PurposeTo investigate the impact of ComBat harmonization on the performance of 1.5T/3.0T MRI radiomic features in predicting the overall survival(OS) of patients with locally advanced nasopharyngeal carcinoma(LANPC).MethodsThis dual-center retrospective study included 573 patients with LANPC (435 male and 138 female patients). The 3.0T MRI dataset from Hospital 1 was used as the reference batch (training cohort, n=287), and the 1.5T MRI dataset from Hospital 2 was subjected to ComBat harmonization. The 1.5T MRI dataset before ComBat harmonization served as Validation Cohort 1 (n=286), while the 1.5T MRI dataset after ComBat harmonization was designated as Validation Cohort 2. Radiomics features were extracted from the segmented tumors, and principal component analysis (PCA) was applied to assess the batch effect of radiomics features between the two validation cohorts. A radiomics-clinical prognostic model was developed using radiomic features and other clinical factors using multivariate Cox regression. The concordance index (C-index) was used to evaluate model performance in predicting OS, and Kaplan-Meier survival analysis was conducted to explore the impact of the model on the prognosis of LANPC patients.ResultsPCA without ComBat revealed noticeable differences in the first two principal components between batches, indicating a batch effect or unstable radiomic features. Following ComBat harmonization, the principal components showed more consistency between batches, demonstrating radiomics feature stability between batches. Multivariate Cox regression identified EBV-DNA and platelet count as independent clinical factors, which were integrated with the radiomics score to construct the final prognostic model. The C-indexes of the model for predicting OS in the training, validation 1 and validation 2 cohorts was 0.797, 0.610 and 0.648, respectively. The 5-year OS for the model defined low-risk group was significantly better than that of the high-risk group (P < 0.001).ConclusionComBat harmonization effectively reduced the inter-batch effect of radiomic feature sets across different centers and scanners. While the model maintained favorable discrimination for OS and robust risk-group separation via Kaplan-Meier analysis, the primary benefit of ComBat harmonization was the improved qualitative consistency of risk stratification between multi-center datasets, which may support the clinical application of risk-adapted therapy for LANPC.

PurposeTo establish a dual-energy CT (DECT) based nomogram for predicting progression-free survival (PFS) in locally advanced nasopharyngeal carcinoma (LANPC).MethodsIn this retrospective study, 52 LANPC patients who underwent DECT scans and post-treatment follow-up (median follow-up = 42.2 months) were enrolled. DECT parameters of tumor lesions including iodine concentration (IC), normalized iodine concentration (NIC), the slope of the spectral Hounsfield unit (HU) curve (λHU), and effective atomic number (Zeff) were analyzed to predict PFS. A nomogram integrating clinical data and DECT-derived parameters was constructed. The model’s performance was evaluated using calibration curves, Harrell’s concordance index (C-index), and receiver operating characteristic (ROC) curve.ResultsNIC, neutrophil-to-lymphocyte ratio (NLR), and lactate dehydrogenase (LDH) were the independent prognostic factors for PFS, and were incorporated into constructing the nomogram. Calibration plots demonstrated strong agreement between predicted and observed PFS rates. The C-index for the nomogram was 0.88 (95% confidence interval [CI]: 0.80–0.90). The nomogram model demonstrated predictive accuracy for PFS, with the area under the ROC curves (AUCs) of 0.939, 0.880, and 0.879 at 1-, 2-, and 3-year, respectively.ConclusionThe DECT-based nomogram exhibited excellent predictive accuracy for PFS in LANPC patients, highlighting its potential as a valuable clinical tool.

Objectives This study aimed to develop a disease-free survival (DFS) prediction model incorporating radiomics and intratumor heterogeneity (ITH) scores for locally advanced nasopharyngeal carcinoma (LANPC), and to establish an anti-epidermal growth factor receptor (EGFR) therapy risk model. Materials and Methods A retrospective analysis was conducted on 950 pathologically confirmed LANPC patients (training cohort: n = 632, including 81 receiving anti-EGFR therapy; test cohort: n = 318, including 47 receiving anti-EGFR therapy). All patients underwent 1.5 T MRI (T2-Weighted Imaging and contrast-enhanced T1-Weighted Imaging). Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) and support vector machine (SVM) survival algorithms. Subsequently, five predictive models were developed and compared: a Comprehensive Risk Model (CRM) integrating clinical features, ITH score, and radiomics score; an ITH-radiomics model (IRM); a standalone ITH model (ITHM); a standalone radiomics model (RM); and a clinical model (CM). Model performance was evaluated using the area under the curve (AUC) and the concordance index (C-index), and clinical utility was assessed with decision curve analysis. Finally, Kaplan-Meier analysis with the log-rank test compared survival between the model-defined risk groups. Additionally, the DeepSurv deep neural network was employed to simulate personalized treatment recommendations based on the patient's risk profile. Results With median follow-ups of 73 months (training) and 68.1 months (test), disease progression occurred in 34.2% (216/632) and 36.5% (116/318) of cases, respectively. The CRM achieved the highest C-index value for assessing DFS in patients with LANPC, with values of 0.829 and 0.760 in the training and test cohorts, respectively. Patients who met the DeepSurv treatment recommendations had better DFS. Conclusion The superior performance of the CRM supports its potential to enhance DFS prediction in LANPC and to inform anti-EGFR therapy selection.

Background:Breast tumor segmentation is a critical aspect of magnetic resonance imaging (MRI)-based breast disease diagnosis. Numerous networks and algorithms, including U-Net and its enhancements, have been proposed for breast tumor segmentation. However, existing methods have certain shortcomings and limitations, including insufficient extraction of multi-scale contextual information, which poses challenges in adapting to tumors of different sizes and distinguishing tumor boundaries from surrounding tissues. Additionally, the feature extraction process lacks specificity and is prone to interference from irrelevant information outside the tumor region. This study aimed to address these challenges, and achieve the accurate and automated segmentation of breast tumors in MRI scans. Methods:A new three-dimensional (3D) breast tumor segmentation network named the multi-scale hybrid attention U-shaped network (MHAU-Net) was designed. The network used four sets of atrous convolutions with different dilated ratios to extract multi-scale context information. Global pooling and single-channel convolution structures were employed to construct channel and spatial blocks. Subsequently, the network integrated four sets of atrous convolutions with spatial and channel attention blocks to extract hybrid attention features. Compared to existing MRI segmentation networks for breast tumors, the MHAU-Net demonstrated superior performance in extracting informative features and adapting to tumors of diverse sizes and shapes. Results:To evaluate the proposed approach, we curated a large-scale breast MRI dataset comprising 906 3D images. A comparative analysis with seven commonly used segmentation networks revealed the superior performance of our method. Our network had a dice similarity coefficient (DSC) and intersection over union (IoU) of 84.1%±2.1% and 74.2%±3.4%, respectively, representing a 6.0% and 7.1% improvement over the baseline 3D U-Net. Additionally, our method had DSC values of 85.7%±1.6%, 84.3%±2.8%, 86.7%±1.7%, and 86.3%±1.5% for single, small, large, and mass tumors, respectively. Conclusions:Our results highlight the superior overall performance of the proposed method, and show its ability to adapt to various types of tumor images. This study establishes a solid foundation for further exploring the application value of deep learning in breast cancer diagnosis.

To develop and validate an interpretable and generalized machine learning model using MRI for the individualized prediction of induction chemotherapy (ICT) response and survival in locoregionally advanced nasopharyngeal carcinoma (LANPC). A total of 1368 patients who underwent MRI examinations before ICT from three hospitals were retrospectively enrolled and divided into training, internal validation, external validation, and cross-field strength validation cohorts. Significant radiomics and clinical features were selected from coarse to fine. An interpretable genetic algorithm-enhanced artificial neural network (GNN) was applied for models’ development and validation. The performance of junior and senior doctors in predicting ICT response with and without model aid was evaluated. The interpretable GNN model achieved good generalization performance in predicting ICT response, with areas under the curve (AUCs) ranging from 0.808 to 0.864 across all cohorts. Survival analysis demonstrated that low-risk patients defined by GNN-radiomics signature and clinical factors had better progression-free survival than high-risk patients in all cohorts (hazard ratio ranging from 3.231 to 12.787, p < 0.05). The predictive performance of junior and senior doctors for ICT response significantly improved with model assistance (AUCs: 0.686 vs. 0.785 and 0.736 vs. 0.836, p < 0.05). An interpretable, applicable, and generalized GNN model based on multi-center databases achieved superior performance in predicting ICT response and survival in LANPC patients, which may contribute to the personalized treatment of LANPC. Question Currently, there is a lack of accurate methods for predicting and evaluating the efficacy and prognosis of nasopharyngeal carcinoma (NPC). Findings Genetic algorithm-enhanced artificial neural network model excels in predicting induction chemotherapy response and survival outcome of NPC, providing valuable assistance to doctors in clinical practice. Clinical relevance This model can identify patients likely to benefit from induction chemotherapy, promoting individualized treatment and optimizing clinical management.

This study aimed to investigate whether establishing a machine learning (ML) model based on contrast-enhanced cone-beam breast computed tomography (CE-CBBCT) radiomic features could predict human epidermal growth factor receptor 2-positive breast cancer (BC). Eighty-eight patients diagnosed with invasive BC who underwent preoperative CE-CBBCT were retrospectively enrolled. Patients were randomly assigned to the training and testing cohorts at a ratio of approximately 7:3. A total of 1046 quantitative radiomics features were extracted from the CE-CBBCT images using PyRadiomics. Z-score normalization was used to standardize the radiomics features, and Pearson correlation coefficient and one-way analysis of variance were used to explore the significant features. Six ML algorithms (support vector machine, random forest [RF], logistic regression, adaboost, linear discriminant analysis, and decision tree) were used to construct optimal predictive models. Receiver operating characteristic curves were constructed and the area under the curve (AUC) was calculated. Four top-performing radiomic models were selected to develop the 6 predictive features. The AUC values for support vector machine, linear discriminant analysis, RF, logistic regression, adaboost, and decision tree were 0.741, 0.753, 1.000, 0.752, 1.000, and 1.000, respectively, in the training cohort, and 0.700, 0.671, 0.806, 0.665, 0.706, and 0.712, respectively, in the testing cohort. Notably, the RF model exhibited the highest predictive ability with an AUC of 0.806 in the testing cohort. For the RF model, the DeLong test showed statistically significant differences in the AUC between the training and testing cohorts (Z = 2.105, P = .035). The ML model based on CE-CBBCT radiomics features showed promising predictive ability for human epidermal growth factor receptor 2-positive BC, with the RF model demonstrating the best diagnostic performance.

Purpose:This study aimed to explore the diagnostic value of high-resolution magnetic resonance images and tumour markers in predicting lymph node metastasis of rectal cancer. Material and methods:The clinical, imaging, and pathological data of patients with suspected rectal cancer were collected. The baseline data, and surgical and pathological characteristics were compared between the lymph node metastasis group and no metastasis group. Univariate and multivariate logistic regression were used to analyse the clinical and pathological factors, and preoperative magnetic resonance imaging (MRI) signs of extramural vascular invasion and rectal cancer lymph node metastasis. A nomogram model was established with statistically significant factors. Results:150 patients were included. Among them, 50 (33.3%) presented with vascular tumour thrombus, and 72 (48.0%) had lymph node metastasis. The detection of regional lymph nodes (DWI-LN) was an independent risk factor for lymph node metastasis. The area under curve of the nomogram model was 0.804. Conclusion:Preoperative serum CA19.9, and the relationship between tumour and peritoneal reflection in preoperative MRI and DWI-LN have clinical value in predicting lymph node metastasis in patients with rectal cancer.

BACKGROUND:Ferroptosis can have a major impact on the development and advancement of hepatocellular carcinoma (HCC) due to its clear association with heightened vulnerability to the disease. This study aimed to develop a novel nanoplatform to evaluate its effectiveness in in vivo and in vitro models of HCC. METHODS:Erastin, a compound that induces iron-dependent cell death, and HMME, a sonosensitizer, were enclosed within mesoporous silica nanoparticles (MSNs). The nanoparticles were engineered to exhibit a responsive assembly-disassembly mechanism. Hydrophilic hyaluronic acid (HA) was utilized for conjugation modification to synthesize Erastin/HMME@MSNs-HA. In vivo and in vitro experiments were conducted to elucidate the antitumor mechanisms of this nanomaterial. RESULTS:In the in vitro cellular experiments, Erastin/HMME@MSNs-HA was rapidly degraded by hyaluronidase, leading to increased endocytosis of the cancer cells. Cellular breakdown led to the generation of harmful reactive oxygen species (ROS), decreased glutathione levels, and increased lipid peroxidation, resulting in a decrease in mitochondrial membrane potential, dysfunctional mitochondria, reduced cell growth, and increased cell death. Additionally, the Erastin/HMME@MSNs-HA nanotherapy platform, when combined with ultrasound (US) treatment, exhibited significant therapeutic effectiveness against tumors in vivo. It induced significant cell death in cancerous tissues, decreased tumor growth, worsened tissue oxygen deprivation, and exhibited good compatibility with the body. CONCLUSION:These findings indicate that the nanoplatform can effectively alleviate tumor hypoxia while inducing apoptosis and ferroptosis, laying the foundation for enhancing the efficacy of ROS-mediated HCC therapy.

Background and objectiveThis study aims to explore the relationship between melanocortin-1 receptor (MC1R) expression levels and clinical pathological parameters of melanoma, as well as its potential as a prognostic biomarker.MethodsThis retrospective study included 99 melanoma patients in our hospital from June 2017 to July 2023. MC1R expression was assessed by immunohistochemistry assays. Histochemistry score (H-score) determined the level of MC1R immunohistochemistry expression in melanoma. The relationships among MC1R expression, clinical pathological parameters in melanoma patients were assessed using Chi-square and Fisher’s precision probability tests. Kaplan-Meier assay and log-rank test were utilized to estimate survival curves. Potential independent factors among the enrolled patients were investigated using COX regression analysis.ResultsAccording to median value of H-score, 38 cases with low MC1R expression and 61 cases with high MC1R expression in melanoma tumor tissues were observed. Patients with high MC1R expression in melanoma tissues exhibited a worse prognosis compared to patients with low MC1R expression. The survival time difference was statistically significant [MC1R expression in melanoma tumor tissue (MC1RT): median DFS, 12.83 vs. 17.53 months, χ2 = 5.395, P=0.0202; median OS, 16.47 vs. 21.77 months, χ2 = 5.082, P=0.0243. MC1R expression in normal adjacent to melanoma tissue (MC1RN): median DFS, 12.03 vs. 14.29 months, χ2 = 6.864, P=0.0088; median OS, 16.73 vs. 21.77 months, χ2 = 5.649, P=0.0175]. Multivariate COX regression model analysis indicated that MC1RN, MC1RT, sex, ESR, tumor site, targeted therapy, and immunotherapy were potential prognostic factors for the DFS. Furthermore, MC1RN, MC1RT, sex, tumor site, TLN, PLN, and immunotherapy were potential prognostic factors for the OS. Calibration curve indicated the predicted probabilities of nomogram models were in accordance with the actual probabilities, and the prediction accuracy was relatively high at one year and three years following surgery. The decision clinical curve revealed that the nomogram models had better predictive performance for DFS and OS than the MC1RT or MC1RN thresholds.ConclusionsLow MC1R expression in melanoma tumor tissues and adjacent normal tissue might be beneficial for the prognosis of melanoma patients. MC1R was a predictive factor for the prognosis of melanoma patients. Nomogram models based on MC1R demonstrated good prediction ability.

Background/Objectives: The lack of reliable prognostic predictors in breast cancer undermines the efficacy of its prediction, prevention, and personalized medicine (PPPM/3PM) approach. This study aimed to develop an integrated model based on cone-beam breast computed tomography (CBBCT) and hematological indicators to predict the prognosis of preoperative stage I-III breast cancer. Methods:A retrospective analysis was performed on 243 patients with pathologically confirmed stage I-III breast cancer. A new machine learning framework for feature selection integrated 10 machine learning algorithms and their 101 combinations. After feature selection, the patient risk score was calculated to construct a nomogram model for breast cancer prognosis. The nomogram model was evaluated using receiver operating characteristic (ROC) curve analysis and calibration curve. Univariate and multivariate logistic regression analyses verified the screened features and determined independent risk factors. Results: A machine learning computational framework based on 101 combinations selected 12 prognostic indicators of overall survival (OS) and 18 disease-free survivals (DFS) from 37 CBBCT and hematological features. The entire model achieved an AUC value of 0.837 in the training dataset and 0.813 in the validation dataset, which is superior to the clinical model without CBBCT indicators regarding OS prediction performance. Similarly, the AUC of the training and validation sets for DFS prediction was 0.996 and 0.732. Molecular typing, Enhancement curve types, and Morphology were independent risk factors associated with OS in the clinical prediction model. Calcification was an independent risk factor associated with DFS. We constructed a nomogram model combining the above features. Conclusions: Our study screened prognostic-related CBBCT and hematological features, and the nomogram showed satisfactory preoperative predictive efficacy for stage I-III breast cancer. It can be incorporated into the PPPM framework to help clinicians make more accurate treatment decisions.

Background:Dual-phenotype hepatocellular carcinoma (DPHCC) is associated with a higher risk of recurrence, but little is known about its clinicodemographic characteristics or imaging features. This study aimed to assess whether contrast-enhanced computed tomography (CECT) and patient characteristics can facilitate preoperative differentiation of DPHCC and non-DPHCC. Methods:Features on CECT images and clinicodemographic characteristics were retrospectively analyzed from a consecutive series of hepatocellular carcinoma (HCC) patients between January 2020 and December 2020. Disease was confirmed based on surgical pathology, and CECT was performed within four weeks before surgery. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors for DPHCC, and an imaging model based on CECT features and a combined model based on clinicodemographic characteristics and CECT features were constructed, respectively. Delong's test was used for comparison of the area under the curve (AUC) values between the two models. Kaplan-Meier survival analysis was used to assess overall survival (OS) in DPHCC and non-DPHCC groups. Results:A total of 29 patients with DPHCC and 140 with non-DPHCC were included in this study. DPHCC was significantly more prevalent among female patients and less prevalent among those infected with hepatitis B virus (HBV). CECT associated DPHCC with rim arterial phase hyperenhancement (APHE) and peripheral washout, whereas it associated non-DPHCC with non-rim APHE and non-peripheral washout. Multivariate logistic regression identified one independent CECT feature of DPHCC: rim APHE [odds ratio (OR) 11.040, 95% confidence interval (CI): 1.98-63.532]. The imaging model was constructed based on rim APHE-predicted DPHCC with an AUC of 0.562 (95% CI: 0.439-0.684). Multivariate logistic regression identified three independent clinicodemographic characteristics and CECT features of DPHCC: female sex (OR 4.519, 95% CI: 1.529-13.357), infection with HBV (OR 0.234, 95% CI: 0.084-0.654) and rim APHE (OR 15.016, 95% CI: 2.335-96.585). The combined model was constructed based on three independent predictors of DPHCC with an AUC of 0.716 (95% CI: 0.603-0.829). Delong's test showed that the AUC of the combined model was higher than that of the imaging model, and the difference was statistically significant (Z=3.207, P<0.05). The OS rates of the patients in the DPHCC and non-DPHCC groups were 68.7% and 77.2%, respectively. Kaplan-Meier survival analysis showed no statistical difference in OS rates between groups (P=0.362). Conclusions:The combined model established based on female sex, infection with HBV, and rim APHE by CECT can facilitate preoperative differentiation of DPHCC and non-DPHCC. DPHCC is more likely to cause death than non-DPHCC, suggesting that active postoperative management of patients with DPHCC is required.

This study aimed to develop an integrated model based on cone-beam breast computed tomography (CBBCT) and hematological indicators to predict the prognosis of preoperative stage I–III breast cancer. A retrospective analysis was performed on 243 patients with pathologically confirmed stage I–III breast cancer. A novel machine learning framework for feature selection was employed, which integrates 14 distinct algorithms and explores 101 possible combinations, enhancing the ability to identify the most relevant features in high-dimensional medical imaging datasets. After feature selection, a patient risk score was calculated to construct a nomogram model for breast cancer prognosis. The nomogram model was evaluated using receiver operating characteristic (ROC) curve analysis and calibration curves. Univariate and multivariate regression analyses were conducted to validate the screened features and determine independent risk factors. A machine learning computational framework based on 101 combinations selected 12 prognostic indicators for overall survival (OS) and 18 for disease-free survival (DFS) from 37 CBBCT and hematological features. The model incorporating clinical and imaging indicators achieved an average area under the curve (AUC) value of 0.832 in both the training and validation datasets, demonstrating superior overall survival (OS) prediction performance compared to the clinical model without CBBCT indicators (AUC = 0.777). Similarly, the AUC values for DFS prediction in the training and validation sets were 0.996 and 0.732, respectively. Molecular typing, enhancement curve types, and morphology were independent risk factors for OS in the clinical prediction model. Calcification was an independent risk factor associated with DFS. A nomogram model was established combining the above features. Our study successfully screened prognostic-related CBBCT and hematological features. The developed nomogram showed satisfactory preoperative predictive efficacy for stage I–III breast cancer.

Microwave ablation (MWA) holds promise as a tumor treatment modality, yet incomplete ablation with low-frequency MWA (iMWA) remains a significant obstacle to survival, while the high-frequency MWA poses safety concerns. To address these challenges, we introduce a novel bimetallic iMWA nanosensitizer, CFT-NPs, constructed via metal-coordination interactions between tannic acid (TA) and iron/calcium dual metal ions (Fe3+/Ca2+). The Fe3+/Ca2+ in CFT-NPs work in harmony to convert electromagnetic energy into heat, thereby bolstering the effectiveness of iMWA while maintaining good biosafety. Furthermore, the pH-triggered rupture of CFT-NPs release TA, Fe3+, and Ca2+. The liberated Fe3+ undergoes reduction by TA, and when combined with Ca2+, they trigger ferroptosis and Ca2+ overload respectively, significantly amplifying the therapeutic effects of iMWA. Utilization iMWA with CFT-NPs results in lipid oxidation, mitochondrial dysfunction, and disruption of redox balance, both in vitro and in vivo. Notably, this nanosensitizer exerts a robust antitumor effect, effectively inhibiting tumor growth and downregulating the expression of matrix metalloproteinases, which is associated with tumor metastasis. Collectively, this innovative study offers a promising approach to overcome the challenges of incomplete ablation and biological safety, enhancing the antitumor efficacy of iMWA..

BackgroundThe immune system plays an important role in the development and treatment of thyroid cancer(THCA).However, the correlation between immune cells and THCA has not been systematically studied.MethodsThis study used a two-sample Mendelian randomization (MR) study to determine the causal relationship between immune cell characteristics and THCA. Based on a large sample of publicly available genetic data, we explored the causal relationship between 731 immune cell characteristics and THCA risk. The 731 immunophenotypes were divided into 7 groups, including B cell panel(n=190),cDC panel(n=64),Maturation stages of T cell panel(n=79),Monocyte panel(n=43),Myeloid cell panel(n=64),TBNK panel(n=124),and Treg panel(n=167). The sensitivity of the results was analyzed, and heterogeneity and horizontal pleiotropy were excluded.ResultsAfter FDR correction, the effect of immunophenotype on THCA was not statistically significant. It is worth mentioning, however, that there are some unadjusted low P-values phenotypes. The odds ratio (OR) of CD62L on monocyte on THCA risk was estimated to be 0.953 (95% CI=0.930~0.976, P=1.005×10−4),and which was estimated to be 0.975(95% CI=0.961–0.989, P=7.984×10−4) for Resting Treg%CD4 on THCA risk. Furthermore, THCA was associated with a reduced risk of 5 immunophenotype:CD25 on CD39+ CD4 on Treg (OR=0.871, 95% CI=0.812~0.935, P=1.274×10−4), activated Treg AC (OR=0.884, 95% CI=0.820~0.953, P=0.001), activated & resting Treg % CD4 Treg (OR=0.872, 95%CI=0.811~0.937,P=2.109×10−4),CD28- CD25++ CD8br AC(OR=0.867,95% CI=0.809~0.930,P=6.09×10−5),CD28-CD127-CD25++CD8brAC(OR=0.875,95%CI=0.814~0.942,P=3.619×10−4).THCA was associated with an increased risk of Secreting Treg % CD4 Treg (OR=1.143, 95% CI=1.064~1.229, P=2.779×10−4) and CD19 on IgD+ CD24+ (OR=1.118, 95% CI=1.041~1.120, P=0.002).ConclusionsThese findings suggest the causal associations between immune cells and THCA by genetic means. Our results may have the potential to provide guidance for future clinical research.

To explore the value of CT-based radiomics model in the differential diagnosis of benign ovarian tumors (BeOTs), borderline ovarian tumors (BOTs), and early malignant ovarian tumors (eMOTs). The retrospective research was conducted with pathologically confirmed 258 ovarian tumor patients from January 2014 to February 2021. The patients were randomly allocated to a training cohort ( n = 198) and a test cohort ( n = 60). By providing a three-dimensional (3D) characterization of the volume of interest (VOI) at the maximum level of images, 4238 radiomic features were extracted from the VOI per patient. The Wilcoxon–Mann–Whitney (WMW) test, least absolute shrinkage and selection operator (LASSO), and support vector machine (SVM) were employed to select the radiomic features. Five machine learning (ML) algorithms were applied to construct three-class diagnostic models. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the radiomics models. The test cohort was used to verify the generalization ability of the radiomics models. The receiver-operating characteristic (ROC) was used to evaluate diagnostic performance of radiomics model. Global and discrimination performance of five models was evaluated by average area under the ROC curve (AUC). The average ROC indicated that random forest (RF) diagnostic model in training cohort demonstrated the best diagnostic performance (micro/macro average AUC, 0.98/0.99), which was then confirmed with by LOOCV (micro/macro average AUC, 0.89/0.88) and external validation (test cohort) (micro/macro average AUC, 0.81/0.79). Our proposed CT-based radiomics diagnostic models may effectively assist in preoperatively differentiating BeOTs, BOTs, and eMOTs.

Background: Primary intraosseous meningioma of the skull (PIMS) is a rare type of primary extradural meningioma (PEM) involving cranial bone. The existing literature strongly suggest the importance of radiological feacures in pathological diagnosis of PIMS. Thereby, the aim of this study is to investigate the association between imaging classification and histopathological grading in PIMS. Methods: In this retrospective study, we retrospectively analyzed the computed tomography scan/magnetic resonance imaging and pathological data pertaining to patients with pathologically proven PIMS. The association between radiological features, imaging classification, and histopathological grading was analyzed using logistic regression analysis. Results: In this study, data of 25 patients with PIMS were assessed. The univariate logistic regression analysis results showed significant correlation between histopathological grading and imaging classification (OR: 22.5; 95% CI: 2.552 -198.378; p = 0.005), intra- and extracalvarial extension (OR: 7.2; 95% CI: 1.066 -48.639; p = 0.043), and tumor margin (OR: 7.19; 95% CI: 1.06 -47.61; p = 0.043). According to the results of multivariate logistic regression analysis, imaging classification was the strongest independent risk factor for high-grade PIMS, and the risk of aggressiveness of osteoblastic type of PIMS was 16.664 times higher than that of osteolytic type of PIMS (OR: 16.664; 95% CI: 1.15 -241.508; p = 0.039). Conclusions: Imaging classification is an independent risk factor for high-grade PIMS.

ObjectiveWe aimed to evaluate the diagnostic effectiveness of computed tomography (CT)-based radiomics for predicting lymph node metastasis (LNM) in patients diagnosed with esophageal cancer (EC).MethodsThe present study conducted a comprehensive search by accessing the following databases: PubMed, Embase, Cochrane Library, and Web of Science, with the aim of identifying relevant studies published until July 10th, 2023. The diagnostic accuracy was summarized using the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC). The researchers utilized Spearman’s correlation coefficient for assessing the threshold effect, besides performing meta-regression and subgroup analysis for the exploration of possible heterogeneity sources. The quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies-2 and the Radiomics Quality Score (RQS).ResultsThe meta-analysis included six studies conducted from 2018 to 2022, with 483 patients enrolled and LNM rates ranging from 27.2% to 59.4%. The pooled sensitivity, specificity, PLR, NLR, DOR, and AUC, along with their corresponding 95% CI, were 0.73 (0.67, 0.79), 0.76 (0.69, 0.83), 3.1 (2.3, 4.2), 0.35 (0.28, 0.44), 9 (6, 14), and 0.78 (0.74, 0.81), respectively. The results demonstrated the absence of significant heterogeneity in sensitivity, while significant heterogeneity was observed in specificity; no threshold effect was detected. The observed heterogeneity in the specificity was attributed to the sample size and CT-scan phases (P < 0.05). The included studies exhibited suboptimal quality, with RQS ranging from 14 to 16 out of 36. However, most of the enrolled studies exhibited a low-risk bias and minimal concerns relating to applicability.ConclusionThe present meta-analysis indicated that CT-based radiomics demonstrated a favorable diagnostic performance in predicting LNM in EC. Nevertheless, additional high-quality, large-scale, and multicenter trials are warranted to corroborate these findings.Systematic Review RegistrationOpen Science Framework platform at https://osf.io/5zcnd.

Background:Liver tumor segmentation based on medical imaging is playing an increasingly important role in liver tumor research and individualized therapeutic decision-making. However, it remains a challenging in terms of the accuracy of automatic segmentation of liver tumors. Therefore, we aimed to develop a novel deep neural network for improving the results from the automatic segmentation of liver tumors. Methods:This paper proposes the attention-guided context asymmetric fusion network (AGCAF-Net), combining attention guidance and fusion context modules on the basis of a residual neural network for the automatic segmentation of liver tumors. According to the attention-guided context block (AGCB), the feature map is first divided into multiple small blocks, the local correlation between features is calculated, and then the global nonlocal fusion module (GNFM) is used to obtain the global information between pixels. Additionally, the context pyramid module (CPM) and asymmetric semantic fusion module (AFM) are used to obtain multiscale features and resolve the feature mismatch during feature fusion, respectively. Finally, we used the liver tumor segmentation benchmark (LiTS) dataset to verify the efficiency of our designed network. Results:Our results showed that AGCAF-Net with AFM and CPM is effective in improving the accuracy of liver tumor segmentation, with the Dice coefficient increasing from 82.5% to 84.1%. The segmentation results of liver tumors by AGCAF-Net were superior to those of several state-of-the-art U-net methods, with a Dice coefficient of 84.1%, a sensitivity of 91.7%, and an average symmetric surface distance of 3.52. Conclusions:AGCAF-Net can obtain better matched and accurate segmentation in liver tumor segmentation, thus effectively improving the accuracy of liver tumor segmentation.

Simple and sensitive determination of total antioxidant capacity (TAC) in food samples is highly desirable. In this work, an electrochemical platform was established based on a silica nanochannel film (SNF)-modified electrode, facilitating fast and highly sensitive analysis of TAC in colored food samples. SNF was grown on low-cost and readily available tin indium oxide (ITO) electrode. Fe3+-phenanthroline complex-Fe(III)(phen)3 was applied as the probe, and underwent chemical reduction to form Fe2+-phenanthroline complex-Fe(II)(phen)3 in the presence of antioxidants. Utilizing an oxidative voltage of +1 V, chronoamperometry was employed to measure the current generated by the electrochemical oxidation of Fe(II)(phen)3, allowing for the assessment of antioxidants. As the negatively charged SNF displayed remarkable enrichment towards positively charged Fe(II)(phen)3, the sensitivity of detection can be significantly improved. When Trolox was employed as the standard antioxidant, the electrochemical sensor demonstrated a linear detection range from 0.01 μM to 1 μM and from 1 μM to 1000 μM, with a limit of detection (LOD) of 3.9 nM. The detection performance is better that that of the conventional colorimetric method with a linear de range from 1 μM to 40 μM. Owing to the anti-interfering ability of nanochannels, direct determination of TAC in colored samples including coffee, tea, and edible oils was realized.

To develop machine learning models based on preoperative dynamic enhanced magnetic resonance imaging (DCE-MRI) radiomics and to explore their potential prognostic value in the differential diagnosis of human epidermal growth factor receptor 2 (HER2)-low from HER2-positive breast cancer (BC). A total of 233 patients with pathologically confirmed invasive breast cancer admitted to our hospital between January 2018 and December 2022 were included in this retrospective analysis. Of these, 103 cases were diagnosed as HER2-positive and 130 cases were HER2 low-expression BC. The Synthetic Minority Oversampling Technique is employed to address the class imbalance problem. Patients were randomly split into a training set (163 cases) and a validation set (70 cases) in a 7:3 ratio. Radiomics features from DCE-MRI second-phase imaging were extracted. Z-score normalization was used to standardize the radiomics features, and Pearson’s correlation coefficient and recursive feature elimination were used to explore the significant features. Prediction models were constructed using 6 machine learning algorithms: logistic regression, random forest, support vector machine, AdaBoost, decision tree, and auto-encoder. Receiver operating characteristic curves were constructed, and predictive models were evaluated according to the area under the curve (AUC), accuracy, sensitivity, and specificity. In the training set, the AUC, accuracy, sensitivity, and specificity of all models were 1.000. However, in the validation set, the auto-encoder model’s AUC, accuracy, sensitivity, and specificity were 0.994, 0.976, 0.972, and 0.978, respectively. The remaining models’ AUC, accuracy, sensitivity, and specificity were 1.000. The DeLong test showed no statistically significant differences between the machine learning models in the training and validation sets (Z = 0, P = 1). Our study investigated the feasibility of using DCE-MRI-based radiomics features to predict HER2-low BC. Certain radiomics features showed associations with HER2-low BC and may have predictive value. Machine learning prediction models developed using these radiomics features could be beneficial for distinguishing between HER2-low and HER2-positive BC. These noninvasive preoperative models have the potential to assist in clinical decision-making for HER2-low breast cancer, thereby advancing personalized clinical precision.