Zhenjiang Li

Purpose To explore the potential of texture analysis based on apparent diffusion coefficient (ADC) maps, as a predictor of local invasion depth (stage pT1‐2 versus pT3‐4) and nodal status (pN0 versus pN1‐2) of rectal cancer. Materials and Methods Sixty‐eight patients with rectal cancer underwent preoperative magnetic resonance (MR) imaging including diffusion weighted imaging (DWI) at a 3.0 Tesla system. Routine ADC variables (ADC mean , ADC min , ADC max ), histogram features (skewness, kurtosis) and gray level co‐occurrence matrix features (entropy, contrast, correlation) were compared between pT1‐2 and pT3‐4 stages, between pN0 and pN1‐2 stages. Results Skewness, entropy, and contrast were significantly lower in patients with pT1‐2 as compared to those with pT3‐4 tumors (0.166 versus 0.476, P = 0.015; 3.212 versus 3.441 P = 0.004; 10.773 versus 13.596, P = 0.017). Furthermore, skewness and entropy were identified as independent predictors for extramural invasion of tumors (stage pT3‐4). Significant differences were observed between pN0 and pN1‐2 tumors with respect to ADC mean (1.152 versus 1.044, P = 0.029), ADC max (1.692 versus 1.460, P = 0.006) and entropy (3.299 versus 3.486, P = 0.015). ADC max. and entropy were independent predictors of positive nodal status. Conclusion Texture analysis on ADC maps could provide valuable information in identifying locally advanced rectal cancer. Level of Evidence : 3 J. MAGN. RESON. IMAGING 2017;45:1798–1808

PURPOSE: To explore the clinical potential of texture analysis using contrast-enhanced 3.0T magnetic resonance imaging (MRI) for predicting the therapeutic response of nasopharyngeal carcinoma (NPC) to chemoradiotherapy. MATERIALS AND METHODS: The dataset comprised pretreatment T1 -, T2 -, and diffusion-weighted MR images from 53 eligible patients with newly diagnosed NPC. The patients were divided into two sets: the training set including 31 responders and 11 nonresponders and the testing set including eight responders and three nonresponders. The region of interest (ROI) was delineated by two radiologists for each sequence. Quantitative image parameters were extracted and statistically filtered to identify a subset of reproducible and nonredundant parameters that were used to construct the predictive model. The internal validation was performed using stratified 10-fold cross-validation in the training set and the external validation was performed in the testing set. McNemar's test was used to test the statistical difference between the performances of the extracted parameters in predicting the treatment response. RESULTS: All three parameter sets showed potential in predicting treatment response with high accuracy (T1 : 0.952/0.939, T2 : 0.904/0.905, diffusion-weighted [DWI]: 0.881/0.929). Supervised learning models based on parameters extracted from the T1 sequence showed better classification performance than those extracted from the T2 -weighted (T2 W) (artificial neural network [ANN]: P = 0.043, k-nearest neighbors [kNN]: P = 0.033) and DWI (ANN: P = 0.032. kNN: P = 0.014). No statistical difference was observed in the performance of the two classifiers (P = 0.083). CONCLUSION: Texture analysis based on T1 W, T2 W, and DWI could act as imaging biomarkers of tumor response to chemoradiotherapy in NPC patients and serve as a new radiological analysis tool for treatment prediction. J. Magn. Reson. Imaging 2016;44:445-455.

PURPOSE: The goal of this study was to investigate the feasibility of differentiating brain metastases from different types of lung cancers using texture analysis (TA) of T1 postcontrast MR images. METHODS: TA was performed, and four subset textures were extracted and calculated separately. The capability of each texture to classify the different types of lung carcinoma was investigated using the Kruskal-Wallis test and receiver operating characteristic analysis. K-nearest neighbor (KNN) classifier model and back-propagation artificial neural network (BP-ANN) classifier model were used to build models and improve the predictive ability of TA. RESULTS: Texture-based lesion classification was highly specific in differentiating brain metastases originated from different types of lung cancers, with misclassification rates of 3.1%, 4.3%, 5.8%, and 8.1%, respectively, for small cell lung carcinoma, squamous cell carcinoma, adenocarcinoma, and large cell lung carcinoma. The BP-ANN model had a better predictive ability than the KNN model. No texture feature could distinguish between all four types of lung cancer. CONCLUSIONS: TA may predict the differences among various pathological types of lung cancer with brain metastases. The texture parameters, which reflect the tumor histopathology structure, may serve as an adjunct tool for clinically accurate diagnoses and deserves further investigation. Magn Reson Med 76:1410-1419, 2016. © 2015 International Society for Magnetic Resonance in Medicine.

PurposeTo develop and validate a pretreatment computed tomography (CT)-based deep-learning (DL) model for predicting the treatment response to concurrent chemoradiation therapy (CCRT) among patients with locally advanced thoracic esophageal squamous cell carcinoma (TESCC).Methods and MaterialsWe conducted a prospective, multicenter study on the therapeutic efficacy of CCRT among TESCC patients across 9 hospitals in China (ChiCTR2000039279). A total of 306 patients with locally advanced TESCC diagnosed by histopathology from August 2015 to May 2020 were included in this study. A 3-dimensional DL radiomics model (3D-DLRM) was developed and validated based on pretreatment CT images to predict the response to CCRT. Furthermore, the prediction performance of the newly developed 3D-DLRM was analyzed according to 3 categories: radiation therapy plan, radiation field, and prescription dose used.ResultsThe 3D-DLRM achieved good prediction performance, with areas under the receiver operating characteristic curve of 0.897 (95% confidence interval, 0.840-0.959) for the training cohort and 0.833 (95% confidence interval, 0.654-1.000) for the validation cohort. Specifically, the 3D-DLRM accurately predicted patients who would not respond to CCRT, with a positive predictive value (PPV) of 100% for the validation cohort. Moreover, the 3D-DLRM performed well in all 3 categories, each with areas under the receiver operating characteristic curve of >0.8 and positive predictive values of approximately 100%.ConclusionThe proposed pretreatment CT-based 3D-DLRM provides a potential tool for predicting the response to CCRT among patients with locally advanced TESCC. With the help of precise pretreatment prediction, we may guide the individualized treatment of patients and improve survival. To develop and validate a pretreatment computed tomography (CT)-based deep-learning (DL) model for predicting the treatment response to concurrent chemoradiation therapy (CCRT) among patients with locally advanced thoracic esophageal squamous cell carcinoma (TESCC). We conducted a prospective, multicenter study on the therapeutic efficacy of CCRT among TESCC patients across 9 hospitals in China (ChiCTR2000039279). A total of 306 patients with locally advanced TESCC diagnosed by histopathology from August 2015 to May 2020 were included in this study. A 3-dimensional DL radiomics model (3D-DLRM) was developed and validated based on pretreatment CT images to predict the response to CCRT. Furthermore, the prediction performance of the newly developed 3D-DLRM was analyzed according to 3 categories: radiation therapy plan, radiation field, and prescription dose used. The 3D-DLRM achieved good prediction performance, with areas under the receiver operating characteristic curve of 0.897 (95% confidence interval, 0.840-0.959) for the training cohort and 0.833 (95% confidence interval, 0.654-1.000) for the validation cohort. Specifically, the 3D-DLRM accurately predicted patients who would not respond to CCRT, with a positive predictive value (PPV) of 100% for the validation cohort. Moreover, the 3D-DLRM performed well in all 3 categories, each with areas under the receiver operating characteristic curve of >0.8 and positive predictive values of approximately 100%. The proposed pretreatment CT-based 3D-DLRM provides a potential tool for predicting the response to CCRT among patients with locally advanced TESCC. With the help of precise pretreatment prediction, we may guide the individualized treatment of patients and improve survival.