To evaluate the ability of preoperative MRI-based radiomic features in predicting lymph node metastasis (LNM) in patients with cervical cancer. PubMed, Embase, Web of Science, Cochrane Library databases, and four Chinese databases were searched to identify relevant studies published up until October 22, 2021. Two reviewers screened all papers independently for eligibility. We included diagnostic accuracy studies that used radiomics-MRI for LNM in patients with cervical cancer, using histopathology as the reference standard.Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Radiomics Quality Score. Overall diagnostic odds ratio (DOR), sensitivity, specificity and area under the curve (AUC) were calculated to assess the prediction efficacy of MRI-based radiomic features in patients with cervical cancer. Spearman's correlation coefficient was calculated and subgroup analysis performed to investigate causes of heterogeneity. Twelve studies comprising 793 female patients were included. The pooled DOR, sensitivity, specificity, and AUC of radiomics in detecting LNM were 12.08 [confidence interval (CI) 8.18, 17.85], 80% (72%, 87%), 76% (72%, 80%), and 0.83 (0.76, 0.89), respectively. The meta-analysis showed significant heterogeneity among the included studies. No threshold effect was detected. Subgroup analysis showed that multiple sequences, and radiomics combined with clinical factors, radiomics approach [DOR:15.49 (6.06, 39.62), 18.93 (8.46, 42.38), and 10.63 (6.23, 18.12), respectively] could slightly improve diagnostic performance compared with apparent diffusion coefficient-based radiomic features, T2 + dynamic contrast-enhanced MRI-based radiomic features, T2 images-based radiomic features, single radiomics, and human reading [DOR: 4.9 (1.91, 12.74), 7.63 (3.78, 15.38), 8.31 (3.05, 22.61), 16.10 (9.10, 28.47), and 6.46 (3.08, 13.56), respectively]. Our meta-analysis showed that preoperative MRI-based radiomic features performs well in predicting LNM in patients with cervical cancer. This noninvasive and convenient tool may be used to facilitate preoperative identification of LNM.

Objective: The aim of this study was to perform a meta‐analysis to evaluate the diagnostic performance of machine learning(ML)-based radiomics of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) DCE-MRI in predicting axillary lymph node metastasis (ALNM) and sentinel lymph node metastasis(SLNM) in breast cancer. Methods: English and Chinese databases were searched for original studies. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and Radiomics Quality Score (RQS) were used to assess the methodological quality of the included studies. The pooled sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC) were used to summarize the diagnostic accuracy. Spearman’s correlation coefficient and subgroup analysis were performed to investigate the cause of the heterogeneity. Results: Thirteen studies (1618 participants) were included in this meta-analysis. The pooled sensitivity, specificity, DOR, and AUC with 95% confidence intervals were 0.82 (0.75, 0.87), 0.83 (0.74, 0.89), 21.56 (10.60, 43.85), and 0.89 (0.86, 0.91), respectively. The meta-analysis showed significant heterogeneity among the included studies. There was no threshold effect in the test. The result of subgroup analysis showed that ML, 3.0 T, area of interest comprising the ALN, being manually drawn, and including ALNs and combined sentinel lymph node (SLN)s and ALNs groups could slightly improve diagnostic performance compared to deep learning, 1.5 T, area of interest comprising the breast tumor, semiautomatic scanning, and the SLN, respectively. Conclusions: ML-based radiomics of DCE-MRI has the potential to predict ALNM and SLNM accurately. The heterogeneity of the ALNM and SLNM diagnoses included between the studies is a major limitation.

Purpose. This study aimed to investigate the value of biparametric magnetic resonance imaging (bp-MRI)-based radiomics signatures for the preoperative prediction of prostate cancer (PCa) grade compared with visual assessments by radiologists based on the Prostate Imaging Reporting and Data System Version 2.1 (PI-RADS V2.1) scores of multiparametric MRI (mp-MRI). Methods. This retrospective study included 142 consecutive patients with histologically confirmed PCa who were undergoing mp-MRI before surgery. MRI images were scored and evaluated by two independent radiologists using PI-RADS V2.1. The radiomics workflow was divided into five steps: (a) image selection and segmentation, (b) feature extraction, (c) feature selection, (d) model establishment, and (e) model evaluation. Three machine learning algorithms (random forest tree (RF), logistic regression, and support vector machine (SVM)) were constructed to differentiate high-grade from low-grade PCa. Receiver operating characteristic (ROC) analysis was used to compare the machine learning-based analysis of bp-MRI radiomics models with PI-RADS V2.1. Results. In all, 8 stable radiomics features out of 804 extracted features based on T2-weighted imaging (T2WI) and ADC sequences were selected. Radiomics signatures successfully categorized high-grade and low-grade PCa cases ( ) in both the training and test datasets. The radiomics model-based RF method (area under the curve, AUC: 0.982; 0.918), logistic regression (AUC: 0.886; 0.886), and SVM (AUC: 0.943; 0.913) in both the training and test cohorts had better diagnostic performance than PI-RADS V2.1 (AUC: 0.767; 0.813) when predicting PCa grade. Conclusions. The results of this clinical study indicate that machine learning-based analysis of bp-MRI radiomic models may be helpful for distinguishing high-grade and low-grade PCa that outperformed the PI-RADS V2.1 scores based on mp-MRI. The machine learning algorithm RF model was slightly better.

Background: Non-muscle-invasive bladder cancer (NMIBC) is categorized into high and low grades with different clinical treatments and prognoses. Thus, accurate preoperative evaluation of the histologic NMIBC grade through imaging techniques is essential.Objectives: To develop and validate an MRI-based radiomics nomogram for individualized prediction of NMIBC grading.Methods: The study included 169 consecutive patients with NMIBC (training cohort: n = 118, validation cohort: n = 51). A total of 3148 radiomic features were extracted, and one-way analysis of variance and least absolute shrinkage and selection operator were used to select features for building the radiomics score(Rad-score). Three models to predict NMIBC grading were developed using logistic regression analysis: a clinical model, a radiomics model and a radiomics–clinical combined nomogram model. The discrimination and calibration power and clinical applicability of the models were evaluated. The diagnostic performance of each model was compared by determining the area under the curve (AUC) in receiver operating characteristic (ROC) curve analysis.Results: A total of 24 features were used to build the Rad-score. A clinical model, a radiomics model, and a radiomics–clinical nomogram model that incorporated the Rad-score, age, and number of tumors were constructed. The radiomics model and nomogram showed AUCs of 0.910 and 0.931 in the validation set, which outperformed the clinical model (0.745). The decision curve analysis also showed that the radiomics model and combined nomogram model yielded higher net benefits than the clinical model.Conclusion: A radiomics–clinical combined nomogram model has the potential to be used as a non-invasive tool for the differentiating low-from high-grade NMIBCs.

Objective: The aim of this study was to establish a predictive nomogram for predicting prostate cancer (PCa) in patients with gray-zone prostate-specific antigen (PSA) levels (4–10.0 ng/mL) based on radiomics and other traditional clinical parameters. Methods: In all, 274 patients with gray-zone PSA levels were included in this retrospective study. They were randomly divided into training and validation sets (n = 191 and 83, respectively). Data on the clinical risk factors related to PCa with gray-zone PSA levels (such as Prostate Imaging Reporting and Data System, version 2.1 [PI-RADS V2.1] category, age, prostate volume, and serum PSA level) were collected for all patients. Lesion volumes of interest (VOI) from T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) imaging were annotated by two radiologists. The radiomics model, clinical model, and combined prediction model, which was presented on a nomogram by incorporating the radiomics signature and clinical and radiological risk factors for PCa, were developed using logistic regression. The area under the receiver operator characteristic (AUC-ROC) and decision, calibration curve were used to compare the three models for the diagnosis of PCa with gray-zone PSA levels. Results: The predictive nomogram (AUC: 0.953) incorporating the radiomics score and PI-RADS V2.1 category, age, and the radiomics model (AUC: 0.941) afforded much higher diagnostic efficacy than the clinical model (AUC: 0.866). The addition of the rad score could improve the discriminatory performance of the clinical model. The decision curve analysis indicated that the radiomics or combined model could be more beneficial compared to the clinical model for the prediction of PCa. The nomogram showed good agreement for detecting PCa with gray-zone PSA levels between prediction and histopathologic confirmation. Conclusion: The nomogram, which combined the radiomics score and PI-RADS V2.1 category and age, is an effective and non-invasive method for predicting PCa. Furthermore, as well as good calibration and is clinically useful, which could reduce unnecessary prostate biopsies in patients having PCa with gray-zone PSA levels.