A PD-L1-targeting chimeric switch receptor enhances efficacy of CAR-T cell for pleural and peritoneal metastasis.

Pleural and peritoneal metastasis accompanied by malignant pleural effusion (MPE) or malignant ascites (MA) is frequent in patients with advanced solid tumors that originate from the lung, breast, gastrointestinal tract and ovary. Regional delivery of CAR-T cells represents a new strategy to control tumor dissemination in serous cavities. However, malignant effusions constitute an immune-suppressive environment that potentially induces CAR-T cell dysfunction. Here, we demonstrated that the anti-tumor cytotoxicity of conventional 2nd-generation CAR-T cells was significantly inhibited by both the cellular and non-cellular components of MPE/MA, which was primarily attributed to impaired CAR-T cell proliferation and cytokine production in MPE/MA environment. Interestingly, we found that PD-L1 was widely expressed on freshly-isolated MPE/MA cells. Based on this feature, a novel PD-L1-targeting chimeric switch receptor (PD-L1.BB CSR) was designed, which can bind to PD-L1, switching the inhibitory signal into an additional 4-1BB signal. When co-expressed with a 2nd-generation CAR, PD-L1.BB CSR-modified CAR-T cells displayed superior fitness and enhanced functions in both culture medium and MPE/MA environment, causing rapid and durable eradication of pleural and peritoneal metastatic tumors in xenograft models. Further investigations revealed elevated expressions of T-cell activation, proliferation, and cytotoxicity-related genes, and we confirmed that PD-L1 scFv and 4-1BB intracellular domain, the two important components of PD-L1.BB CSR, were both necessary for the functional improvements of CAR-T cells. Overall, our study shed light on the clinical application of PD-L1.BB CSR-modified dual-targeting CAR-T cells. Based on this study, a phase I clinical trial was initiated in patients with pleural or peritoneal metastasis (NCT04684459).

Myeloid-derived suppressor cells as immunosuppressive regulators and therapeutic targets in cancer.

Myeloid-derived suppressor cells (MDSCs) are a heterogenic population of immature myeloid cells with immunosuppressive effects, which undergo massive expansion during tumor progression. These cells not only support immune escape directly but also promote tumor invasion via various non-immunological activities. Besides, this group of cells are proved to impair the efficiency of current antitumor strategies such as chemotherapy, radiotherapy, and immunotherapy. Therefore, MDSCs are considered as potential therapeutic targets for cancer therapy. Treatment strategies targeting MDSCs have shown promising outcomes in both preclinical studies and clinical trials when administrated alone, or in combination with other anticancer therapies. In this review, we shed new light on recent advances in the biological characteristics and immunosuppressive functions of MDSCs. We also hope to propose an overview of current MDSCs-targeting therapies so as to provide new ideas for cancer treatment.

CRISPR/Cas9 Gene-Editing in Cancer Immunotherapy: Promoting the Present Revolution in Cancer Therapy and Exploring More.

In recent years, immunotherapy has showed fantastic promise in pioneering and accelerating the field of cancer therapy and embraces unprecedented breakthroughs in clinical practice. The clustered regularly interspaced short palindromic repeat (CRISPR)-associated protein 9 (CRISPR-Cas9) system, as a versatile gene-editing technology, lays a robust foundation to efficiently innovate cancer research and cancer therapy. Here, we summarize recent approaches based on CRISPR/Cas9 system for construction of chimeric antigen receptor T (CAR-T) cells and T cell receptor T (TCR-T) cells. Besides, we review the applications of CRISPR/Cas9 in inhibiting immune checkpoint signaling pathways and highlight the feasibility of CRISPR/Cas9 based engineering strategies to screen novel cancer immunotherapy targets. Conclusively, we discuss the perspectives, potential challenges and possible solutions in this vivid growing field.

Differential diagnostic ability of 18F-FDG PET/CT radiomics features between renal cell carcinoma and renal lymphoma.

BACKGROUND: The aim of this study is to determine the differential diagnostic value of texture parameters of PET/CT on renal cell carcinoma and renal lymphoma. METHODS: Twenty renal lymphoma and 18 renal cell carcinoma (RCC) patients were analyzed in this study. The pathological information and basic characteristics were extracted from the electronic medical record system of our hospital. We used LIFEx package to extract data from the radiomics images. Receiver operating characteristic analysis and binary logistic regression analysis was applied in determining the diagnostic accuracy of texture parameters as well as the synthetic parameter, of which the sensitivity and specificity was improved. RESULTS: There were 14 (two in Histogram, two in Grey Level Co-occurrence Matrix, five in Grey-Level Run Length Matrix, five in Grey-Level Zone Length Matrix) out of the texture parameters showing an area under the curve (AUC) >0.7 and P<0.05. Synthesized parameters of each section showed even higher differentiation ability, with AUC varying from 0.725 to 1.000. CONCLUSIONS: Texture analysis of 18F-FDG PET/CT could effectively differentiate between RCCs and renal lymphomas.

Comparison of Radiomics-Based Machine-Learning Classifiers in Diagnosis of Glioblastoma From Primary Central Nervous System Lymphoma.

Purpose: The purpose of the current study was to evaluate the ability of magnetic resonance (MR) radiomics-based machine-learning algorithms in differentiating glioblastoma (GBM) from primary central nervous system lymphoma (PCNSL). Method: One-hundred and thirty-eight patients were enrolled in this study. Radiomics features were extracted from contrast-enhanced MR images, and the machine-learning models were established using five selection methods (distance correlation, random forest, least absolute shrinkage and selection operator (LASSO), eXtreme gradient boosting (Xgboost), and Gradient Boosting Decision Tree) and three radiomics-based machine-learning classifiers [linear discriminant analysis (LDA), support vector machine (SVM), and logistic regression (LR)]. Sensitivity, specificity, accuracy, and areas under curves (AUC) of models were calculated, with which the performances of classifiers were evaluated and compared with each other. Result: Brilliant discriminative performance would be observed among all classifiers when combined with the suitable selection method. For LDA-based models, the optimal one was Distance Correlation + LDA with AUC of 0.978. For SVM-based models, Distance Correlation + SVM was the one with highest AUC of 0.959, while for LR-based models, the highest AUC was 0.966 established with LASSO + LR. Conclusion: Radiomics-based machine-learning algorithms potentially have promising performances in differentiating GBM from PCNSL.

Role of Contrast-Enhanced Ultrasound (CEUS) in the Diagnosis of Cervical Lymph Node Metastasis in Nasopharyngeal Carcinoma (NPC) Patients.

Objective: The aim of the study was to evaluate the diagnostic value of contrast-enhanced ultrasound (CEUS) in distinguishing between benign and malignant cervical lymph nodes in patients with nasopharyngeal carcinoma (NPC). Material and Methods: A total of 144 NPC patients with enlarged superficial cervical lymph nodes underwent CEUS examination. The comparison of CEUS image characteristics between malignant and benign cervical lymph nodes was performed in this study as well. We analyzed parameters of the time-intensity curve (TIC), which includes time to peak (TP), area under the gamma curve (AUC), and peak intensity (PI). Furthermore, receiver operating characteristic (ROC) curve analysis was also investigated to evaluate the diagnostic value of CEUS. Result: We conducted 144 lymph node examinations in total, where 64 cases were biopsy-proven benign nodules and 80 cases were biopsy-proven metastatic nodules. The vast majority of the benign nodes displayed centrifugal perfusion (96.88%, 62/64) and homogeneous enhancement (93.75%, 60/64), while most of the malignant nodes showed centripetal perfusion (92.50%, 74/80) and inhomogeneous 80.00% (64/80). In addition, quantitative analysis showed that CEUS parameters including PI, TP, and AUC in benign lymph nodes (12.51 ± 2.15, 23.79 ± 11.80, and 1110.33 ± 286.17, respectively) were significantly higher than that in the malignant nodes (10.51 ± 2.98, 16.52 ± 6.95, and 784.09 ± 340.24, respectively). The assistance of the three aforementioned parameters and CEUS image characteristics would result in an acceptable diagnostic value. Conclusion: Our results suggest that imaging perfusion patterns as well as quantitative parameters obtained from CEUS provide valuable information for the evaluation of cervical lymph nodes in NPC patients.

Machine-Learning Classifiers in Discrimination of Lesions Located in the Anterior Skull Base.

Purpose: The aim of this study was to investigate the diagnostic value of machine-learning models with radiomic features and clinical features in preoperative differentiation of common lesions located in the anterior skull base. Methods: A total of 235 patients diagnosed with pituitary adenoma, meningioma, craniopharyngioma, or Rathke cleft cyst were enrolled in the current study. The discrimination was divided into three groups: pituitary adenoma vs. craniopharyngioma, meningioma vs. craniopharyngioma, and pituitary adenoma vs. Rathke cleft cyst. In each group, five selection methods were adopted to select suitable features for the classifier, and nine machine-learning classifiers were employed to build discriminative models. The diagnostic performance of each combination was evaluated with area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity calculated for both the training group and the testing group. Results: In each group, several classifiers combined with suitable selection methods represented feasible diagnostic performance with AUC of more than 0.80. Moreover, the combination of least absolute shrinkage and selection operator as the feature-selection method and linear discriminant analysis as the classification algorithm represented the best comprehensive discriminative ability. Conclusion: Radiomics-based machine learning could potentially serve as a novel method to assist in discriminating common lesions in the anterior skull base prior to operation.

The Value of CEUS in Distinguishing Cancerous Lymph Nodes From the Primary Lymphoma of the Head and Neck.

Aim: The purpose of this study was to assess the ability of contrast-enhanced ultrasonography (CEUS) in the differential diagnosis of cancerous lymph nodes. Methods: Contrast-enhanced ultrasonography was performed in the cervical nodules of included patients, and the diagnoses were confirmed by pathological examination. Contrast-enhanced ultrasonography images and parameters of head and neck lymphomas were compared with those of cancerous lymph nodes. Besides, receiver operating characteristic curve was operated to access the diagnostic value of CEUS. Results: Finally, a total of 63 head and neck lymphomas and 80 cervical cancerous lymph nodes were enrolled in this study. Results showed that the CEUS images of lymphoma were mainly characterized by homogeneous enhancement (71.43%), and approximately half of them were centripetal perfusion (58.73%), whereas most CEUS images of cancerous lymph nodes were inhomogeneous enhancement (82.50%) and centripetal perfusion (92.50%). Quantitative analysis of CEUS parameters indicated that PI (derived peak intensity) and AUC (area under the curve) of lymphomas were both lower than those of cancerous lymph nodes (PI: 8.78 vs. 10.51, AUC: 652.62 vs. 784.09, respectively) (P < 0.05). Receiver operating characteristic analysis showed that the sensitivity of CEUS parameters in the differential diagnosis was significant (80.00%), although the specificity was not high (47.62%). When parameters were combined with the image features, the accuracy of diagnosis was greatly improved (from 0.655 to 0.899). Conclusion: Contrast-enhanced ultrasonography could be a promising tool for the differential diagnosis of head and neck lymphomas and cancerous lymph nodes.

Contrast-Enhanced CT Texture Analysis: a New Set of Predictive Factors for Small Cell Lung Cancer.

PURPOSE: The purpose of this study was to investigate the relationship between x-ray computed tomography (CT) texture features of small cell lung cancer (SCLC) and the survival of the patients. PROCEDURES: Eighty-eight patients with unresectable SCLCs (extended stage, 57; limited stage, 31) underwent platinum-based chemotherapy at our institution between January 2010 and 2015. All the patients were followed up for at least 18 months or until death. The CT texture features of tumor tissue were extracted from contrast-enhanced CT images taken before antitumor treatment. Receiver operating characteristic (ROC) curve analysis was used to calculate the optimal cutoff values of each texture parameter, based on which the patients were dichotomized into two subgroups to evaluate the prognostic value of each feature. Kaplan-Meier survival analysis and the log rank test were performed to compare the differences of 18-month overall survival (OS) and 6-month event-free survival (EFS) in dichotomized subgroups. Multivariate Cox regression analysis was performed to determine if the features could be taken as independent prognostic factors. RESULTS: A total number of 35 CT texture features were extracted from six matrixes. Four of them (GLCM-Contrast, GLCM-Dissimilarity, Histo-Energy, and Histo-Entropy) were shown to be significantly related to 18-month OS, and two (GLCM-Energy and GLCM-Entropy) were shown to be significantly related to 6-month EFS. Cox regression suggested that GLCM-Dissimilarity was independently associated with OS, while GLCM-Energy were independently associated with EFS. CONCLUSIONS: The texture features of contrast-enhanced computed tomography image could potentially serve as radiological prognostic biomarkers for SCLC patients.

Radiomics based on 18 F-FDG PET/CT could differentiate breast carcinoma from breast lymphoma using machine-learning approach: A preliminary study.

PURPOSE: Our study assessed the ability 18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) radiomics to differentiate breast carcinoma from breast lymphoma using machine-learning approach. METHODS: Sixty-five breast nodules from 44 patients diagnosed as breast carcinoma or breast lymphoma were included. Standardized uptake value (SUV) and radiomic features from CT and PET images were extracted using local image features extraction software. Six discriminative models including PETa (based on clinical, SUV and radiomic features from PET images), PETb (SUV and radiomic features from PET images), PETc (radiomic features only from PET images), CTa (clinical and radiomic features from CT images), CTb (radiomic features only from CT images), and SUV model were generated using least absolute shrinkage and selection operator method and linear discriminant analysis. The areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were calculated to evaluate the discriminative ability of these models. RESULTS: PETa and CTa models showed the best ability to differentiation in training and validation group (AUCs of 0.867 and 0.806 for PETa model, AUCs of 0.891 and 0.759 for CTa model, respectively). CONCLUSION: Models based on clinical, SUV, and radiomic features of 18 F-FDG PET/CT images could accurately discriminate breast carcinoma from breast lymphoma.

Prediction of Overall Survival and Progression-Free Survival by the 18F-FDG PET/CT Radiomic Features in Patients with Primary Gastric Diffuse Large B-Cell Lymphoma.

Purpose. To determine whether the radiomic features of 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) contribute to prognosis prediction in primary gastric diffuse large B-cell lymphoma (PG-DLBCL) patients. Methods. This retrospective study included 35 PG-DLBCL patients who underwent PET/CT scans at West China Hospital before curative treatment. The volume of interest (VOI) was drawn around the tumor, and radiomic analysis of the PET and CT images, within the same VOI, was conducted. The metabolic and textural features of PET and CT images were evaluated. Correlations of the extracted features with the overall survival (OS) and progression-free survival (PFS) were evaluated. Univariate and multivariate analyses were conducted to assess the prognostic value of the radiomic parameters. Results. In the univariate model, many of the textural features, including kurtosis and volume, extracted from the PET and CT datasets were significantly associated with survival (5 for OS and 7 for PFS (PET); 7 for OS and 14 for PFS (CT)). Multivariate analysis identified kurtosis (hazard ratio (HR): 28.685, 95% confidence interval (CI): 2.067-398.152, p=0.012), metabolic tumor volume (MTV) (HR: 26.152, 95% CI: 2.089-327.392, p=0.011), and gray-level nonuniformity (GLNU) (HR: 14.642, 95% CI: 2.661-80.549, p=0.002) in PET and sphericity (HR: 11.390, 95% CI: 1.360-95.371, p=0.025) and kurtosis (HR: 11.791, 95% CI: 1.583-87.808, p=0.016), gray-level nonuniformity (GLNU) (HR: 6.934, 95% CI: 1.069-44.981, p=0.042), and high gray-level zone emphasis (HGZE) (HR: 9.805, 95% CI: 1.359-70.747, p=0.024) in CT as independent prognostic factors. Conclusion. 18F-FDG PET/CT radiomic features are potentially useful for survival prediction in PG-DLBCL patients. However, studies with larger cohorts are needed to confirm the clinical prognostication of these parameters.

Radiomics-Based Machine Learning in Differentiation Between Glioblastoma and Metastatic Brain Tumors.

Purpose: To investigative the diagnostic performance of radiomics-based machine learning in differentiating glioblastomas (GBM) from metastatic brain tumors (MBTs). Method: The current study involved 134 patients diagnosed and treated in our institution between April 2014 and December 2018. Radiomics features were extracted from contrast-enhanced T1 weighted imaging (T1C). Thirty diagnostic models were built based on five selection methods and six classification algorithms. The sensitivity, specificity, accuracy, and area under curve (AUC) of each model were calculated, and based on these the optimal model was chosen. Result : Two models represented promising diagnostic performance with AUC of 0.80. The first model was a combination of Distance Correlation as the selection method and Linear Discriminant Analysis (LDA) as the classification algorithm. In the training group, the sensitivity, specificity, accuracy, and AUC were 0.75, 0.85, 0.80, and 0.80, respectively; and in the testing group, the sensitivity, specificity, accuracy, and AUC of the model were 0.69, 0.86, 0.78, and 0.80, respectively. The second model was the Distance Correlation as the selection method and logistic regression (LR) as the classification algorithm, with sensitivity, specificity, accuracy, and AUC of 0.75, 0.85, 0.80, 0.80 in the training group and 0.69, 0.86, 0.78, 0.80 in the testing group. Conclusion: Radiomic-based machine learning has potential to be utilized in differentiating GBM from MBTs.

Three-Dimensional Texture Analysis Based on PET/CT Images to Distinguish Hepatocellular Carcinoma and Hepatic Lymphoma.

Objectives: This study compared the diagnostic ability of image-based parameters with texture parameters in the differentiation of hepatocellular carcinoma (HCC) and hepatic lymphoma (HL) by positron emission tomography-computed tomography (PET/CT). Methods: Patients with pathological diagnosis of HCC and HL were included in this study. Image-based and texture parameters were obtained by manual drawing of region of interest. Receiver operating characteristic (ROC) was used to test the diagnostic capacity of each parameter. Binary logistic regression was used to transform the most discriminative image-based parameters, texture parameters, and the combination of these parameters into three regression models. ROC was used to test the diagnostic capacity of these models. Result: Ninety-nine patients diagnosed with HCC (n = 76) and HL (n = 23, 10 primary HL, 13 secondary HL) by histological examination were included in this study (From 2011 to 2018, West China hospital). According to the AUC and p-value, 2 image-based parameters and five texture parameters were selected. The diagnostic ability of texture-based model was better than that of image-based model, and after combination of those two groups of parameters the diagnostic capacity improved. Conclusion: Texture parameters can differentiate HCC from HL quantitatively and improve the diagnostic ability of image-based parameters.

Glioblastoma and Anaplastic Astrocytoma: Differentiation Using MRI Texture Analysis.

Introduction: Glioblastoma and anaplastic astrocytoma (ANA) are two of the most common primary brain tumors in adults. The differential diagnosis is important for treatment recommendations and prognosis assessment. This study aimed to assess the discriminative ability of texture analysis using machine learning to distinguish glioblastoma from ANA. Methods: A total of 123 patients with glioblastoma (n = 76) or ANA (n = 47) were enrolled in this study. Texture features were extracted from contrast-enhanced Magnetic Resonance (MR) images using LifeX package. Three independent feature-selection methods were performed to select the most discriminating parameters:Distance Correlation, least absolute shrinkage and selection operator (LASSO), and gradient correlation decision tree (GBDT). These selected features (datasets) were then randomly split into the training and the validation group at the ratio of 4:1 and were fed into linear discriminant analysis (LDA), respectively, and independently. The standard sensitivity, specificity, the areas under receiver operating characteristic curve (AUC) and accuracy were calculated for both training and validation group. Results: All three models (Distance Correlation + LDA, LASSO + LDA and GBDT + LDA) showed promising ability to discriminate glioblastoma from ANA, with AUCs ≥0.95 for both the training and the validation group using LDA algorithm and no overfitting was observed. LASSO + LDA showed the best discriminative ability in horizontal comparison among three models. Conclusion: Our study shows that MRI texture analysis using LDA algorithm had promising ability to discriminate glioblastoma from ANA. Multi-center studies with greater number of patients are warranted in future studies to confirm the preliminary result.

Discrimination of Pancreatic Serous Cystadenomas From Mucinous Cystadenomas With CT Textural Features: Based on Machine Learning.

Objectives: This study was designed to estimate the performance of textural features derived from contrast-enhanced CT in the differential diagnosis of pancreatic serous cystadenomas and pancreatic mucinous cystadenomas. Methods: Fifty-three patients with pancreatic serous cystadenoma and 25 patients with pancreatic mucinous cystadenoma were included. Textural parameters of the pancreatic neoplasms were extracted using the LIFEx software, and were analyzed using random forest and Least Absolute Shrinkage and Selection Operator (LASSO) methods. Patients were randomly divided into training and validation sets with a ratio of 4:1; random forest method was adopted to constructed a diagnostic prediction model. Scoring metrics included sensitivity, specificity, accuracy, and AUC. Results: Radiomics features extracted from contrast-enhanced CT were able to discriminate pancreatic mucinous cystadenomas from serous cystadenomas in both the training group (slice thickness of 2 mm, AUC 0.77, sensitivity 0.95, specificity 0.83, accuracy 0.85; slice thickness of 5 mm, AUC 0.72, sensitivity 0.90, specificity 0.84, accuracy 0.86) and the validation group (slice thickness of 2 mm, AUC 0.66, sensitivity 0.86, specificity 0.71, accuracy 0.74; slice thickness of 5 mm, AUC 0.75, sensitivity 0.85, specificity 0.83, accuracy 0.83). Conclusions: In conclusion, our study provided preliminary evidence that textural features derived from CT images were useful in differential diagnosis of pancreatic mucinous cystadenomas and serous cystadenomas, which may provide a non-invasive approach to determine whether surgery is needed in clinical practice. However, multicentre studies with larger sample size are needed to confirm these results.

Ability of 18F-FDG PET/CT Radiomic Features to Distinguish Breast Carcinoma from Breast Lymphoma.

Purpose. To investigate the value of SUV metrics and radiomic features based on the ability of 18F-FDG PET/CT in differentiating between breast lymphoma and breast carcinoma. Methods. A total of 67 breast nodules from 44 patients who underwent 18F-FDG PET/CT pretreatment were retrospectively analyzed. Radiomic parameters and SUV metrics were extracted using the LIFEx package on PET and CT images. All texture parameters were divided into six groups: histogram (HISTO), SHAPE, gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), neighborhood gray-level different matrix (NGLDM), and gray-level zone-length matrix (GLZLM). Receiver operating characteristics (ROC) curves were generated to evaluate the discriminative ability of each parameter, and the optimal parameter in each group was selected to generate a new predictive variable by using binary logistic regression. PET predictive variable, CT predictive variable, the combination of PET and CT predictive variables, and SUVmax were compared in terms of areas under the curve (AUCs), sensitivity, specificity, and accuracy. Results. Except for SUVmin (p=0.971), the averages of FDG uptake metrics of lymphoma were significantly higher than those of carcinoma (p ≤ 0.001), with the following median values: SUVmean, 4.75 versus 2.38 g/ml (P < 0.001); SUVstd, 2.04 versus 0.88 g/ml (P=0.001); SUVmax, 10.69 versus 4.76 g/ml (P=0.001); SUVpeak, 9.15 versus 2.78 g/ml (P < 0.001); TLG, 42.24 versus 9.90 (P < 0.001). In the ROC curves analysis based on radiomic features and SUVmax, the AUC for SUVmax was 0.747, for CT texture parameters was 0.729, for PET texture parameters was 0.751, and for the combination of CT and PET texture parameters was 0.771. Conclusion. The SUV metrics in 18FDG PET/CT images showed a potential ability in the differentiation between breast lymphoma and carcinoma. The combination of SUVmax and PET/CT texture analysis may be promising to provide an effectively discriminant modality for the differential diagnosis of breast lymphoma and carcinoma, even for the differentiation of subtypes of lymphoma.

Ability of Radiomics in Differentiation of Anaplastic Oligodendroglioma From Atypical Low-Grade Oligodendroglioma Using Machine-Learning Approach.

Objectives: To investigate the ability of radiomics features from MRI in differentiating anaplastic oligodendroglioma (AO) from atypical low-grade oligodendroglioma using machine-learning algorithms. Methods: A total number of 101 qualified patients (50 participants with AO and 51 with atypical low-grade oligodendroglioma) were enrolled in this retrospective, single-center study. Forty radiomics features of tumor images derived from six matrices were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images. Three selection methods were performed to select the optimal features for classifiers, including distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT). Then three machine-learning classifiers were adopted to generate discriminative models, including linear discriminant analysis, support vector machine, and random forest (RF). Receiver operating characteristic analysis was conducted to evaluate the discriminative performance of each model. Results: Nine predictive models were established based on radiomics features from T1C images and FLAIR images. All of the classifiers represented feasible ability in differentiation, with AUC more than 0.840 when combined with suitable selection method. For models based on T1C images, the combination of LASSO and RF classifier represented the highest AUC of 0.904 in the validation group. For models based on FLAIR images, the combination of GBDT and RF classifier showed the highest AUC of 0.861 in the validation group. Conclusion: Radiomics-based machine-learning approach could potentially serve as a feasible method in distinguishing AO from atypical low-grade oligodendroglioma.

The efficacy and safety of anti-CD19/CD20 chimeric antigen receptor- T cells immunotherapy in relapsed or refractory B-cell malignancies:a meta-analysis.

BACKGROUND: Chimeric antigen receptor T (CAR T) cells immunotherapy is rapidly developed in treating cancers, especially relapsed or refractory B-cell malignancies. METHODS: To assess the efficacy and safety of CAR T therapy, we analyzed clinical trials from PUBMED and EMBASE. RESULTS: Results showed that the pooled response rate, 6-months and 1-year progression-free survival (PFS) rate were 67%, 65.62% and 44.18%, respectively. We observed that received lymphodepletion (72% vs 44%, P = 0.0405) and high peak serum IL-2 level (85% vs 31%, P = 0.04) were positively associated with patients' response to CAR T cells. Similarly, costimulatory domains (CD28 vs CD137) in second generation CAR T was positively associated with PFS (52.69% vs 33.39%, P = 0.0489). The pooled risks of all grade adverse effects (AEs) and grade ≥ 3 AEs were 71% and 43%. Most common grade ≥ 3 AEs were fatigue (18%), night sweats (14%), hypotension (12%), injection site reaction (12%), leukopenia (10%), anemia (9%). CONCLUSIONS: In conclusion, CAR T therapy has promising outcomes with tolerable AEs in relapsed or refractory B-cell malignancies. Further modifications of CAR structure and optimal therapy strategy in continued clinical trials are needed to obtain significant improvements.