Comparative Study of C-TIRADS, ACR-TIRADS, and EU-TIRADS for Diagnosis and Management of Thyroid Nodules.

RATIONALE AND OBJECTIVES: Chinese Thyroid Imaging Reporting and Data Systems (C-TIRADS) was developed to provide a more simplified tool for stratifying thyroid nodules. Here we aimed to validate the efficacy of C-TIRADS in distinguishing benign from malignant and in guiding fine-needle aspiration biopsies in comparison with the American College of Radiology TIRADS (ACR-TIRADS) and European TIRADS (EU-TIRADS). MATERIALS AND METHODS: This study retrospectively included 3438 thyroid nodules (≥10 mm) in 3013 patients (mean age, 47.1 years ± 12.9) diagnosed between January 2013 and November 2019. Ultrasound features of the nodules were evaluated and categorized according to the lexicons of the three TIRADS. We compared these TIRADS by using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), sensitivity, specificity, net reclassification improvement (NRI), and unnecessary fine-needle aspiration biopsy (FNAB) rate. RESULTS: Of the 3438 thyroid nodules, 707 (20.6%) were malignant. C-TIRADS showed higher discrimination performance (AUROC, 0.857; AUPRC, 0.605) than ACR-TIRADS (AUROC, 0.844; AUPRC, 0.567) and EU-TIRADS (AUROC, 0.802; AUPRC, 0.455). The sensitivity of C-TIRADS (85.3%) was lower than that of ACR-TIRADS (89.1%) but higher than that of EU-TIRADS (78.4%). The specificity of C-TIRADS (76.9%) was similar to that of EU-TIRADS (78.9%) and higher than that of ACR-TIRADS (69.5%). The unnecessary FNAB rate was lowest with C-TIRADS (21.2%), followed by ACR-TIRADS (41.7%) and EU-TIRADS (58.3%). C-TIRADS obtained significant NRI for recommending FNAB over ACR-TIRADS (19.0%, P < 0.001) and EU-TIRADS (25.5%, P < 0.001). CONCLUSION: C-TIRADS may be a clinically applicable tool to manage thyroid nodules, which warrants thorough tests in other geographic settings.

Machine learning-based multimodal MRI texture analysis for assessing renal function and fibrosis in diabetic nephropathy: a retrospective study.

Introduction: Diabetic nephropathy (DN) has become a major public health burden in China. A more stable method is needed to reflect the different stages of renal function impairment. We aimed to determine the possible practicability of machine learning (ML)-based multimodal MRI texture analysis (mMRI-TA) for assessing renal function in DN. Methods: For this retrospective study, 70 patients (between 1 January 2013 and 1 January 2020) were included and randomly assigned to the training cohort (n1 = 49) and the testing cohort (n2 = 21). According to the estimated glomerular filtration rate (eGFR), patients were assigned into the normal renal function (normal-RF) group, the non-severe renal function impairment (non-sRI) group, and the severe renal function impairment (sRI) group. Based on the largest coronal image of T2WI, the speeded up robust features (SURF) algorithm was used for texture feature extraction. Analysis of variance (ANOVA) and relief and recursive feature elimination (RFE) were applied to select the important features and then support vector machine (SVM), logistic regression (LR), and random forest (RF) algorithms were used for the model construction. The values of area under the curve (AUC) on receiver operating characteristic (ROC) curve analysis were used to assess their performance. The robust T2WI model was selected to construct a multimodal MRI model by combining the measured BOLD (blood oxygenation level-dependent) and diffusion-weighted imaging (DWI) values. Results: The mMRI-TA model achieved robust and excellent performance in classifying the sRI group, non-sRI group, and normal-RF group, with an AUC of 0.978 (95% confidence interval [CI]: 0.963, 0.993), 0.852 (95% CI: 0.798, 0.902), and 0.972 (95% CI: 0.995, 1.000), respectively, in the training cohort and 0.961 (95% CI: 0.853, 1.000), 0.809 (95% CI: 0.600, 0.980), and 0.850 (95% CI: 0.638, 0.988), respectively, in the testing cohort. Discussion: The model built from multimodal MRI on DN outperformed other models in assessing renal function and fibrosis. Compared to the single T2WI sequence, mMRI-TA can improve the performance in assessing renal function.

MRI texture-based machine learning models for the evaluation of renal function on different segmentations: a proof-of-concept study.

BACKGROUND: To develop and validate an MRI texture-based machine learning model for the noninvasive assessment of renal function. METHODS: A retrospective study of 174 diabetic patients (training cohort, n = 123; validation cohort, n = 51) who underwent renal MRI scans was included. They were assigned to normal function (n = 71), mild or moderate impairment (n = 69), and severe impairment groups (n = 34) according to renal function. Four methods of kidney segmentation on T2-weighted images (T2WI) were compared, including regions of interest covering all coronal slices (All-K), the largest coronal slices (LC-K), and subregions of the largest coronal slices (TLCO-K and PIZZA-K). The speeded-up robust features (SURF) and support vector machine (SVM) algorithms were used for texture feature extraction and model construction, respectively. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of models. RESULTS: The models based on LC-K and All-K achieved the nonsignificantly highest accuracy in the classification of renal function (all p values > 0.05). The optimal model yielded high performance in classifying the normal function, mild or moderate impairment, and severe impairment, with an area under the curve of 0.938 (95% confidence interval [CI] 0.935-0.940), 0.919 (95%CI 0.916-0.922), and 0.959 (95%CI 0.956-0.962) in the training cohorts, respectively, as well as 0.802 (95%CI 0.800-0.807), 0.852 (95%CI 0.846-0.857), and 0.863 (95%CI 0.857-0.887) in the validation cohorts, respectively. CONCLUSION: We developed and internally validated an MRI-based machine-learning model that can accurately evaluate renal function. Once externally validated, this model has the potential to facilitate the monitoring of patients with impaired renal function.

Thy-Wise: An interpretable machine learning model for the evaluation of thyroid nodules.

Current risk stratification systems for thyroid nodules suffer from low specificity and high biopsy rates. Recently, machine learning (ML) is introduced to assist thyroid nodule diagnosis but lacks interpretability. Here, we developed and validated ML models on 3965 thyroid nodules, as compared to the American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS). Subsequently, a SHapley Additive exPlanation (SHAP) algorithm was leveraged to interpret the results of the best-performing ML model. Clinical characteristics including thyroid-function tests were collected from medical records. Five ACR TI-RADS ultrasonography (US) categories plus nodule size were assessed by experienced radiologists. Random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGBoost) were used to build US-only and US-clinical ML models. The ML models and ACR TI-RADS were compared in terms of diagnostic performance and unnecessary biopsy rate. Among the ML models, the US-only RF model (hereafter, Thy-Wise) achieved the optimal performance. Compared to ACR TI-RADS, Thy-Wise showed higher accuracy (82.4% vs 74.8% for the internal validation; 82.1% vs 73.4% for external validation) and specificity (78.7% vs 68.3% for internal validation; 78.5% vs 66.9% for external validation) while maintaining sensitivity (91.7% vs 91.2% for internal validation; 91.9% vs 91.1% for external validation), as well as reduced unnecessary biopsies (15.3% vs 32.3% for internal validation; 15.7% vs 47.3% for external validation). The SHAP-based interpretation of Thy-Wise enables clinicians to better understand the reasoning behind the diagnosis, which may facilitate the clinical translation of this model.

Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos.

BACKGROUND: Transcatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with the same tumor stage. Accurate prediction of TACE response remains a major concern to avoid overtreatment. Thus, we aimed to develop and validate an artificial intelligence system for real-time automatic prediction of TACE response in HCC patients based on digital subtraction angiography (DSA) videos via a deep learning approach. METHODS: This retrospective cohort study included a total of 605 patients with intermediate-stage HCC who received TACE as their initial therapy. A fully automated framework (i.e., DSA-Net) contained a U-net model for automatic tumor segmentation (Model 1) and a ResNet model for the prediction of treatment response to the first TACE (Model 2). The two models were trained in 360 patients, internally validated in 124 patients, and externally validated in 121 patients. Dice coefficient and receiver operating characteristic curves were used to evaluate the performance of Models 1 and 2, respectively. RESULTS: Model 1 yielded a Dice coefficient of 0.75 (95% confidence interval [CI]: 0.73-0.78) and 0.73 (95% CI: 0.71-0.75) for the internal validation and external validation cohorts, respectively. Integrating the DSA videos, segmentation results, and clinical variables (mainly demographics and liver function parameters), Model 2 predicted treatment response to first TACE with an accuracy of 78.2% (95%CI: 74.2-82.3), sensitivity of 77.6% (95%CI: 70.7-84.0), and specificity of 78.7% (95%CI: 72.9-84.1) for the internal validation cohort, and accuracy of 75.1% (95% CI: 73.1-81.7), sensitivity of 50.5% (95%CI: 40.0-61.5), and specificity of 83.5% (95%CI: 79.2-87.7) for the external validation cohort. Kaplan-Meier curves showed a significant difference in progression-free survival between the responders and non-responders divided by Model 2 (p = 0.002). CONCLUSIONS: Our multi-task deep learning framework provided a real-time effective approach for decoding DSA videos and can offer clinical-decision support for TACE treatment in intermediate-stage HCC patients in real-world settings.

Radiogenomic association between the T2-FLAIR mismatch sign and IDH mutation status in adult patients with lower-grade gliomas: an updated systematic review and meta-analysis.

OBJECTIVES: To reveal a radiogenomic correlation between the presence of the T2-fluid-attenuated inversion recovery resection (T2-FLAIR) mismatch sign on MR images and isocitrate dehydrogenase (IDH) mutation status in adult patients with lower-grade gliomas (LGGs). METHODS: A web-based systemic search for eligible literature up to April 13, 2021, was conducted on PubMed, Embase, and the Cochrane Library databases by two independent reviewers. This study was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. We included studies evaluating the accuracy of the T2-FLAIR mismatch sign in diagnosing the IDH mutation in adult patients with LGGs. The T2-FLAIR mismatch sign was defined as a T2-hyperintense lesion that is hypointense on FLAIR except for a hyperintense rim. RESULTS: Fourteen studies (n = 1986) were finally identified. The mean age of patients in the included studies ranged from 38.5 to 56 years. The pooled area under the curve (AUC), sensitivity, and specificity were obtained for each molecular profile: IDHmut-Codel: 0.46 (95% confidence interval [CI]: 0.42-0.50), 1% (95%CI: 0-7%), and 69% (95%CI: 62-75%), respectively; IDHmut-Noncodel: 0.75 (95%CI: 0.71-0.79), 42% (95%CI: 34-50%), and 99% (95%CI: 96-100%), respectively; IDH-Mutation regardless of 1p/19q codeletion status: 0.77 (95%CI: 0.73-0.80), 29% (95%CI: 21-40%), and 99% (95%CI: 92-100%), respectively. CONCLUSIONS: The T2-FLAIR mismatch sign was an insensitive but highly specific marker for IDHmut-Noncodel and IDH-Mutation LGGs, whereas it was not a useful marker for IDHmut-Codel LGGs. The findings might identify the T2-FLAIR mismatch sign as a non-invasive imaging biomarker for the selection of patients with IDH-mutant LGGs. KEY POINTS: • The T2-FLAIR mismatch sign was not a sensitive sign for IDH mutation in LGGs. • The T2-FLAIR mismatch sign was related to IDHmut-Noncodel with a specificity of 99%. • The pooled specificity (69%) of the T2-FLAIR mismatch sign for IDHmut-Codel was low.

Current status and quality of radiomic studies for predicting immunotherapy response and outcome in patients with non-small cell lung cancer: a systematic review and meta-analysis.

PURPOSE: Prediction of immunotherapy response and outcome in patients with non-small cell lung cancer (NSCLC) is challenging due to intratumoral heterogeneity and lack of robust biomarkers. The aim of this study was to systematically evaluate the methodological quality of radiomic studies for predicting immunotherapy response or outcome in patients with NSCLC. METHODS: We systematically searched for eligible studies in the PubMed and Web of Science datasets up to April 1, 2021. The methodological quality of included studies was evaluated using the phase classification criteria for image mining studies and the radiomics quality scoring (RQS) tool. A meta-analysis of studies regarding the prediction of immunotherapy response and outcome in patients with NSCLC was performed. RESULTS: Fifteen studies were identified with sample sizes ranging from 30 to 228. Seven studies were classified as phase II, and the remaining as discovery science (n = 2), phase 0 (n = 4), phase I (n = 1), and phase III (n = 1). The mean RQS score of all studies was 29.6%, varying from 0 to 68.1%. The pooled diagnostic odds ratio for predicting immunotherapy response in NSCLC using radiomics was 14.99 (95% confidence interval [CI] 8.66-25.95). In addition, radiomics could divide patients into high- and low-risk group with significantly different overall survival (pooled hazard ratio [HR]: 1.96, 95%CI 1.61-2.40, p < 0.001) and progression-free survival (pooled HR: 2.39, 95%CI 1.69-3.38, p < 0.001). CONCLUSIONS: Radiomics has potential to noninvasively predict immunotherapy response and outcome in patients with NSCLC. However, it has not yet been implemented as a clinical decision-making tool. Further external validation and evaluation within clinical pathway can facilitate personalized treatment for patients with NSCLC.

Predicting Intensive Care Unit Length of Stay After Acute Type A Aortic Dissection Surgery Using Machine Learning.

Background: Patients with acute type A aortic dissection are usually transferred to the intensive care unit (ICU) after surgery. Prolonged ICU length of stay (ICU-LOS) is associated with higher level of care and higher mortality. We aimed to develop and validate machine learning models for predicting ICU-LOS after acute type A aortic dissection surgery. Methods: A total of 353 patients with acute type A aortic dissection transferred to ICU after surgery from September 2016 to August 2019 were included. The patients were randomly divided into the training dataset (70%) and the validation dataset (30%). Eighty-four preoperative and intraoperative factors were collected for each patient. ICU-LOS was divided into four intervals (<4, 4-7, 7-10, and >10 days) according to interquartile range. Kendall correlation coefficient was used to identify factors associated with ICU-LOS. Five classic classifiers, Naive Bayes, Linear Regression, Decision Tree, Random Forest, and Gradient Boosting Decision Tree, were developed to predict ICU-LOS. Area under the curve (AUC) was used to evaluate the models' performance. Results: The mean age of patients was 51.0 ± 10.9 years and 307 (87.0%) were males. Twelve predictors were identified for ICU-LOS, namely, D-dimer, serum creatinine, lactate dehydrogenase, cardiopulmonary bypass time, fasting blood glucose, white blood cell count, surgical time, aortic cross-clamping time, with Marfan's syndrome, without Marfan's syndrome, without aortic aneurysm, and platelet count. Random Forest yielded the highest performance, with an AUC of 0.991 (95% confidence interval [CI]: 0.978-1.000) and 0.837 (95% CI: 0.766-0.908) in the training and validation datasets, respectively. Conclusions: Machine learning has the potential to predict ICU-LOS for acute type A aortic dissection. This tool could improve the management of ICU resources and patient-throughput planning, and allow better communication with patients and their families.

Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients.

Gliomas can be classified into five molecular groups based on the status of IDH mutation, 1p/19q codeletion, and TERT promoter mutation, whereas they need to be obtained by biopsy or surgery. Thus, we aimed to use MRI-based radiomics to noninvasively predict the molecular groups and assess their prognostic value. We retrospectively identified 357 patients with gliomas and extracted radiomic features from their preoperative MRI images. Single-layered radiomic signatures were generated using a single MR sequence using Bayesian-regularization neural networks. Image fusion models were built by combing the significant radiomic signatures. By separately predicting the molecular markers, the predictive molecular groups were obtained. Prognostic nomograms were developed based on the predictive molecular groups and clinicopathologic data to predict progression-free survival (PFS) and overall survival (OS). The results showed that the image fusion model incorporating radiomic signatures from contrast-enhanced T1-weighted imaging (cT1WI) and apparent diffusion coefficient (ADC) achieved an AUC of 0.884 and 0.669 for predicting IDH and TERT status, respectively. cT1WI-based radiomic signature alone yielded favorable performance in predicting 1p/19q status (AUC = 0.815). The predictive molecular groups were comparable to actual ones in predicting PFS (C-index: 0.709 vs. 0.722, P = 0.241) and OS (C-index: 0.703 vs. 0.751, P = 0.359). Subgroup analyses by grades showed similar findings. The prognostic nomograms based on grades and the predictive molecular groups yielded a C-index of 0.736 and 0.735 in predicting PFS and OS, respectively. Accordingly, MRI-based radiomics may be useful for noninvasively detecting molecular groups and predicting survival in gliomas regardless of grades.

Concurrent chemoradiotherapy with additional chemotherapy for nasopharyngeal carcinoma: A pooled analysis of propensity score-matching studies.

OBJECTIVE: To determine the benefits of adding induction chemotherapy (IC) and adjuvant chemotherapy (AC) to concurrent chemoradiotherapy (CCRT) for nasopharyngeal carcinoma (NPC) based on propensity score-matching (PSM) studies. METHODS: Eligible PSM studies were searched in the PubMed, Web of Science, and Embase databases from inception to September 1, 2020. The primary endpoints included overall survival (OS), distant metastasis-free survival (DMFS), and locoregional recurrence-free survival (LRFS). RESULTS: A total of 14 trials consisting of 4086 participants were included. Significant benefits were observed between IC + CCRT and CCRT for OS (hazard ratio [HR], 0.76; 95% confidence interval [CI]: 0.64-0.91) and DMFS (HR, 0.77; 95% CI: 0.64-0.94) with the exception of LRFS (HR, 1.14; 95% CI: 0.90-1.43). However, CCRT + AC did not achieve significant improvements. CONCLUSIONS: IC with CCRT yields significant survival benefits in terms of OS and DMFS, whereas CCRT with AC fails to achieve any additional benefit in all endpoints.

Predicting hyperprogressive disease in patients with advanced hepatocellular carcinoma treated with anti-programmed cell death 1 therapy.

BACKGROUND: Hyperprogressive disease (HPD) is a new progressive pattern in patients with advanced hepatocellular carcinoma (HCC) treated with programmed cell death 1 (PD-1) inhibitors. We aimed to investigate risk factors associated with HPD in advanced HCC patients undergoing anti-PD-1 therapy. METHODS: A total of 69 patients treated with anti-PD-1 therapy between March 2017 and January 2020 were included. HPD was determined according to the time to treatment failure, tumour growth rate, and tumour growth rate ratio. Univariate and multivariate analyses were performed to identify clinical variables significantly associated with HPD. A risk model was constructed based on clinical variables with prognostic significance for HPD. FINDINGS: Overall, 10 (14·49%) had HPD. Haemoglobin level, portal vein tumour thrombus, and Child-Pugh score were significantly associated with HPD. The risk model had an area under the curve of 0·931 (95% confidence interval, 0·844-1·000). Patients with HPD had a significantly shorter overall survival (OS) than that of the patients with non-HPD (p < 0·001). However, there was no significant difference in OS between PD (progressive disease) patients with and without HPD (p = 0·05). INTERPRETATION: We identified three clinical variables as risk factors for HPD, providing an opportunity to aid the pre-treatment evaluation of the risk of HPD in patients treated with immunotherapy. FUNDING: This study was funded by the National Natural Science Foundation of China (81571664, 81871323, and 81801665); National Natural Science Foundation of Guangdong Province (2018B030311024); Scientific Research General Project of Guangzhou Science Technology and Innovation Commission (201707010,328); and China Postdoctoral Science Foundation (2016M600145).

Machine learning classifiers for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery.

Background: To develop machine-learning based models to predict the progression-free survival (PFS) and overall survival (OS) in patients with gliomas and explore the effect of different feature selection methods on the prediction. Methods: We included 505 patients (training cohort, n = 354; validation cohort, n = 151) with gliomas between January 1, 2011 and December 31, 2016. The clinical, neuroimaging, and molecular genetic data of patients were retrospectively collected. The multi-causes discovering with structure learning (McDSL) algorithm, least absolute shrinkage and selection operator regression (LASSO), and Cox proportional hazards regression model were employed to discover the predictors for 3-year PFS and OS, respectively. Eight machine learning classifiers with 5-fold cross-validation were developed to predict 3-year PFS and OS. The area under the curve (AUC) was used to evaluate the prognostic performance of classifiers. Results: McDSL identified four causal factors (tumor location, WHO grade, histologic type, and molecular genetic group) for 3-year PFS and OS, whereas LASSO and Cox identified wide-range number of factors associated with 3-year PFS and OS. The performance of each machine learning classifier based on McDSL, LASSO, and Cox was not significantly different. Logistic regression yielded the optimal performance in predicting 3-year PFS based on the McDSL (AUC, 0.872, 95% confidence interval [CI]: 0.828-0.916) and 3-year OS based on the LASSO (AUC, 0.901, 95% CI: 0.861-0.940). Conclusions: McDSL is more reproducible than LASSO and Cox model in the feature selection process. Logistic regression model may have the highest performance in predicting 3-year PFS and OS of gliomas.

MRI-Based Deep-Learning Model for Distant Metastasis-Free Survival in Locoregionally Advanced Nasopharyngeal Carcinoma.

BACKGROUND: Distant metastasis is the primary cause of treatment failure in locoregionally advanced nasopharyngeal carcinoma (LANPC). PURPOSE: To develop a model to evaluate distant metastasis-free survival (DMFS) in LANPC and to explore the value of additional chemotherapy to concurrent chemoradiotherapy (CCRT) for different risk groups. STUDY TYPE: Retrospective. POPULATION: In all, 233 patients with biopsy-confirmed nasopharyngeal carcinoma (NPC) from two hospitals. FIELD STRENGTH: 1.5T and 3T. SEQUENCE: Axial T2 -weighted (T2 -w) and contrast-enhanced T1 -weighted (CET1 -w) images. ASSESSMENT: Deep learning was used to build a model based on MRI images (including axial T2 -w and CET1 -w images) and clinical variables. Hospital 1 patients were randomly divided into training (n = 169) and validation (n = 19) cohorts; Hospital 2 patients were assigned to a testing cohort (n = 45). LANPC patients were divided into low- and high-risk groups according to their DMFS (P < 0.05). Kaplan-Meier survival analysis was performed to compare the DMFS of different risk groups and subgroup analysis was performed to compare patients treated with CCRT alone and treated with additional chemotherapy to CCRT in different risk groups, respectively. STATISTICAL TESTS: Univariate analysis was performed to identify significant clinical variables. The area under the receiver operating characteristic (ROC) curve (AUC) was used to assess the model performance. RESULTS: Our deep-learning model integrating the deep-learning signature, node (N) stage (from TNM staging), plasma Epstein-Barr virus (EBV)-DNA, and treatment regimens yielded an AUC of 0.796 (95% confidence interval [CI]: 0.729-0.863), 0.795 (95% CI: 0.540-1.000), and 0.808 (95% CI: 0.654-0.962) in the training, internal validation, and external testing cohorts, respectively. Low-risk patients treated with CCRT alone had longer DMFS than patients treated with additional chemotherapy to CCRT (P < 0.05). DATA CONCLUSION: The proposed deep-learning model, based on MRI features and clinical variates, facilitated the prediction of DMFS in LANPC patients. LEVEL OF EVIDENCE: 3. TECHNICAL EFFICACY STAGE: 4.

Machine-learning based MRI radiomics models for early detection of radiation-induced brain injury in nasopharyngeal carcinoma.

BACKGROUND: Early radiation-induced temporal lobe injury (RTLI) diagnosis in nasopharyngeal carcinoma (NPC) is clinically challenging, and prediction models of RTLI are lacking. Hence, we aimed to develop radiomic models for early detection of RTLI. METHODS: We retrospectively included a total of 242 NPC patients who underwent regular follow-up magnetic resonance imaging (MRI) examinations, including contrast-enhanced T1-weighted and T2-weighted imaging. For each MRI sequence, four non-texture and 10,320 texture features were extracted from medial temporal lobe, gray matter, and white matter, respectively. The relief and 0.632 + bootstrap algorithms were applied for initial and subsequent feature selection, respectively. Random forest method was used to construct the prediction model. Three models, 1, 2 and 3, were developed for predicting the results of the last three follow-up MRI scans at different times before RTLI onset, respectively. The area under the curve (AUC) was used to evaluate the performance of models. RESULTS: Of the 242 patients, 171 (70.7%) were men, and the mean age of all the patients was 48.5 ± 10.4 years. The median follow-up and latency from radiotherapy until RTLI were 46 and 41 months, respectively. In the testing cohort, models 1, 2, and 3, with 20 texture features derived from the medial temporal lobe, yielded mean AUCs of 0.830 (95% CI: 0.823-0.837), 0.773 (95% CI: 0.763-0.782), and 0.716 (95% CI: 0.699-0.733), respectively. CONCLUSION: The three developed radiomic models can dynamically predict RTLI in advance, enabling early detection and allowing clinicians to take preventive measures to stop or slow down the deterioration of RTLI.

Development and validation of a Web-based malignancy risk-stratification system of thyroid nodules.

OBJECTIVES: Previous publications on risk-stratification systems for malignant thyroid nodules were based on conventional ultrasound only. We aimed to develop a practical and simplified prediction model for categorizing the malignancy risk of thyroid nodules based on clinical data, biochemical data, conventional ultrasound and real-time elastography. DESIGN: Retrospective cohort study. PATIENTS: A total of 2818 patients (1890 female, mean age, 45.5 ± 13.2 years) with 2850 thyroid nodules were retrospectively evaluated between April 2011 and October 2016. 26.8% nodules were malignant. MEASUREMENTS: We used a randomly divided sample of 80% of the nodules to perform a multivariate logistic regression analysis. Cut-points were determined to create a risk-stratification scoring system. Patients were classified as having low, moderate and high probability of malignancy according to their scores. We validated the models to the remaining 20% of the nodules. The area under the curve (AUC) was used to evaluate the discrimination ability of the systems. RESULTS: Ten variables were selected as predictors of malignancy. The point-based scoring systems with and without elasticity score achieved similar AUCs of 0.916 (95% confidence interval [CI]: 0.885-0.948) and 0.906 (95% CI: 0.872-0.941) when validated. Malignancy risk was segmented from 0% to 100.0% and was positively associated with an increase in risk scores. We then developed a Web-based risk-stratification system of thyroid nodules (http: thynodscore.com). CONCLUSION: A simple and reliable Web-based risk-stratification system could be practically used in stratifying the risk of malignancy in thyroid nodules.

Evaluating primary intra-arterial chemotherapy versus intravenous plus intra-arterial chemotherapy for advanced intraocular retinoblastoma.

PURPOSE: Although intra-arterial chemotherapy (IAC) is commonly used for treating intraocular retinoblastoma, it is not a systemic therapy. We aimed to investigate whether the addition of intravenous chemotherapy (IVC) before IAC administration had any effects (whether beneficial or adverse) on patient outcomes. METHODS: This multicenter retrospective cohort study included 213 patients with advanced intraocular retinoblastoma who received IVC plus IAC (n = 103) or IAC alone (n = 110) between April 2009 and January 2017. Eyes were grouped according to the International Intraocular Retinoblastoma Classification. Kaplan-Meier and Cox regression analyses were performed to compare survival outcomes between the two groups. Moreover, details regarding enucleation were recorded. RESULTS: The 3-year ocular survival rates were 62% in the IVC plus IAC group and 68% in the IAC group (hazard ratio (HR) 0.88, 95% confidence interval (CI) 0.55-1.43, P = 0.61). Moreover, the corresponding 3-year overall survival rates were 97% and 93%, respectively (HR 1.56, 95% CI 0.41-5.90, P = 0.51), while the 3-year event-free survival rates were 76% and 72%, respectively (HR 0.96, 95% CI 0.56-1.65, P = 0.89). CONCLUSIONS: Within a 3-year follow-up period, IVC plus IAC produced no additional benefit over primary IAC for treating advanced intraocular retinoblastoma in terms of local tumor control and extending survival. Longer follow-up periods are required to assess long-term efficacy.

Immune-checkpoint inhibitor plus chemotherapy versus conventional chemotherapy for treatment of recurrent or metastatic head and neck squamous cell carcinoma: a systematic review and network meta-analysis.

BACKGROUND: Multiple therapies including immune-checkpoint inhibitors are emerging as effective treatment for patients with recurrent or metastatic head and neck squamous cell carcinoma (R/M HNSSC). However, the optimal first-line and second-line treatments remains controversial. METHODS: We systematically searched databases and conducted a systematic review of phase II/III randomized controlled trials (RCTs) that compared two or more treatments for R/M HNSSC. Progression-free survival (PFS), overall survival (OS) and adverse events (AEs) ⩾3 with hazard ratios (HRs) were extracted and synthesized based on a frequentist network meta-analysis. RESULTS: Twenty-six trials involving 8908 patients were included. Of first-line treatments, pembrolizumab plus cisplatin plus 5-fluorouracil is associated with significantly improved OS (P-score = 0.91) and TPEx ranked first for prolonging PFS (0.91). EXTREME plus docetaxel (0.18) ranked lowest for AEs ⩾3. Of second-line treatments, nivolumab was the highest-ranked treatment for prolonging OS (0.95), while buparlisib plus paclitaxel was the highest-ranked treatment for PFS (0.94). Subgroup analyses suggested that nivolumab was significantly associated with improvement of OS in patients with high PD-L1 expression (HR 0.55, 0.43-0.70), whereas its OS benefit is similar with conventional chemotherapy for those with low PD-L1 expression. Buparlisib plus paclitaxel showed the best OS benefit in subgroups of patients with HPV-negative status, and with oral cavity or larynx as primary tumor sites. CONCLUSIONS: Pembrolizumab plus cisplatin plus 5-fluorouracil is likely to be the best first-line treatment when OS is a priority. Otherwise, TPEx should be the optimal first-line option due to its superior PFS prolongation efficacy, best safety profile, and similar OS benefit with pembrolizumab plus cisplatin plus 5-fluorouracil. Nivolumab appears to be the best second-line option with best OS prolongation efficacy and outstanding safety profile in the overall population. Future RCTs with meticulous grouping of patients and detailed reporting are urgently needed for individualized treatment.

Prognostic value of the radiomics-based model in progression-free survival of hypopharyngeal cancer treated with chemoradiation.

PURPOSE: To develop a radiomics-based model to stratify the risk of early progression (local/regional recurrence or metastasis) among patients with hypopharyngeal cancer undergoing chemoradiotherapy and modify their pretreatment plans. MATERIALS AND METHODS: We randomly assigned 113 patients into two cohorts: training (n = 80) and validation (n = 33). The radiomic significant features were selected in the training cohort using least absolute shrinkage and selection operator and Akaike information criterion methods, and they were used to build the radiomic model. The concordance index (C-index) was applied to evaluate the model's prognostic performance. A Kaplan-Meier analysis and the log-rank test were used to assess risk stratification ability of models in predicting progression. A nomogram was plotted to predict individual risk of progression. RESULTS: Composed of four significant features, the radiomic model showed good performance in stratifying patients into high- and low-risk groups of progression in both the training and validation cohorts (log-rank test, p = 0.00016, p = 0.0063, respectively). Peripheral invasion and metastasis were selected as significant clinical variables. The combined radiomic-clinical model showed good discriminative performance, with C-indices 0.804 (95% confidence interval (CI), 0.688-0.920) and 0.756 (95% CI, 0.605-0.907) in the training and validation cohorts, respectively. The median progression-free survival (PFS) in the high-risk group was significantly shorter than that in the low-risk group in the training (median PFS, 9.5 m and 19.0 m, respectively; p [log-rank] < 0.0001) and validation (median PFS, 11.3 m and 22.5 m, respectively; p [log-rank] = 0.0063) cohorts. CONCLUSIONS: A radiomics-based model was established to predict the risk of progression in hypopharyngeal cancer with chemoradiotherapy. KEY POINTS: • Clinical information showed limited performance in stratifying the risk of progression among patients with hypopharyngeal cancer. • Imaging features extracted from CECT and NCCT images were independent predictors of PFS. • We combined significant features and valuable clinical variables to establish a nomogram to predict individual risk of progression.

Radiomic Nomogram: Pretreatment Evaluation of Local Recurrence in Nasopharyngeal Carcinoma based on MR Imaging.

Background: To develop and validate a radiomic nomogram incorporating radiomic features with clinical variables for individual local recurrence risk assessment in nasopharyngeal carcinoma (NPC) patients before initial treatment. Methods: One hundred and forty patients were randomly divided into a training cohort (n = 80) and a validation cohort (n = 60). A total of 970 radiomic features were extracted from pretreatment magnetic resonance (MR) images of NPC patients from May 2007 to December 2013. Univariate and multivariate analyses were used for selecting radiomic features associated with local recurrence, and multivariate analyses was used for building radiomic nomogram. Results: Eight contrast-enhanced T1-weighted (CET1-w) image features and seven T2-weighted (T2-w) image features were selected to build a Cox proportional hazard model in the training cohort, respectively. The radiomic nomogram, which combined radiomic features and multiple clinical variables, had a good evaluation ability (C-index: 0.74 [95% CI: 0.58, 0.85]) in the validation cohort. The radiomic nomogram successfully categorized those patients into low- and high-risk groups with significant differences in the rate of local recurrence-free survival (P <0.05). Conclusions: This study demonstrates that MR imaging-based radiomics can be used as an aid tool for the evaluation of local recurrence, in order to develop tailored treatment targeting specific characteristics of individual patients.

Intra-arterial chemotherapy as primary or secondary treatment for infants diagnosed with advanced retinoblastoma before 3 months of age.

BACKGROUND: To evaluate the safety and efficacy of intra-arterial chemotherapy (IAC) for the primary or secondary treatment of infants diagnosed with advanced retinoblastoma before 3 months of age. METHODS: This single-center retrospective study included 39 infants (42 eyes) aged ≤3 months who were diagnosed with unilateral or bilateral advanced intraocular retinoblastoma (group D and E eyes) and received IAC as primary or secondary treatment between June 2012 and February 2017. Based on each patient's therapeutic history and response to chemotherapeutic drugs, melphalan, topotecan, and/or carboplatin were used for IAC. The main outcomes included the technical success rate for IAC, survival rates, and adverse events. RESULTS: In total, 29 and 13 eyes received IAC as primary and secondary treatments, respectively. Catheterization was successful in 136 of 137 procedures. All eyes in the secondary IAC group had previously received intravenous chemotherapy. The mean number of IAC sessions for each eye was 3 (range, 2-6). The 2-year ocular survival rates were 80.7% (95% confidence interval [CI], 58.9-91.7) in the primary IAC group and 91.7% (95% CI, 53.9-98.8) in the secondary IAC group. During the follow-up period, 1 patient with unilateral disease (group E) developed extraocular disease and died. The 2-year recurrence-free survival rates in the primary and secondary IAC groups were 71.9% (95% CI, 49.4-85.7) and 75.0% (95% CI, 40.8-91.2), respectively. During each catheterization procedure, the main complications included eyelid erythema (2.4%), fundus hemorrhage (11.9%), myelosuppression (7.7%), transient vomiting and hair loss (2.6%), and transient pancytopenia (2.6%). Prolonged complications included phthisis bulbi (19.0%), vision loss (19.0%), poor vision (9.5%), and cataract (2.4%). There was no case of stroke, neurological impairment, secondary malignant tumor, or metastasis. CONCLUSIONS: Our findings suggest that IAC, whether primary or secondary, is effective and fairly safe for the management of advanced retinoblastoma in infants aged < 3 months. However, adverse events related to intra-arterial injection and the visual outcomes cannot be neglected and require further investigation.