 3 investigators and data extraction was performed by 2 investigators. Risk of bias was examined with the QUADAS-2 criteria. Diagnostic test meta-analysis was performed with a random-effects model. RESULTS: A total of 541 studies were retrieved. Finally, 22 studies were selected for the systematic review and 18 studies were included in the meta-analysis. In the 18 publications, a total of 524 patients with digestive system tumors, 459 primary tumor lesions of digestive system tumors, and 1921 metastatic lesions of digestive system tumors were included in the meta-analysis. Based on patients, the sensitivity of [68Ga]Ga-FAPI PET for the diagnosis of digestive system tumors was 0.98 (95% CI: 0.94-0.99). Based on lesions, the sensitivity of [68Ga]Ga-FAPI PET for the diagnostic evaluation of primary tumor lesions of the digestive system was 0.97 (95% CI: 0.93-0.99); the sensitivity of [68Ga]Ga-FAPI PET for the diagnostic evaluation of non-primary lesions (lymph node metastases and distant metastases) of the digestive system tumors was 0.94 (95% CI: 0.79-0.99). CONCLUSION: [68Ga]Ga-FAPI PET has high accuracy and its sensitivity is at a high level for the diagnostic evaluation of digestive system tumors. Clinicians, nuclear medicine physicians, and radiologists may consider using [68Ga]Ga-FAPI PET/CT or PET/MR in the evaluation of primary tumors, lymph node metastases, and distant metastases in digestive system tumors.

Dose prediction of organs at risk in patients with cervical cancer receiving brachytherapy using needle insertion based on a neural network method.

OBJECTIVE: A neural network method was employed to establish a dose prediction model for organs at risk (OAR) in patients with cervical cancer receiving brachytherapy using needle insertion. METHODS: A total of 218 CT-based needle-insertion brachytherapy fraction plans for loco-regionally advanced cervical cancer treatment were analyzed in 59 patients. The sub-organ of OAR was automatically generated by self-written MATLAB, and the volume of the sub-organ was read. Correlations between D2cm3 of each OAR and volume of each sub-organ-as well as high-risk clinical target volume for bladder, rectum, and sigmoid colon-were analyzed. We then established a neural network predictive model of D2cm3 of OAR using the matrix laboratory neural net. Of these plans, 70% were selected as the training set, 15% as the validation set, and 15% as the test set. The regression R value and mean squared error were subsequently used to evaluate the predictive model. RESULTS: The D2cm3/D90 of each OAR was related to volume of each respective sub-organ. The R values for bladder, rectum, and sigmoid colon in the training set for the predictive model were 0.80513, 0.93421, and 0.95978, respectively. The ∆D2cm3/D90 for bladder, rectum, and sigmoid colon in all sets was 0.052 ± 0.044, 0.040 ± 0.032, and 0.041 ± 0.037, respectively. The MSE for bladder, rectum, and sigmoid colon in the training set for the predictive model was 4.779 × 10-3, 1.967 × 10-3 and 1.574 × 10-3, respectively. CONCLUSION: The neural network method based on a dose-prediction model of OAR in brachytherapy using needle insertion was simple and reliable. In addition, it only addressed volumes of sub-organs to predict the dose of OAR, which we believe is worthy of further promotion and application.

Preoperative prediction of cervical cancer survival using a high-resolution MRI-based radiomics nomogram.

BACKGROUND: Cervical cancer patients receiving radiotherapy and chemotherapy require accurate survival prediction methods. The objective of this study was to develop a prognostic analysis model based on a radiomics score to predict overall survival (OS) in cervical cancer patients. METHODS: Predictive models were developed using data from 62 cervical cancer patients who underwent radical hysterectomy between June 2020 and June 2021. Radiological features were extracted from T2-weighted (T2W), T1-weighted (T1W), and diffusion-weighted (DW) magnetic resonance images prior to treatment. We obtained the radiomics score (rad-score) using least absolute shrinkage and selection operator (LASSO) regression and Cox's proportional hazard model. We divided the patients into low- and high-risk groups according to the critical rad-score value, and generated a nomogram incorporating radiological features. We evaluated the model's prediction performance using area under the receiver operating characteristic (ROC) curve (AUC) and classified the participants into high- and low-risk groups based on radiological characteristics. RESULTS: The 62 patients were divided into high-risk (n = 43) and low-risk (n = 19) groups based on the rad-score. Four feature parameters were selected via dimensionality reduction, and the scores were calculated after modeling. The AUC values of ROC curves for prediction of 3- and 5-year OS using the model were 0.84 and 0.93, respectively. CONCLUSION: Our nomogram incorporating a combination of radiological features demonstrated good performance in predicting cervical cancer OS. This study highlights the potential of radiomics analysis in improving survival prediction for cervical cancer patients. However, further studies on a larger scale and external validation cohorts are necessary to validate its potential clinical utility.

Development of a Radiotherapy Localisation Computed Tomography-Based Radiomic Model for Predicting Survival in Patients With Nasopharyngeal Carcinoma Treated With Intensity-Modulated Radiotherapy Following Induction Chemotherapy.

BACKGROUND: Our purpose is to develop a model combining radiomic features of radiotherapy localisation computed tomography and clinical characteristics that can be used to estimate overall survival in patients with nasopharyngeal carcinoma treated with intensity-modulated radiotherapy following induction chemotherapy. METHODS: We recruited 145 patients with pathologically confirmed nasopharyngeal carcinoma between February 2012 and April 2015. In total, 851 radiomic features were extracted from radiotherapy localisation computed tomography images for the gross tumour volume of the nasopharynx and the gross tumour volume of neck metastatic lymph nodes. The least absolute shrinkage and selection operator algorithm was applied to select radiomics features, build the model and calculate the Rad-score. The patients were divided into high- and low-risk groups based on their Rad-scores. A nomogram for estimating overall survival based on both radiomic and clinical features was generated using multivariate Cox regression hazard models. Prediction reliability was evaluated using Harrell's concordance index. RESULTS: In total, seven radiomic features and one clinical characteristic were extracted for survival analysis, and the combination of radiomic and clinical features was a better predictor of overall survival (concordance index = .849 [confidence interval: .782-.916]) than radiomic features (concordance index = .793 [confidence interval: .697-.890]) or clinical characteristics (concordance index = .661 [confidence interval: .673-.849]) alone. CONCLUSION: Our results show that a nomogram combining radiomic features of radiotherapy localisation computed tomography and clinical characteristics can predict overall survival in patients with nasopharyngeal carcinoma treated with intensity-modulated radiotherapy following induction chemotherapy more effectively than radiomic features or clinical characteristics alone.

Predictive factors for survival following stereotactic body radiotherapy for hepatocellular carcinoma with portal vein tumour thrombosis and construction of a nomogram.

BACKGROUND: We evaluated the treatment response and predictive factors for overall survival (OS) in patients with hepatocellular carcinoma (HCC) and portal vein tumour thrombosis (PVTT), who underwent stereotactic body radiotherapy (SBRT). Additionally, we developed and validated a personalised prediction model for patient survival. METHODS: Clinical information was retrospectively collected for 80 patients with HCC and PVTT, who were treated with SBRT at the Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital) between December 2015 and June 2019. A multivariate Cox proportional hazard regression model was used to identify the independent predictive factors for survival. Clinical factors were subsequently presented in a nomogram. The area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used to evaluate the accuracy of the model and the net clinical benefit. RESULTS: All patients completed the planned radiotherapy treatment, and the median follow-up duration was 10 months (range, 1-35.3 months). The median survival duration was 11.5 months, with 3-, 6-, and 12-month survival rates of 92.5, 74.5, and 47.5%, respectively. The multivariable Cox regression model indicated that the following were significant independent predictors of OS: clinical T stage (p = 0.001, hazard ratio [HR] = 3.085, 95% confidence interval [CI]: 1.514-6.286), cirrhosis (p = 0.014, HR = 2.988, 95% CI: 1.246-7.168), age (p = 0.005, HR = 1.043, 95% CI: 1.013-1.075), alpha-fetoprotein level (p = 0.022, HR = 1.000, 95% CI: 1.000-1.000), and haemoglobin level (p = 0.008, HR = 0.979, 95% CI: 0.963-0.994). A nomogram based on five independent risk factors and DCA demonstrated a favourable predictive accuracy of patient survival (AUC = 0.74, 95% CI: 0.63-0.85) and the clinical usefulness of the model. CONCLUSIONS: SBRT is an effective treatment for patients with HCC with PVTT. Notably, clinical T stage, presence of cirrhosis, age, alpha-fetoprotein levels, and haemoglobin levels are independent prognostic factors for survival. The presented nomogram can be used to predict the survival of patients with HCC and PVTT, who underwent SBRT.

Nutritional outcomes after radiotherapy target volume reduction for nasopharyngeal cancer: a Phase III trial.

Aim: This study aimed to assess the nutritional status of patients with locoregionally advanced nasopharyngeal cancer, for whom intensity-modulated radiotherapy (IMRT) was planned using their pre- or post-induction chemotherapy (IC) nasopharyngeal gross tumor volume. Materials & methods: 212 cases of stage III-IVb nasopharyngeal cancer were randomized into groups A (n = 97) and B (n = 115). IMRT was planned for groups A and B using pre-IC and post-IC images, respectively. Results: There was a significant decrease in the nutritional parameters of group B compared with those of group A during radiotherapy. Multivariate analysis indicated that the T stage and nasopharyngeal gross tumor volume IMRT-planning protocol were prognostic factors of poor nutritional status. Conclusion: Decreasing the IMRT target volume through IC can improve nutritional status.

Preliminary report of a single-channel applicator in high dose rate afterloading brachytherapy for cervical cancer.

The aim of this study was to evaluate whether a patented single-channel applicator, which was modified from the traditional tandem applicator and wrapped with an oval-shield alloy around the source channel, has the same clinical efficacy and safety as the standard Fletcher-type applicator in high dose rate (HDR) brachytherapy for carcinoma of the cervix. Between December 2011 and February 2017, 299 patients with pathologically confirmed International Federation of Gynecology and Obstetrics (2009) stage Ib2-IVa cervical cancer were recruited to the trial and finished the allocated intervention. Of the first 151 patients, 71 were allocated to the Fletcher group and 80 to the single-channel group, satisfying the criteria for a preliminary analysis. All but 3 patients were treated with concurrent cisplatin chemotherapy and external beam radiotherapy followed by HDR brachytherapy. The 2-year overall survival, progression-free survival, and locoregional failure-free survival was 80.3%, 77.5%, and 78.9%, respectively, for the Fletcher group, and 86.3%, 82.5%, and 83.8%, respectively, for the single-channel group. The seriousness of acute treatment-related toxicities was similar in the 2 groups. The cumulative rate of late rectal complications of grade 3-4 in the Fletcher group and the single-channel group was 2.8% and 2.5%, respectively. The cumulative rate of grade 3 bladder complications was 2.8% for the Fletcher group and 1.3% for the single-channel group. The preliminary results of our study show that the patented single-channel intracavitary applicator might be able to provide protection for the rectum and bladder and seems to have the same clinical efficacy as the standard Fletcher-type 3-channel applicator in HDR brachytherapy for carcinoma of the cervix. This trial was registered with the Chinese Clinical Trial Registry (registration no. ChiCTR-TRC-12002321).

A quality control method for intensity-modulated radiation therapy planning based on generalized equivalent uniform dose.

To ensure good quality intensity-modulated radiation therapy (IMRT) planning, we proposed the use of a quality control method based on generalized equivalent uniform dose (gEUD) that predicts absorbed radiation doses in organs at risk (OAR). We conducted a retrospective analysis of patients who underwent IMRT for the treatment of cervical carcinoma, nasopharyngeal carcinoma (NPC), or non-small cell lung cancer (NSCLC). IMRT plans were randomly divided into data acquisition and data verification groups. OAR in the data acquisition group for cervical carcinoma and NPC were further classified as sub-organs at risk (sOAR). The normalized volume of sOAR and normalized gEUD (a = 1) were analyzed using multiple linear regression to establish a fitting formula. For NSCLC, the normalized intersection volume of the planning target volume (PTV) and lung, the maximum diameter of the PTV (left-right, anterior-posterior, and superior-inferior), and the normalized gEUD (a = 1) were analyzed using multiple linear regression to establish a fitting formula for the lung gEUD (a = 1). The r-squared and P values indicated that the fitting formula was a good fit. In the data verification group, IMRT plans verified the accuracy of the fitting formula, and compared the gEUD (a = 1) for each OAR between the subjective method and the gEUD-based method. In conclusion, the gEUD-based method can be used effectively for quality control and can reduce the influence of subjective factors on IMRT planning optimization.

[Design of an adaptive radiation therapy system for target movement compensation].

In order to decrease the radiotherapy error caused by target motion, an adaptive radiation therapy system for target movement compensation has been designed and passed by simulation test. The real-time position of the target labelled by a mark was captured by the control system and compared with the reference point. Then the treatment couch was controlled to move in the opposite direction for compensation according to that position information. The three dimensional movement of the treatment bed relied on three independent stepping motors which were controlled by a control system. Experiments showed that the adaptive radiation therapy system was able to reduce the therapy error caused by target movement. It would be useful in radiotherapy clinical practice with high real-time position precision.

[Application of elastic registration based on Demons algorithm in cone beam CT].

We applied Demons and accelerated Demons elastic registration algorithm in radiotherapy cone beam CT (CBCT) images, We provided software support for real-time understanding of organ changes during radiotherapy. We wrote a 3D CBCT image elastic registration program using Matlab software, and we tested and verified the images of two patients with cervical cancer 3D CBCT images for elastic registration, based on the classic Demons algorithm, minimum mean square error (MSE) decreased 59.7%, correlation coefficient (CC) increased 11.0%. While for the accelerated Demons algorithm, MSE decreased 40.1%, CC increased 7.2%. The experimental verification with two methods of Demons algorithm obtained the desired results, but the small difference appeared to be lack of precision, and the total registration time was a little long. All these problems need to be further improved for accuracy and reducing of time.

CT radiomics based on different machine learning models for classifying gross tumor volume and normal liver tissue in hepatocellular carcinoma.

BACKGROUND & AIMS: The present study utilized extracted computed tomography radiomics features to classify the gross tumor volume and normal liver tissue in hepatocellular carcinoma by mainstream machine learning methods, aiming to establish an automatic classification model. METHODS: We recruited 104 pathologically confirmed hepatocellular carcinoma patients for this study. GTV and normal liver tissue samples were manually segmented into regions of interest and randomly divided into five-fold cross-validation groups. Dimensionality reduction using LASSO regression. Radiomics models were constructed via logistic regression, support vector machine (SVM), random forest, Xgboost, and Adaboost algorithms. The diagnostic efficacy, discrimination, and calibration of algorithms were verified using area under the receiver operating characteristic curve (AUC) analyses and calibration plot comparison. RESULTS: Seven screened radiomics features excelled at distinguishing the gross tumor area. The Xgboost machine learning algorithm had the best discrimination and comprehensive diagnostic performance with an AUC of 0.9975 [95% confidence interval (CI): 0.9973-0.9978] and mean MCC of 0.9369. SVM had the second best discrimination and diagnostic performance with an AUC of 0.9846 (95% CI: 0.9835- 0.9857), mean Matthews correlation coefficient (MCC)of 0.9105, and a better calibration. All other algorithms showed an excellent ability to distinguish between gross tumor area and normal liver tissue (mean AUC 0.9825, 0.9861,0.9727,0.9644 for Adaboost, random forest, logistic regression, naivem Bayes algorithm respectively). CONCLUSION: CT radiomics based on machine learning algorithms can accurately classify GTV and normal liver tissue, while the Xgboost and SVM algorithms served as the best complementary algorithms.

Construction of a predictive model for postoperative hospitalization time in colorectal cancer patients based on interpretable machine learning algorithm: a prospective preliminary study.

Objective: This study aims to construct a predictive model based on machine learning algorithms to assess the risk of prolonged hospital stays post-surgery for colorectal cancer patients and to analyze preoperative and postoperative factors associated with extended hospitalization. Methods: We prospectively collected clinical data from 83 colorectal cancer patients. The study included 40 variables (comprising 39 predictor variables and 1 target variable). Important variables were identified through variable selection via the Lasso regression algorithm, and predictive models were constructed using ten machine learning models, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Light Gradient Boosting Machine, KNN, and Extreme Gradient Boosting, Categorical Boosting, Artificial Neural Network and Deep Forest. The model performance was evaluated using Bootstrap ROC curves and calibration curves, with the optimal model selected and further interpreted using the SHAP explainability algorithm. Results: Ten significantly correlated important variables were identified through Lasso regression, validated by 1000 Bootstrap resamplings, and represented through Bootstrap ROC curves. The Logistic Regression model achieved the highest AUC (AUC=0.99, 95% CI=0.97-0.99). The explainable machine learning algorithm revealed that the distance walked on the third day post-surgery was the most important variable for the LR model. Conclusion: This study successfully constructed a model predicting postoperative hospital stay duration using patients' clinical data. This model promises to provide healthcare professionals with a more precise prediction tool in clinical practice, offering a basis for personalized nursing interventions, thereby improving patient prognosis and quality of life and enhancing the efficiency of medical resource utilization.

Cerium oxide nanoparticles in wound care: a review of mechanisms and therapeutic applications.

Skin wound healing is a complex and tightly regulated process. The frequent occurrence and reoccurrence of acute and chronic wounds cause significant skin damage to patients and impose socioeconomic burdens. Therefore, there is an urgent requirement to promote interdisciplinary development in the fields of material science and medicine to investigate novel mechanisms for wound healing. Cerium oxide nanoparticles (CeO2 NPs) are a type of nanomaterials that possess distinct properties and have broad application prospects. They are recognized for their capabilities in enhancing wound closure, minimizing scarring, mitigating inflammation, and exerting antibacterial effects, which has led to their prominence in wound care research. In this paper, the distinctive physicochemical properties of CeO2 NPs and their most recent synthesis approaches are discussed. It further investigates the therapeutic mechanisms of CeO2 NPs in the process of wound healing. Following that, this review critically examines previous studies focusing on the effects of CeO2 NPs on wound healing. Finally, it suggests the potential application of cerium oxide as an innovative nanomaterial in diverse fields and discusses its prospects for future advancements.

Improved automatic segmentation of brain metastasis gross tumor volume in computed tomography images for radiotherapy: a position attention module for U-Net architecture.

Background: Brain metastases present significant challenges in radiotherapy due to the need for precise tumor delineation. Traditional methods often lack the efficiency and accuracy required for optimal treatment planning. This paper proposes an improved U-Net model that uses a position attention module (PAM) for automated segmentation of gross tumor volumes (GTVs) in computed tomography (CT) simulation images of patients with brain metastases to improve the efficiency and accuracy of radiotherapy planning and segmentation. Methods: We retrospectively collected CT simulation imaging datasets of patients with brain metastases from two centers, which were designated as the training and external validation datasets. The U-Net architecture was enhanced by incorporating a PAM into the transition layer, which improved the automated segmentation capability of the U-Net model. With cross-entropy loss employed as the loss function, the samples from the training dataset underwent training. The model's segmentation performance on the external validation dataset was assessed using metrics including the Dice similarity coefficient (DSC), intersection over union (IoU), accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and Hausdorff distance (HD). Results: The proposed automated segmentation model demonstrated promising performance on the external validation dataset, achieving a DSC of 0.753±0.172. In terms of evaluation metrics (including the DSC, IoU, accuracy, sensitivity, MCC, and HD), the model outperformed the standard U-Net, which had a DSC of 0.691±0.142. The proposed model produced segmentation results that were closer to the ground truth and could reveal more detailed features of brain metastases. Conclusions: The PAM-improved U-Net model offers considerable advantages in the automated segmentation of the GTV in CT simulation images for patients with brain metastases. Its superior performance in comparison with the standard U-Net model supports its potential for streamlining and improving the accuracy of radiotherapy. With its ability to produce segmentation results consistent with the ground truth, the proposed model holds promise for clinical adoption and provides a reference for radiation oncologists to make more informed GTV segmentation decisions.

Deep learning and machine learning predictive models for neurological function after interventional embolization of intracranial aneurysms.

Objective: The objective of this study is to develop a model to predicts the postoperative Hunt-Hess grade in patients with intracranial aneurysms by integrating radiomics and deep learning technologies, using preoperative CTA imaging data. Thereby assisting clinical decision-making and improving the assessment and prognosis of postoperative neurological function. Methods: This retrospective study encompassed 101 patients who underwent aneurysm embolization surgery. 851 radiomic features were extracted from CTA images. 512 deep learning features are extracted from last layer of ResNet50 deep convolutional neural network model. The feature screening process pipeline encompassed intraclass correlation coefficient analysis, principal component analysis, U test, spearman correlation analysis, minimum redundancy maximum relevance algorithm and Lasso regression, to identify features most correlated with postoperative Hunt-Hess grading. In the model construction phase, three distinct models were constructed: radiomics feature-based model (RSM), deep learning feature-based model (DLM), and deep learning-radiomics feature fusion model (DLRSCM). The study also calculated the radiomics score and combined it with clinical data to construct a Nomogram for predictive modeling. DLM, RSM and DLRSCM model was constructed by 9 base algorithms and 1 ensemble learning algorithm - Stacking ensemble model. Model performance was evaluated based on the area under the Receiver Operating Characteristic (ROC) curve (AUC), Matthews Correlation Coefficient (MCC), calibration curves, and decision curves analysis. Results: 5 significant radiomic feature and 4 significant deep learning features were obtained through the feature selection process. These features were utilized for model construction. Bootstrap resampling method was used for internal validation of the models. In terms of model evaluation, the DLM model, the stacking ensemble algorithm results achieved an AUC of 0.959 and MCC of 0.815. In the RSM model, the stacking ensemble model AUC was 0.935 and MCC was 0.793. The stacking ensemble model in DLRSCM outperformed others, with an AUC of 0.968 and MCC of 0.820. Results indicated that the ANN performed optimally among all base models, while the stacked ensemble learning model exhibited the highest predictive performance. Conclusion: This study demonstrates that the combination of radiomics and deep learning is an effective approach to predict the postoperative Hunt-Hess grade in patients with intracranial aneurysms. This holds significant value in the early identification of postoperative neurological complications and in enhancing clinical decision-making.

Improved brain metastases segmentation using generative adversarial network and conditional random field optimization mask R-CNN.

BACKGROUND: In radiotherapy, the delineation of the gross tumor volume (GTV) in brain metastases using computed tomography (CT) simulation localization is very important. However, despite the criticality of this process, a pronounced gap exists in the availability of tools tailored for the automatic segmentation of the GTV based on CT simulation localization images. PURPOSE: This study aims to fill this gap by devising an effective tool specifically for the automatic segmentation of the GTV using CT simulation localization images. METHODS: A dual-network generative adversarial network (GAN) architecture was developed, wherein the generator focused on refining CT images for more precise delineation, and the discriminator differentiated between real and augmented images. This architecture was coupled with the Mask R-CNN model to achieve meticulous GTV segmentation. An end-to-end training process facilitated the integration between the GAN and Mask R-CNN functionalities. Furthermore, a conditional random field (CRF) was incorporated to refine the initial masks generated by the Mask R-CNN model to ensure optimal segmentation accuracy. The performance was assessed using key metrics, namely, the Dice coefficient (DSC), intersection over union (IoU), accuracy, specificity, and sensitivity. RESULTS: The GAN+Mask R-CNN+CRF integration method in this study performs well in GTV segmentation. In particular, the model has an overall average DSC of 0.819 ± 0.102 and an IoU of 0.712 ± 0.111 in the internal validation. The overall average DSC in the external validation data is 0.726 ± 0.128 and the IoU is 0.640 ± 0.136. It demonstrates favorable generalization ability. CONCLUSION: The integration of the GAN, Mask R-CNN, and CRF optimization provides a pioneering tool for the sophisticated segmentation of the GTV in brain metastases using CT simulation localization images. The method proposed in this study can provide a robust automatic segmentation approach for brain metastases in the absence of MRI.

Deciphering the fibrotic process: mechanism of chronic radiation skin injury fibrosis.

This review explores the mechanisms of chronic radiation-induced skin injury fibrosis, focusing on the transition from acute radiation damage to a chronic fibrotic state. It reviewed the cellular and molecular responses of the skin to radiation, highlighting the role of myofibroblasts and the significant impact of Transforming Growth Factor-beta (TGF-ß) in promoting fibroblast-to-myofibroblast transformation. The review delves into the epigenetic regulation of fibrotic gene expression, the contribution of extracellular matrix proteins to the fibrotic microenvironment, and the regulation of the immune system in the context of fibrosis. Additionally, it discusses the potential of biomaterials and artificial intelligence in medical research to advance the understanding and treatment of radiation-induced skin fibrosis, suggesting future directions involving bioinformatics and personalized therapeutic strategies to enhance patient quality of life.

Development and validation of radiomics machine learning model based on contrast-enhanced computed tomography to predict axillary lymph node metastasis in breast cancer.

Preoperative identification of axillary lymph node metastasis can play an important role in treatment selection strategy and prognosis evaluation. This study aimed to establish a clinical nomogram based on lymph node images to predict lymph node metastasis in breast cancer patients. A total of 193 patients with non-specific invasive breast cancer were divided into training (n = 135) and validation set (n = 58). Radiomics features were extracted from lymph node images instead of tumor region, and the least absolute shrinkage and selection operator logistic algorithm was used to select the extracted features and generate radiomics score. Then, the important clinical factors and radiomics score were integrated into a nomogram. A receiver operating characteristic curve was used to evaluate the nomogram, and the clinical benefit of using the nomogram was evaluated by decision curve analysis. We found that clinical N stage and radiomics score were independent clinical predictors. Besides, the nomogram accurately predicted axillary lymph node metastasis, yielding an area under the receiver operating characteristic curve of 0.95 (95% confidence interval 0.93-0.98) in the validation set, indicating satisfactory calibration. Decision curve analysis confirmed that the nomogram had higher clinical utility than clinical N stage or radiomics score alone. Overall, the nomogram based on radiomics features and clinical factors can help radiologists to predict axillary lymph node metastasis preoperatively and provide valuable information for individual treatment.

Research on automatic classification technology of kidney tumor and normal kidney tissue based on computed tomography radiomics.

Purpose: By using a radiomics-based approach, multiple radiomics features can be extracted from regions of interest in computed tomography (CT) images, which may be applied to automatically classify kidney tumors and normal kidney tissues. The study proposes a method based on CT radiomics and aims to use extracted radiomics features to automatically classify of kidney tumors and normal kidney tissues and to establish an automatic classification model. Methods: CT data were retrieved from the 2019 Kidney and Kidney Tumor Segmentation Challenge (KiTS19) in The Cancer Imaging Archive (TCIA) open access database. Arterial phase-enhanced CT images from 210 cases were used to establish an automatic classification model. These CT images of patients were randomly divided into training (168 cases) and test (42 cases) sets. Furthermore, the radiomics features of gross tumor volume (GTV) and normal kidney tissues in the training set were extracted and screened, and a binary logistic regression model was established. For the test set, the radiomic features and cutoff value of P were consistent with the training set. Results: Three radiomics features were selected to establish the binary logistic regression model. The accuracy (ACC), sensitivity (SENS), specificity (SPEC), area under the curve (AUC), and Youden index of the training and test sets based on the CT radiomics classification model were all higher than 0.85. Conclusion: The automatic classification model of kidney tumors and normal kidney tissues based on CT radiomics exhibited good classification ability. Kidney tumors could be distinguished from normal kidney tissues. This study may complement automated tumor delineation techniques and warrants further research.