[Application of MRI-based Radiomics Models in the Assessment of Hepatic Metastasis of Rectal Cancer].

OBEJECTIVE: To explore the clinical value of using radiomics models based on different MRI sequences in the assessment of hepatic metastasis of rectal cancer. METHODS: 140 patients with pathologically confirm edrectal cancer were included in the study. They underwent baseline magnetic resonance imaging (MRI) between April 2015 and May 2018 before receiving any treatment. According to the results of liver biopsy, surgical pathology, and imaging, patients were put into two groups, the patients with hepatic metastasis and those without. T2 weighted images (T2WI), diffusion weighted images (DWI) and apparent diffusion coefficient (ADC) images were used to draw the region of interest (ROI) of primary lesions on consecutive slices on ITK-SNAP. 3-D ROIs were generated and loaded into Artificial Intelligent Kit for extraction of radiomics features and 396 features were extracted for each sequence. The feature data were preprocessed on Python and the samples were oversampled, using Support Vector Machine-Synthetic Minority Over-Sampling Technique (SVM-SMOTE) to balance the number of samples in the group with liver metastasis and the group with no liver metastasis at the end of the follow-up. Then, the samples were divided into the training cohort and the test cohort at a ratio of 2∶1. The logistic regression models were developed with selected radionomic features on R software. The receiver operating characteristics (ROC) curves and calibration curves were used to evaluate the performance of the models. RESULTS: In total, 52 patients with liver metastasis and 88 patients without liver metastasis at the end of follow-up were enrolled. Carcinoembryonic antigen (CEA) and T stage and N stage evaluated on the MRI images showed statistically significant difference between the two groups ( P<0.05). After data preprocessing and selecting, except for 17 non-radiomic features, the model combining T2WI, DWI and ADC features, the model of T2WI features alone, the model of DWI features alone and the model of ADC features alone were developed with 32 features, 10 features, 30 features and 15 features, respectively. The combined model (T2WI+DWI+ADC), the T2WI model, and the ADC model can assess hepatic metastasis accurately, with the area under curve ( AUC) on the train set reaching 93.5%, 89.2%, 90.6% and that of the test set reaching 80.8%, 80.5%, 81.4%, respectively. The combined model did not show a higher AUC than those of the T2WI and ADC alone models. Model based on DWI features has a slightly insufficient AUC of 90.3% in the train set and 75.1% in the test set. The calibration curve showed the smallest fluctuation in the combined model, which is closest fit to the diagonal reference line. The fluctuation in the three independent data set models were similar. The calibration curves of all the four models showed that as the risk increased, the prediction of the models turned from an underestimation to an overestimating the risk. In brief, the combined model showed the best performance, with the best fit to the diagonal reference line in calibration curve and high AUC comparable to the AUC of the T2WI model and ADC model. The performance of T2WI and ADC alone models were second to that of the combined model, while the DWI alone model showed relatively poor performance. CONCLUSION: Radiomics models based on MRI could be effectively used in assessing liver metastasis in rectal cancer, which may help determine clinical staging and treatment.

[Application of Automated Machine Learning Based on Radiomics Features of T2WI and RS-EPI DWI to Predict Preoperative T Staging of Rectal Cancer].

OBJECTIVE: To explore the radiomics features of T2 weighted image (T2WI) and readout-segmented echo-planar imaging (RS-EPI) plus difusion-weighted imaging (DWI), to develop an automated mahchine-learning model based on the said radiomics features, and to test the value of this model in predicting preoperative T staging of rectal cancer. METHODS: The study retrospectively reviewed 131 patients who were diagnosed with rectal cancer confirmed by the pathology results of their surgical specimens at West China Hospital of Sichuan University between October, 2017 and December, 2018. In addition, these patients had preoperative rectal MRI. Tumor regions from preoperative MRI were manually segmented by radiologists with the ITK-SNAP software from T2WI and RS-EPI DWI images. PyRadiomics was used to extract 200 features-100 from T2WI and 100 from the apparent diffusion coefficient (ADC) calculated from the RS-EPI DWI. MWMOTE and NEATER were used to resample and balance the dataset, and 13 cases of T 1-2 stage simulation cases were added. The overall dataset was divided into a training set (111 cases) and a test set (37 cases) by a ratio of 3∶1. Tree-based Pipeline Optimization Tool (TPOT) was applied on the training set to optimize model parameters and to select the most important radiomics features for modeling. Five independent T stage models were developed accordingly. Accuracy and the area under the curve ( AUC) of receiver operating characteristic (ROC) were used to pick out the optimal model, which was then applied on the training set and the original dataset to predict the T stage of rectal cancer. RESULTS: The performance of the the five T staging models recommended by automated machine learning were as follows: The accuracy for the training set ranged from 0.802 to 0.838, sensitivity, from 0.762 to 0.825, specificity, from 0.833 to 0.896, AUC, from 0.841 to 0.893, and average precision (AP) from 0.870 to 0.901. After comparison, an optimal model was picked out, with sensitivity, specificity and AUC for the training set reaching 0.810, 0.875, and 0.893, respectively. The sensitivity, specificity and AUC for the test set were 0.810, 0.813, and 0.810, respectively. The sensitivity, specificity and AUC for the original dataset were 0.810, 0.830, and 0.860, respectively. CONCLUSION: Based on the radiomics data of T2WI and RS-EPI DWI, the model established by automated machine learning showed a fairly high accuracy in predicting rectal cancer T stage.

A diagnostic test of three-dimensional magnetic resonance elastography imaging for preoperative prediction of microvascular invasion in patients with T1 stage clear cell renal carcinoma.

Background: Detection of microvascular invasion (MVI) of kidney tumors is important for selecting the optimal therapeutic strategy. Currently, the prediction of MVI lacks an accurate imaging biomarker. This study evaluated the performance of three-dimensional (3D) magnetic resonance elastography (MRE) imaging in predicting microvascular invasion (MVI) of T1 stage clear cell renal carcinoma (ccRCC). Methods: In this prospective study, we conducted pre-surgical imaging with a clinical 3.0 T magnetic resonance imaging (MRI) system. Firstly, 83 consecutive patients were enrolled in this study. A 3D MRE stiffness map was generated and transferred to a post-processing workstation. Contrast-enhanced computed tomography (CT) was conducted to calculate the tumor enhancement ratio. The presence of MVI was evaluated by histopathological analysis and graded according to the risk stratification based upon the number and distribution. The mean stiffness and CT tumor enhancement ratio was calculated for tumors with or without MVI. The diagnostic performance [sensitivity, specificity, positive predictive value, negative predictive value, area under the curve (AUC)] and independent predicting factors for MVI were investigated. Results: Finally, A total of 80 patients (aged 46.7±13.2 years) were enrolled, including 22 cases of tumors with MVI. The mean MRE stiffness of kidney parenchyma and kidney tumors was 4.8±0.2 and 4.5±0.7 kPa, respectively. There was significant difference in the mean MRE stiffness between tumors with MVI (5.4±0.6 kPa) and tumors without MVI (4.1±0.3 kPa) (P<0.05). The sensitivity, specificity, positive predictive value, negative predictive value, and the AUC for mean stiffness in the prediction of MVI were 100%, 75%, 63%, 96%, and 0.87 [95% confidence interval (CI): 0.72, 0.94], respectively. The corresponding values for the CT tumor enhancement ratio were 90%, 80%, 63%, 96%, and 0.88 (95% CI: 0.71, 0.93), respectively. The odds ratio (OR) value for MRE tumor stiffness and CT kidney tumor enhancement ratio in the prediction of MVI was 2.9 (95% CI: 1.8, 3.7) and 1.2 (95% CI: 1.0, 1.7), respectively (P>0.05). Conclusions: 3D MRE imaging has promising diagnostic performance for predicting MVI in T1 stage ccRCC, which may improve the reliability of surgical strategy selection with T1 stage ccRCC.

Arterial Spin Labeling MRI for Predicting Microvascular Invasion of T1 Staging Renal Clear Cell Carcinoma Preoperatively.

BACKGROUND: Microvascular invasion (MVI) is a valuable factor for T1 staging renal clear cell carcinoma (ccRCC) operation strategy decision, which is confirmed histopathologically post-operation. This study aimed to prospectively evaluate the performance of arterial spin labeling (ASL) MRI for predicting MVI of T1 staging ccRCC preoperatively. METHODS: 16 volunteers and 39 consecutive patients were enrolled. MRI examinations consisted of ASL (three post label delays separately) of the kidney, followed by T1 and T2-weighted imaging. Two sessions of ASL were used to evaluate the reproducibility on volunteers. Renal blood flow of renal cortex, medulla, the entire and solid part of the tumor were measured on ASL images. Conventional imaging features were extracted. MVI and WHO/ISUP classification were evaluated histopathologically. A paired t-test was used to compare the renal cortex and medulla between ASL 1 and ASL 2. The reproducibility was assessed using the intraclass correlation. Differences in mean perfusion between the entire and the solid parts of tumors with or without MVI were assessed separately using Student's t test. The diagnostic performance was assessed. Logistic regression analysis was used to indicate the independent prediction index for MVI. RESULTS: The two sessions of ASL showed no significant difference between the mean cortex values of RBF. The cortical RBF measurements demonstrated good agreement. 12 ccRCCs presented with MVI histopathologically. Mean perfusion of the solid part of tumors with MVI were 536.4 ± 154.8 ml/min/100 g (PLD1), 2912.5 ± 939.3 ml/min/100 g (PLD2), 3280.3 ± 901.2 ml/min/100 g (PLD3). Mean perfusion of the solid part of tumors without MVI were 453.5 ± 87.2 ml/min/100 g (PLD1), 1043.6 ± 695.8 ml/min/100 g (PLD2), 1577.6 ± 1085.8 ml/min/100 g (PLD3). These two groups have significant difference at all the PLDs (p < 0.05). The RBF of PLD1 of the solid part of tumor perfusion showed well diagnostic performance for predicting MVI: sensitivity 75%, specificity 100%, positive predictive value 66.7%, and negative predictive value 95.7%. The maximum diameter of the tumor, ill-defined margin, and the solid part of tumor perfusion were the independent prediction index for MVI. CONCLUSION: ASL MR imaging has good reproducibility for renal cortex, and good diagnostic performance for predicting MVI for ccRCC.