Comparative evaluation of imaging methods for prognosis assessment in esophageal squamous cell carcinoma: focus on diffusion-weighted magnetic resonance imaging, computed tomography and esophagography.

Objective: To identify the most sensitive imaging examination method to evaluate the prognosis of esophageal squamous cell carcinoma (ESCC). Materials and methods: Thirty patients with esophageal squamous cell carcinoma (ESCC) participated in the study and underwent chemoradiotherapy (CRT). They were divided into two groups based on their survival status: the survival group and non-survival group. The diagnostic tests were utilized to determine the most effective imaging examination method for assessing the prognosis. Results: 1. There were no significant differences in tumor length shown on esophagography or computed tomography (CT) or the maximal esophageal wall thickness shown on CT at the specified time points between the two groups. 2. The tumor length on diffusion-weighted imaging (DWI) in the survival group was significantly lower than in the non-survival group at the end of the sixth week of treatment (P=0.001). The area under the ROC curve was 0.840 (P=0.002), and the diagnostic efficiency was moderately accurate. 3. The apparent diffusion coefficient (ADC) values of the survival group were significantly higher than those in the non-survival group at the end of the fourth week and sixth week of treatment (both P<0.001). Areas under the curve were 0.866 and 0.970, with P values of 0.001 and <0.001 and good diagnostic accuracy. Cox regression analyses indicated the ADC at the end of the sixth week of treatment was an independent risk factor. Conclusions: Compared with esophagography and CT, DW-MRI has certain advantages in predicting the prognosis of ESCC.

Pairwise machine learning-based automatic diagnostic platform utilizing CT images and clinical information for predicting radiotherapy locoregional recurrence in elderly esophageal cancer patients.

OBJECTIVE: To investigate the feasibility and accuracy of predicting locoregional recurrence (LR) in elderly patients with esophageal squamous cell cancer (ESCC) who underwent radical radiotherapy using a pairwise machine learning algorithm. METHODS: The 130 datasets enrolled were randomly divided into a training set and a testing set in a 7:3 ratio. Clinical factors were included and radiomics features were extracted from pretreatment CT scans using pyradiomics-based software, and a pairwise naive Bayes (NB) model was developed. The performance of the model was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). To facilitate practical application, we attempted to construct an automated esophageal cancer diagnosis system based on trained models. RESULTS: To the follow-up date, 64 patients (49.23%) had experienced LR. Ten radiomics features and two clinical factors were selected for modeling. The model demonstrated good prediction performance, with area under the ROC curve of 0.903 (0.829-0.958) for the training cohort and 0.944 (0.849-1.000) for the testing cohort. The corresponding accuracies were 0.852 and 0.914, respectively. Calibration curves showed good agreement, and DCA curve confirmed the clinical validity of the model. The model accurately predicted LR in elderly patients, with a positive predictive value of 85.71% for the testing cohort. CONCLUSIONS: The pairwise NB model, based on pre-treatment enhanced chest CT-based radiomics and clinical factors, can accurately predict LR in elderly patients with ESCC. The esophageal cancer automated diagnostic system embedded with the pairwise NB model holds significant potential for application in clinical practice.

Deep learning nomogram for predicting neoadjuvant chemotherapy response in locally advanced gastric cancer patients.

PURPOSE: Developed and validated a deep learning radiomics nomogram using multi-phase contrast-enhanced computed tomography (CECT) images to predict neoadjuvant chemotherapy (NAC) response in locally advanced gastric cancer (LAGC) patients. METHODS: This multi-center study retrospectively included 322 patients diagnosed with gastric cancer from January 2013 to June 2023 at two hospitals. Handcrafted radiomics technique and the EfficientNet V2 neural network were applied to arterial, portal venous, and delayed phase CT images to extract two-dimensional handcrafted and deep learning features. A nomogram model was built by integrating the handcrafted signature, the deep learning signature, with clinical features. Discriminative ability was assessed using the receiver operating characteristics (ROC) curve and the precision-recall (P-R) curve. Model fitting was evaluated using calibration curves, and clinical utility was assessed through decision curve analysis (DCA). RESULTS: The nomogram exhibited excellent performance. The area under the ROC curve (AUC) was 0.848 [95% confidence interval (CI), 0.793-0.893)], 0.802 (95% CI 0.688-0.889), and 0.751 (95% CI 0.652-0.833) for the training, internal validation, and external validation sets, respectively. The AUCs of the P-R curves were 0.838 (95% CI 0.756-0.895), 0.541 (95% CI 0.329-0.740), and 0.556 (95% CI 0.376-0.722) for the corresponding sets. The nomogram outperformed the clinical model and handcrafted signature across all sets (all P < 0.05). The nomogram model demonstrated good calibration and provided greater net benefit within the relevant threshold range compared to other models. CONCLUSION: This study created a deep learning nomogram using CECT images and clinical data to predict NAC response in LAGC patients undergoing surgical resection, offering personalized treatment insights.

Prediction of lymph node metastasis in advanced gastric adenocarcinoma based on dual-energy CT radiomics: focus on the features of lymph nodes with a short axis diameter ≥6 mm.

Objective: To explore the value of the features of lymph nodes (LNs) with a short-axis diameter ≥6 mm in predicting lymph node metastasis (LNM) in advanced gastric adenocarcinoma (GAC) based on dual-energy CT (DECT) radiomics. Materials and methods: Data of patients with GAC who underwent radical gastrectomy and LN dissection were retrospectively analyzed. To ensure the correspondence between imaging and pathology, metastatic LNs were only selected from patients with pN3, nonmetastatic LNs were selected from patients with pN0, and the short-axis diameters of the enrolled LNs were all ≥6 mm. The traditional features of LNs were recorded, including short-axis diameter, long-axis diameter, long-to-short-axis ratio, position, shape, density, edge, and the degree of enhancement; univariate and multivariate logistic regression analyses were used to establish a clinical model. Radiomics features at the maximum level of LNs were extracted in venous phase equivalent 120 kV linear fusion images and iodine maps. Intraclass correlation coefficients and the Boruta algorithm were used to screen significant features, and random forest was used to build a radiomics model. To construct a combined model, we included the traditional features with statistical significance in univariate analysis and radiomics scores (Rad-score) in multivariate logistic regression analysis. Receiver operating curve (ROC) curves and the DeLong test were used to evaluate and compare the diagnostic performance of the models. Decision curve analysis (DCA) was used to evaluate the clinical benefits of the models. Results: This study included 114 metastatic LNs from 36 pN3 cases and 65 nonmetastatic LNs from 28 pN0 cases. The samples were divided into a training set (n=125) and a validation set (n=54) at a ratio of 7:3. Long-axis diameter and LN shape were independent predictors of LNM and were used to establish the clinical model; 27 screened radiomics features were used to build the radiomics model. LN shape and Rad-score were independent predictors of LNM and were used to construct the combined model. Both the radiomics model (area under the curve [AUC] of 0.986 and 0.984) and the combined model (AUC of 0.970 and 0.977) outperformed the clinical model (AUC of 0.772 and 0.820) in predicting LNM in both the training and validation sets. DCA showed superior clinical benefits from radiomics and combined models. Conclusion: The models based on DECT LN radiomics features or combined traditional features have high diagnostic performance in determining the nature of each LN with a short-axis diameter of ≥6 mm in advanced GAC.

Furan-based fluorescent probe free radical capture membrane: Analysis of RO2 radical composition and transformation mechanism in urban atmosphere.

Peroxyl radicals (RO2) are important components of atmospheric radical cycling and generation, but their formation, distribution and evolution mechanisms in the atmospheric environment have not been investigated. In this paper, we propose a novel atmospheric RO2 radical trapping membrane that can trap low carbon number (Rc ≤ 5) RO2 radicals and identify their R-group structures by fluorescence spectroscopy and chromatography. We also analyzed the composition and evolution mechanism of RO2 species under different meteorological conditions in the atmospheric environment of Lanzhou, China, to provide scientific support for the treatment and research of atmospheric chemical pollution.

Computed tomography radiomics identification of T1-2 and T3-4 stages of esophageal squamous cell carcinoma: two-dimensional or three-dimensional?

BACKGROUND: To evaluate two-dimensional (2D) and three-dimensional (3D) computed tomography (CT) radiomics analysis for the T stage of esophageal squamous cell carcinoma (ESCC). METHODS: 398 patients with pathologically confirmed ESCC were divided into training and testing sets. All patients underwent chest CT scans preoperatively. For each tumor, based on CT images, a 2D region of interest (ROI) was outlined on the largest cross-sectional area, and a 3D ROI was outlined layer by layer on each section of the tumor. The radiomics platform was used for feature extraction. For feature selection, stepwise logistic regression was used. The receiver operating characteristic (ROC) curve was used to assess the diagnostic performance of the 2D radiomics model versus the 3D radiomics model. The differences were compared using the DeLong test. The value of the clinical utility of the two radiomics models was evaluated. RESULTS: 1595 radiomics features were extracted. After screening, two radiomics models were constructed. In the training set, the difference between the area under the curve (AUC) of the 2D radiomics model (AUC = 0.831) and the 3D radiomics model (AUC = 0.830) was not statistically significant (p = 0.973). In the testing set, the difference between the AUC of the 2D radiomics model (AUC = 0.807) and the 3D radiomics model (AUC = 0.797) was also not statistically significant (p = 0.748). A 2D model was equally useful as a 3D model in clinical situations. CONCLUSION: The performance of 2D radiomics model is comparable to that of 3D radiomics model in distinguishing between the T1-2 and T3-4 stages of ESCC. In addition, 2D radiomics model may be a more feasible option due to the shorter time required for segmenting the ROI.

Comparison of TNM AJCC/UICC 8th with JES 11th staging systems for prognostic prediction in patients with esophageal squamous cell carcinoma who underwent radical (chemo) radiotherapy in China.

OBJECTIVE: The aim of the study was to compare the prognostic prediction performances of the American Joint Committee on Cancer (AJCC)/Union for International Cancer Control (UICC) 8th staging system and the Japan Esophageal Society (JES) 11th staging system for patients with esophageal squamous cell carcinoma who underwent radical (chemo) radiotherapy. METHODS: In total, 574 patients were enrolled and categorized according to the tumor, node metastasis (TNM) AJCC/UICC 8th and JES 11th editions. Survival rates and disease-free survival were computed using the Kaplan-Meier technique. The log-rank test was used for survival difference analysis. RESULTS: (1) The 8th AJCC/UICC N staging exhibited significant stratification for overall survival (OS) and progression-free survival (PFS). JES 11th showed significant OS stratification, but PFS was not well-stratified for N2-N4. (2) Both staging systems demonstrated significant stratification for OS and PFS. (3) AJCC/UICC 8th TNM staging yielded significantly well-stratified OS and PFS in the differing staging group. JES 11th failed to stratify OS and PFS for stages III and IVA. (4) AJCC/UICC 8th TNM stratified OS and PFS significantly well for lower and middle region tumors, whereas JES 11th inadequately stratified stages III and IVA. (5) Significant multivariable analysis results indicated that AJCC/UICC 8th independently predicted poor OS and PFS. CONCLUSIONS: In Chinese patients with esophageal squamous cell carcinoma who underwent radical (chemo) radiotherapy, the AJCC/UICC 8th edition exhibited superior prognostic prediction capabilities compared with the JES 11th edition.

MicroRNA-22-3p alleviates atherosclerosis by mediating macrophage M2 polarization as well as inhibiting NLRP3 activation.

OBJECTIVE: MicroRNA (miR)-22-3p is expressed in atherosclerosis (AS), but its function and regulatory mechanisms remain unclear. Therefore, the effects of miR-22-3p in AS were assessed in this study. METHODS: MiR-22-3p expression was assessed in AS, and miR-22-3p target genes were predicted using sequencing transcriptomics. The effect of miR-22-3p agomir on atherosclerotic lesions in an AS mouse model were determined by Oil red O, Masson's, and sirius red staining, and by anti-smooth muscle actin and macrophage antigen-3 immunostaining. Gene expression in AS was evaluated by western blot and immunofluorescence. RESULTS: MiR-22-3p was expressed in AS and control samples (32.5% and 33.9% levels, respectively, relative to total miRNA among six highly expressed miRNAs). In the mouse model of AS, miR-22-3p agomir significantly reduced lipid deposition, proliferation of aortic collagen fibres, and macrophage content. Additionally, inducible nitric oxide synthase, interleukin-6, and tumour necrosis factor-α levels were significantly reduced, and levels of arginase 1 and CD206 were significantly enhanced. MiR-22-3p was found to target janus kinase 1(JAK1), and significantly inhibited the activation of NLR family pyrin domain containing 3 (NLRP3) and JAK1 in mice. CONCLUSIONS: MiR-22-3p appears to reduce the inflammatory response in AS, which might be achieved by inducing the M2 macrophage phenotype and suppressing NLRP3 activation via JAK1.

Computed tomographic imaging features to differentiate gastric schwannomas from gastrointestinal stromal tumours: a matched case-control study.

To investigate clinical data and computed tomographic (CT) imaging features in differentiating gastric schwannomas (GSs) from gastric stromal tumours (GISTs) in matched patients, 31 patients with GSs were matched with 62 patients with GISTs (1:2) in sex, age, and tumour site. The clinical and imaging data were analysed. A significant (P < 0.05) difference was found in the tumour margin, enhancement pattern, growth pattern, and LD values between the 31 patients with GSs and 62 matched patients with GISTs. The GS lesions were mostly (93.5%) well defined while only 61.3% GIST lesions were well defined.The GS lesions were significantly (P = 0.036) smaller than the GIST lesions, with the LD ranging 1.5-7.4 (mean 3.67 cm) cm for the GSs and 1.0-15.30 (mean 5.09) cm for GIST lesions. The GS lesions were more significantly (P = 0.001) homogeneously enhanced (83.9% vs. 41.9%) than the GIST lesions. The GS lesions were mainly of the mixed growth pattern both within and outside the gastric wall (74.2% vs. 22.6%, P < 0.05) compared with that of GISTs. No metastasis or invasion of adjacent organs was present in any of the GS lesions, however, 1.6% of GISTs experienced metastasis and 3.2% of GISTs presented with invasion of adjacent organs. Heterogeneous enhancement and mixed growth pattern were two significant (P < 0.05) independent factors for distinguishing GS from GIST lesions. In conclusion: GS and GIST lesions may have significantly different features for differentiation in lesion margin, heterogeneous enhancement, mixed growth pattern, and longest lesion diameter, especially heterogeneous enhancement and mixed growth pattern.

Magnetic resonance imaging findings of pulmonary sclerosing pneumocytoma: a case report and literature review.

Background: Pulmonary sclerosing pneumocytoma (PSP) is a rare lung tumor that is mostly isolated and commonly reported among middle-aged East Asian women. Recently, Immunohistochemistry (IHC) analysis has suggested that PSP is of primitive epithelial origin, most likely derived from type II alveolar air cells. Patients with PSP are generally asymptomatic and usually detected for other unrelated reasons during routine imaging. Several studies have already investigated the computed tomography (CT) features of PSP and their correlation with pathology. Magnetic resonance imaging (MRI) is a radiation-free imaging technique with important diagnostic value for specific pulmonary nodules. However, very few case reports or studies focus on the MRI findings of PSP. Case report: We reported a case of an asymptomatic 56-year-old female with a solitary, well-defined soft-tissue mass in the lower lobe of the left lung. The mass showed iso-to-high signal intensity (SI) than muscle on T1-weighted image (T1WI) and T2-weighted image (T2WI) and a much higher SI on fat-suppressed T2WI, diffusion-weighted image, and apparent diffusion coefficient image. Contrast-enhanced fat-suppressed T1WI revealed noticeable inhomogeneous progressive enhancement throughout the mass. The mass revealed early enhancement without a significant peak, followed by a plateau pattern on dynamic contrast-enhanced MRI images. The patient underwent left basal segmentectomy via thoracoscopic surgery. Histopathology and IHC results of the surgical specimen confirmed that it was a PSP. We concluded that the MRI findings of PSP might adequately reflect the different components within the tumor and aid clinicians in preoperative diagnosis and assessment. To the best of our knowledge, this is the most comprehensive case report on the MRI findings of PSP. Conclusion: The MRI findings of PSP correspond to its histopathological features. Here, we present a case of PSP with the most comprehensive MRI findings, emphasizing the importance of multiple-sequence MRI in diagnosing PSP.

The use of mammography-based radiomics nomograms for the preoperative prediction of the histological grade of invasive ductal carcinoma.

BACKGROUND: Accurate prediction of the grade of invasive ductal carcinoma (IDC) before treatment is vital for individualized therapy and improving patient outcomes. This study aimed to develop and validate a mammography-based radiomics nomogram that would incorporate the radiomics signature and clinical risk factors in the preoperative prediction of the histological grade of IDC. METHODS: The data of 534 patients from our hospital with pathologically confirmed IDC (374 in the training cohort and 160 in the validation cohort) were retrospectively analyzed. A total of 792 radiomics features were extracted from the patients' craniocaudal and mediolateral oblique view images. A radiomics signature was generated using the least absolute shrinkage and selection operator method. Multivariate logistic regression was adopted to establish a radiomics nomogram, the utility of which was evaluated using a receiver-operating characteristic curve, calibration curve, and decision curve analysis (DCA). RESULTS: The radiomics signature was found to have a significant correlation with histological grade (P < 0.01), but the efficacy of the model is limited. The radiomics nomogram, which incorporated the radiomics signature and spicule sign into mammography, showed good consistency and discrimination in both the training cohort [area under the curve (AUC) = 0.75] and the validation cohort (AUC = 0.75). The calibration curves and DCA demonstrated the clinical usefulness of the proposed radiomics nomogram model. CONCLUSIONS: A radiomics nomogram based on the radiomics signature and spicule sign can be used to predict the histological grade of IDC and assist in clinical decision-making for patients with IDC.

CT Radiomics Combined With Clinicopathological Features to Predict Invasive Mucinous Adenocarcinoma in Patients With Lung Adenocarcinoma.

Objective: This study aimed to develop and validate predictive models using clinical parameters, radiomic features, and a combination of both for invasive mucinous adenocarcinoma (IMA) of the lung in patients with lung adenocarcinoma. Method: A total of 173 and 391 patients with IMA and non-IMA, respectively, were retrospectively analyzed from January 2017 to September 2022 in our hospital. Propensity Score Matching was used to match the 2 groups of patients. A total of 1037 radiomic features were extracted from contrast-enhanced computed tomography (CT). The patients were randomly divided into training and test groups at a ratio of 7:3. The least absolute shrinkage and selection operator algorithm was used for radiomic feature selection. Three radiomics prediction models were applied: logistic regression (logistic), support vector machine (SVM), and decision tree. The best-performing model was adopted, and the radiomics score (Radscore) was then computed. A clinical model was developed using logistic regression. Finally, a combined model was established based on a clinical model and a radiomics model. The area under the receiver operating characteristic (ROC) curve (AUC) and decision curve analysis were used to evaluate the predictive value of the developed models. Results: Both clinical and radiomics models established using the logistic method showed the best performance. The Delong test revealed that the combined model was superior to the clinical and radiomics models (P = .018 and .020, respectively). The ROC-AUC (also decision curve analysis) of the combined model was 0.840 and 0.850 in the training and testing groups, respectively, which showed good predictive performance for IMA. The Brier scores for the combined model were 0.161 and 0.154 in the training and testing groups, respectively. Conclusion: The combined model incorporating radiomic CT features and clinical predictors may have the potential to predict IMA in patients with lung cancer.

Computed tomography features of gastric leiomyoma versus gastric stromal tumor: a case-control study with propensity score matching.

OBJECTIVE: To differentiate gastric leiomyomas (GLs) and gastric stromal tumors (GSTs) based on preoperative enhanced computed tomography characteristics. METHODS: Twenty-six pathologically confirmed GLs were propensity score-matched to 26 GSTs in a 1:1 ratio based on sex, age, tumor site, and tumor size. Tumor shape and contour, mucosal ulceration, growth pattern, enhancement pattern and degree, longest diameter, and longest diameter/vertical diameter ratio were compared between the groups. Hemorrhage, calcification, peripheral invasion, and distant metastasis were also included in the regression analysis for differentiation of the two tumors. RESULTS: Mucosal ulceration was significantly more frequent in GSTs than GLs. The enhancement degree of GSTs was significantly higher than that of GLs in the arterial and portal venous phases. Using enhancement degrees of 18 HU and 23 HU in the arterial phase and venous phase as cutoff values, respectively, we found that an enhancement degree of <18 HU in the arterial phase was an independent influential factor for diagnosis of GLs. No significant differences were found in other morphological characteristics. GLs did not metastasize or invade adjacent tissues. CONCLUSION: A low enhancement degree in GLs is the most valuable quantitative feature for differentiating these two similar tumors.

Identification of gastric schwannoma and non-metastatic gastric stromal tumor by CT: a single-institution retrospective diagnostic test.

Background: Gastric schwannoma (GS) was a rare mesenchymal tumor that was difficult to distinguish from a non-metastatic gastric stromal tumor (GST). The nomogram constructed by CT features had an advantage in the differential diagnosis of gastric malignant tumors. Therefore, we conducted a retrospective analysis of their respective computed tomography (CT) features. Methods: We conducted a retrospective single-institution review of resected GS and non-metastatic GST between January 2017 and December 2020. Patients who were pathologically confirmed after surgery and underwent CT within two weeks before surgery were selected. The exclusion criteria were as follows: incomplete clinical data; CT images that were incomplete or of poor quality. A binary logistic regression model was built for analysis. Through univariate and multivariate analysis, CT image features were evaluated to determine the significant differences between GS and GST. Results: The study population comprised 203 consecutive patients (29 with GS and 174 with GST). There were significant differences in gender distribution (P=0.042) and symptoms (P=0.002). Besides, GST tended to involve the presence of necrosis (P=0.003) and lymph nodes (P=0.003). The area under the curve (AUC) value of unenhanced CT (CTU) was 0.708 [95% confidence interval (CI): 62.10-79.56%], the AUC value of venous phase CT (CTP) was 0.774 (95% CI: 69.45-85.34%), and the AUC value of venous phase enhancement (CTPU) was 0.745 (95% CI: 65.87-83.06%). CTP was the most specific feature, with a sensitivity of 83% and a specificity of 66%. The ratio of long diameter to short diameter (LD/SD) was significantly different (P=0.003). The AUC of the binary logistic regression model was 0.904. Multivariate analysis showed that necrosis and LD/SD were independent factors affecting the identification of GS and GST. Conclusions: LD/SD was a novel distinguishing feature between GS and non-metastatic GST. In conjunction with CTP, LD/SD, location, growth pattern, necrosis, and lymph node, a nomogram was constructed to predict.

A comparison of the use of contrast media with different iodine concentrations for enhanced computed tomography.

Objective: In this study, we compared the enhancement of blood vessels and liver parenchyma on enhanced computed tomography (CT) of the upper abdomen with two concentrations of contrast media (400 and 300 mg I/mL) based on similar iodine delivery rate (IDR) of 0.88 and 0.9 g I/s and iodine load of 450 mg I/kg. Methods: We randomly assigned 160 patients into two groups: iomeprol 400 mg I/mL (A group) and iohexol 300 mg I/mL (B group). The CT attenuation values of the main anatomical structures in the two groups with different scanning phases were measured and the image quality of the two groups was analyzed and compared. The peak pressure and local discomfort (including fever and pain) during contrast medium injection were recorded. Results: The mean attenuation value of the abdominal aorta was 313.6 ± 29.6 in the A group and 322.4 ± 30.1 in the B group during the late arterial phase (p = 0.8). Meanwhile, the mean enhancement values of the portal vein were 176.2 ± 19.3 and 165.9 ± 24.5 in the A and B groups, respectively, during the portal venous phase (p = 0.6). The mean CT values of liver parenchyma were 117.1 ± 15.3 and 108.8 ± 18.7 in the A and B groups, respectively, during the portal venous phase (p = 0.9). There was no statistical difference in image quality, peak injection pressure (psi), and local discomfort between the two groups (p > 0.05). Conclusion: When a similar IDR and the same iodine load are used, CT images with different concentrations of contrast media have the same subjective and objective quality, and can meet the diagnostic needs.

Preoperative assessment of high-grade endometrial cancer using a radiomic signature and clinical indicators.

Aim: To develop and validate a radiomics-based combined model (ModelRC) to predict the pathological grade of endometrial cancer. Methods: A total of 403 endometrial cancer patients from two independent centers were enrolled as training, internal validation and external validation sets. Radiomic features were extracted from T2-weighted images, apparent diffusion coefficient map and contrast-enhanced 3D volumetric interpolated breath-hold examination images. Results: Compared with the clinical model and radiomics model, ModelRC showed superior performance; the areas under the receiver operating characteristic curves were 0.920 (95% CI: 0.864-0.962), 0.882 (95% CI: 0.779-0.955) and 0.881 (95% CI: 0.815-0.939) for the training, internal validation and external validation sets, respectively. Conclusion: ModelRC, which incorporated clinical and radiomic features, exhibited excellent performance in the prediction of high-grade endometrial cancer.

Accurate preoperative evaluation of the pathological grade of endometrial carcinoma is very important for the selection of treatment and prognosis. This study tried to develop a simple combined model based on radiomic features from endometrial carcinoma MRI and clinical features of patients. Compared with the clinical model and the radiomic model, the combined model showed superior performance. Therefore, this combined model would help patients and clinicians to make more rational decisions when choosing treatment strategies.

Radiomics nomogram for preoperative differentiation of pulmonary mucinous adenocarcinoma from tuberculoma in solitary pulmonary solid nodules.

OBJECTIVE: To develop and validate predictive models using clinical parameters, radiomic features and a combination of both for preoperative differentiation of pulmonary nodular mucinous adenocarcinoma (PNMA) from pulmonary tuberculoma (PTB). METHOD: A total of 124 and 53 patients with PNMA and PTB, respectively, were retrospectively analyzed from January 2017 to November 2022 in The Fourth Affiliated Hospital of Hebei Medical University (Ligang et al., A machine learning model based on CT and clinical features to distinguish pulmonary nodular mucinous adenocarcinoma from tuberculoma, 2023). A total of 1037 radiomic features were extracted from contrast-enhanced computed tomography (CT). The patients were randomly divided into a training group and a test group at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used for radiomic feature selection. Three radiomics prediction models were applied: logistic regression (LR), support vector machine (SVM) and random forest (RF). The best performing model was adopted, and the radiomics score (Radscore) was then computed. The clinical model was developed using logistic regression. Finally, a combined model was established based on clinical factors and radiomics features. We externally validated the three models in a group of 68 patients (46 and 22 patients with PNMA and PTB, respectively) from Xing Tai People's Hospital (30 and 14 patients with PNMA and PTB, respectively) and The First Hospital of Xing Tai (16 and 8 patients with PNMA and PTB, respectively). The area under the receiver operating characteristic (ROC) curve (AUC) value and decision curve analysis were used to evaluate the predictive value of the developed models. RESULTS: The combined model established by the logistic regression method had the best performance. The ROC-AUC (also a decision curve analysis) of the combined model was 0.940, 0.990 and 0.960 in the training group, test group and external validation group, respectively, and the combined model showed good predictive performance for the differentiation of PNMA from PTB. The Brier scores of the combined model were 0.132 and 0.068 in the training group and test group, respectively. CONCLUSION: The combined model incorporating radiomics features and clinical parameters may have potential value for the preoperative differentiation of PNMA from PTB.

Computed-tomography-based radiomic nomogram for predicting the risk of indeterminate small (5-20 mm) solid pulmonary nodules

PURPOSE: This study aims to develop a diagnostic model that combines computed tomography (CT) images and radiomic features to differentiate indeterminate small (5-20 mm) solid pulmonary nodules (SSPNs). METHODS: This study retrospectively enrolled 413 patients who had had SSPNs surgically removed and histologically confirmed between 2017 and 2019. The SSPNs included solid malignant pulmonary nodules (n = 210) and benign pulmonary nodules (n = 203). The least absolute shrinkage and selection operator was used for radiomic feature selection, and random forest algorithms were used for radiomic model construction. The clinical model and nomogram were established using univariate and multivariable logistic regression analyses combined with clinical symptoms, subjective CT findings, and radiomic features. The area under the curve (AUC) of the receiver operating characteristic curve was used to evaluate the performance of the models. RESULTS: The AUC for the clinical model was 0.77 in the training cohort [n = 289; 95% confidence interval (CI): 0.71-0.82; P = 0.001] and 0.75 in the validation cohort (n = 124; 95% CI: 0.66-0.83; P = 0.016). The AUCs for the nomogram were 0.92 (95% CI: 0.89-0.95; P < 0.001) and 0.85 (95% CI: 0.78-0.91; P < 0.001), respectively. The radiomic score (Rad-score), sex, pleural indentation, and age were the independent predictors that were used to build the nomogram. CONCLUSION: The radiomic nomogram derived from clinical features, subjective CT signs, and the Rad-score can potentially identify the risk of indeterminate SSPNs and aid in the patient's preoperative diagnosis.

Radiomics-based analysis of CT imaging for the preoperative prediction of invasiveness in pure ground-glass nodule lung adenocarcinomas.

OBJECTIVE: The purpose of the study is to investigate the performance of radiomics-based analysis in prediction of pure ground-glass nodule (pGGN) lung adenocarcinomas invasiveness using thin-section computed tomography images. METHODS: A total of 382 patients surgically resected single pGGN and pathologically confirmed were enrolled in the retrospective study. The pGGN cases were divided into two groups: the noninvasive group and the invasive adenocarcinoma (IAC) group. 330 patients were randomly assigned to the training and testing cohorts with a ratio of 7:3 (245 noninvasive lesions, 85 IAC lesions), while 52 patients (30 noninvasive lesions, 22 IAC lesions) were assigned to the external validation cohort. A model, radiomics model, and combined clinical-radiographic-radiomic model were built using the LASSO and multivariate backward stepwise regression analysis on the basis of the selected and radiomics features. The area under the curve (AUC) and decision curve analysis (DCA) were used to evaluate and compare the model performance for invasiveness discrimination among the three cohorts. RESULTS: Three clinical-radiographic features (including age, gender and the mean CT value) and three radiomics features were selected for model building. The combined model and radiomics model performed better than the clinical-radiographic model. The AUCs of the combined model in the training, testing, and validation cohorts were 0.856, 0.859, and 0.765, respectively. The DCA demonstrated the radiomics signatures incorporating clinical-radiographic feature was clinically useful in predicting pGGN invasiveness. CONCLUSIONS: The proposed radiomics-based analysis incorporating the clinical-radiographic feature could accurately predict pGGN invasiveness, providing a noninvasive biomarker for the individualized and precise medical treatment of patients.

Construction of a nomogram model for predicting peritoneal metastasis in gastric cancer: focused on cardiophrenic angle lymph node features.

BACKGROUND: A different treatment was used when peritoneal metastases (PM) occurred in patients with gastric cancer (GC). Certain cancers' peritoneal metastasis could be predicted by the cardiophrenic angle lymph node (CALN). This study aimed to establish a predictive model for PM of gastric cancer based on the CALN. METHODS: Our center retrospectively analyzed all GC patients between January 2017 and October 2019. Pre-surgery computed tomography (CT) scans were performed on all patients. The clinicopathological and CALN features were recorded. PM risk factors were identified via univariate and multivariate logistic regression analyses. The receiver operator characteristic (ROC) curves were generated using these CALN values. Using the calibration plot, the model fit was assessed. A decision curve analysis (DCA) was conducted to assess the clinical utility. RESULTS: 126 of 483 (26.1%) patients were confirmed as having peritoneal metastasis. These relevant factors were associated with PM: age, sex, T stage, N stage, enlarged retroperitoneal lymph nodes (ERLN), CALN, the long diameter of the largest CALN (LD of LCALN), the short diameter of the largest CALN (SD of LCALN), and the number of CALNs (N of CALNs). The multivariate analysis illustrated that the LD of LCALN (OR = 2.752, p < 0.001) was PM's independent risk factor in GC patients. The area under the curve (AUC) of the model was 0.907 (95% CI 0.872-0.941), demonstrating good performance in the predictive value of PM. There is excellent calibration evident from the calibration plot, which is close to the diagonal. The DCA was presented for the nomogram. CONCLUSION: CALN could predict gastric cancer peritoneal metastasis. The model in this study provided a powerful predictive tool for determining PM in GC patients and helping clinicians allocate treatment.