Whole-tumor amide proton transfer-weighted imaging histogram analysis to predict pathological extramural venous invasion in rectal adenocarcinoma: a preliminary study.

OBJECTIVES: To evaluate amide proton transfer-weighted (APTw)-derived whole-tumor histogram analysis parameters in predicting pathological extramural venous invasion (pEMVI) positive status of rectal adenocarcinoma (RA). METHODS: Preoperative MR including APTw imaging of 125 patients with RA (mean 61.4 ± 11.6 years) were retrospectively analyzed. Two radiologists reviewed each case's EMVI status based on the MR-based modified 5-point scale system with conventional MR images. The APTw histogram parameters of primary tumors were obtained automatically using whole-tumor volume histogram analysis. The independent risk factors markedly correlated with pEMVI-positive status were assessed using univariate and multivariate logistic regression analyses. Diagnosis performance was assessed by receiver operating characteristic curve (ROC) analysis. The AUCs were compared using the Delong method. RESULTS: Univariate analysis demonstrated that MR-tumor (T) stage, MR-lymph node (N) stage, APTw-10%, APTw-90%, interquartile range, APTw-minimum, APTw-maximum, APTw-mean, APTw-median, entropy, kurtosis, mean absolute deviation (MAD), and robust MAD were significantly related to pEMVI-positive status (all p < 0.05). Multivariate analysis demonstrated that MR-T stage (OR = 4.864, p = 0.018), MR-N stage (OR = 4.967, p = 0.029), interquartile range (OR = 0.892, p = 0.037), APT-minimum (OR = 1.046, p = 0.031), entropy (OR = 11.604, p = 0.006), and kurtosis (OR = 1.505, p = 0.007) were the independent risk factors enabling prediction of pEMVI-positive status. The AUCs for diagnostic ability of conventional MRI assessment, the APTw histogram model, and the combined model (including APTw histogram and clinical variables) were 0.785, 0.853, and 0.918, respectively. The combined model outperformed the APTw histogram model (p = 0.013) and the conventional MRI assessment (p = 0.006). CONCLUSIONS: Whole-tumor histogram analysis of APTw images combined with clinical factors showed better diagnosis efficiency in predicting EMVI involvement in RA. KEY POINTS: • Rectal adenocarcinomas with pEMVI-positive status are typically associated with higher APTw-SI values. • APTw-minimum, interquartile range, entropy, kurtosis, MR-T stage, and MR-N stage are the independent risk factors for EMVI involvement. • The best prediction for EMVI involvement was obtained with a combined model of APTw histogram and clinical variables (area under the curve, 0.918).

Preoperative MR radiomics based on high-resolution T2-weighted images and amide proton transfer-weighted imaging for predicting lymph node metastasis in rectal adenocarcinoma.

OBJECTIVES: Lymph node (LN) metastasis is an important prognostic factor in rectal cancer (RC). However, accurate identification of LN metastasis can be challenged for radiologists. The aim of our study was to assess the utility of MRI radiomics based on T2-weighted images (T2WI) and amide proton transfer-weighted (APTw) images for predicting LN metastasis in RC preoperatively. METHODS: A total of 125 patients with pathologically confirmed rectal adenocarcinoma (RA) from January 2019 to June 2021 who underwent preoperative MR were enrolled in this retrospective study. Radiomics features were extracted from high-resolution T2WI and APTw images of primary tumor. The most relevant radiomics and clinical features were selected using correlation and multivariate logistic analysis. Radiomics models were built using five machine learning algorithms including support vector machine (SVM), logical regression (LR), k- nearest neighbor (KNN), naive bayes (NB), and random forest (RF). The best algorithm was selected for further establish the clinical- radiomics model. The receiver operating characteristic curve (ROC) analysis was used to assess the performance of radiomics and clinical-radiomics model for predicting LN metastasis. RESULTS: The LR classifier had the best prediction performance, with AUCs of 0.983 (95% CI 0.957-1.000), 0.864 (95% CI 0.729-0.972), 0.851 (95% CI 0.713-0.940) on the training set, validation, and test sets, respectively. In terms of prediction, the clinical-radiomics combined model outperformed the radiomics model. The AUCs of the clinical-radiomics combined model in the validation and test sets were 0.900 (95% CI 0.785-0.986), and 0.929 (95% CI 0.721-0.943), respectively. CONCLUSION: The radiomics model based on high-resolution T2WI and APTw images can predict LN metastasis accurately in patients with RA.

External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study.

OBJECTIVES: The aim of this study was two-fold: (1) to develop and externally validate a multiparameter MR-based machine learning model to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT), and (2) to compare different classifiers' discriminative performance for pCR prediction. METHODS: This retrospective study includes 151 LARC patients divided into internal (centre A, n = 100) and external validation set (centre B, n = 51). The clinical and MR radiomics features were derived to construct clinical, radiomics, and clinical-radiomics model. Random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), and extreme gradient boosting (XGBoost) were used as classifiers. The predictive performance was assessed using the receiver operating characteristic (ROC) curve. RESULTS: Eleven radiomics and four clinical features were chosen as pCR-related signatures. In the radiomics model, the RF algorithm achieved 74.0% accuracy (an AUC of 0.863) and 84.4% (an AUC of 0.829) in the internal and external validation sets. In the clinical-radiomics model, RF algorithm exhibited high and stable predictive performance in the internal and external validation datasets with an AUC of 0.906 (87.3% sensitivity, 73.7% specificity, 76.0% accuracy) and 0.872 (77.3% sensitivity, 88.2% specificity, 86.3% accuracy), respectively. RF showed a better predictive performance than the other classifiers in the external validation datasets of three models. CONCLUSIONS: The multiparametric clinical-radiomics model combined with RF algorithm is optimal for predicting pCR in the internal and external sets, and might help improve clinical stratifying management of LARC patients. KEY POINTS: • A two-centre study showed that radiomics analysis of pre- and post-nCRT multiparameter MR images could predict pCR in patients with LARC. • The combined model was superior to the clinical and radiomics model in predicting pCR in locally advanced rectal cancer. • The RF classifier performed best in the current study.

Combining diffusion kurtosis imaging and clinical data for predicting the extramural venous invasion of rectal adenocarcinoma.

OBJECTIVE: The aim of this study is to investigate the diagnostic ability of diffusion kurtosis imaging (DKI) -derived parameters combining with clinical data as risk factors for EMVI's involvement status in rectal adenocarcinoma. MATERIALS AND METHODS: Preoperative MR examination including DKI and conventional diffusion-weighted imaging (DWI) was performed on 154 rectal adenocarcinoma patients enrolled in this respective study. Kmean, Dmean, and apparent diffusion coefficient (ADC) values were calculated. Clinical information, serum tumor markers, MR and pathological assessment of EMVI were recorded. The Shapiro-Wilk test, two-sample t-test, Mann-Whitney U test, Spearman's rank-order correlation, univariate and multivariate logistic regression analyses were used for statistical analysis. Receiver operating characteristic (ROC) curve analyses were performed to identify risk factors in EMVI involvement. RESULTS: Of the 154 patients, pEMVI-positive rectal tumors had significantly higher Kmean values, lower ADCmean values compared to pEMVI-negative rectal tumors. Kmean values positively correlated with mrEMVI scores, whereas ADCmean values showed a negative correlation with mrEMVI scores. However, there was no significant correlation between the Dmean values and the mrEMVI scores. Univariate analysis demonstrated increased Kmean values, decreased ADCmean values, nodal involvement, an advanced tumor stage, and a G2 tumor grade were significantly related to the pEMVI of rectal adenocarcinoma. The multivariate analysis demonstrated that the Kmean values, lymph node involvement and an advanced tumor stage (T3) were independent risk factors for EMVI. CONCLUSION: The potential for diffusion kurtosis imaging as a biomarker for evaluating the EMVI of rectal cancer is feasible, especially given DKI's capability of detecting tumor heterogeneity noninvasively.

Predicting Treatment Response of Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Using Amide Proton Transfer MRI Combined With Diffusion-Weighted Imaging.

OBJECTIVE: To evaluate amide proton weighted (APTw) MRI combined with diffusion-weighted imaging (DWI) in predicting neoadjuvant chemoradiotherapy (NCRT) response in patients with locally advanced rectal cancer (LARC). METHODS: 53 patients with LARC were enrolled in this retrospective study. MR examination including APTw MRI and DWI was performed before and after NCRT. APTw SI, ADC value, tumor size, CEA level before and after NCRT were assessed. The difference of the above parameters between before and after NCRT was calculated. The tumor regression grading (TRG) was assessed by American Joint Committee on Cancer's Cancer Staging Manual AJCC 8th score. The Shapiro-Wilk test, paired t-test and Wilcoxon Signed Ranks test, two-sample t-test, Mann-Whitney U test and multivariate analysis were used for statistical analysis. RESULTS: Of the 53 patients, 19 had good responses (TRG 0-1), 34 had poor responses (TRG 2-3). After NCRT, all the rectal tumors demonstrated decreased APT values, increased ADC values, reduced tumor volumes and CEA levels (all p < 0.001). Good responders demonstrated higher pre-APT values, higher Δ APT values, lower pre- ADC values and higher Δ tumor volumes than poor responders. Pre-APT combined with pre-ADC achieved the best diagnostic performance, with AUC of 0.895 (sensitivity of 85.29%, specificity of 89.47%, p < 0.001) in predicting good response to NCRT. CONCLUSION: The combination of APTw and DWI may serve as a noninvasive biomarker for evaluating and identifying response to NCRT in LARC patients.