An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer

Abstract

Objective To investigate whether radiomics based on ultrasound images can predict lymphovascular invasion (LVI) of rectal cancer (RC) before surgery. Methods A total of 203 patients with RC were enrolled retrospectively, and they were divided into a training set (143 patients) and a validation set (60 patients). We extracted the radiomic features from the largest gray ultrasound image of the RC lesion. The intraclass correlation coefficient (ICC) was applied to test the repeatability of the radiomic features. The least absolute shrinkage and selection operator (LASSO) was used to reduce the data dimension and select significant features. Logistic regression (LR) analysis was applied to establish the radiomics model. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the comprehensive performance of the model. Results Among the 203 patients, 33 (16.7%) were LVI positive and 170 (83.7%) were LVI negative. A total of 5350 (90.1%) radiomic features with ICC values of ≥ 0.75 were reported, which were subsequently subjected to hypothesis testing and LASSO regression dimension reduction analysis. Finally, 15 selected features were used to construct the radiomics model. The area under the curve (AUC) of the training set was 0.849, and the AUC of the validation set was 0.781. The calibration curve indicated that the radiomics model had good calibration, and DCA demonstrated that the model had clinical benefits. Conclusion The proposed endorectal ultrasound-based radiomics model has the potential to predict LVI preoperatively in RC.

The correlation between time-intensity curve parameters of transrectal contrast-enhanced ultrasound and pathological prognostic factors in rectal adenocarcinoma

“…For example, Zhou et al [29] developed a nomogram for predicting LVI in primary breast cancer patients based on 2D and qualitative CEUS characteristics but did not incorporate quantitative CEUS parameters. Similarly, a radiomics model based on gray ultrasound images showed promise in predicting LVI in rectal cancer [30]. However, our study represents a novel exploration of the relationship between TIC parameters and LVI and PNI in primary rectal adenocarcinomas.…”

Application research of radiomics in colorectal cancer: A bibliometric study

“…The results showed that the clinical-radiomics combined model had the best effect in predicting lymph node metastasis of rectal cancer before surgery, and the AUC in the validation set was 0.929 (95% CI: 0.72–0.94). Wu et al [ 16 ] extracted radiomics features from ultrasound images of 203 rectal cancer patients and established an ultrasound-based radiomics model to predict the lymphovascular invasion status of rectal cancer patients before surgery. The results show that the AUC of the training set of the ultrasound-based radiomics model is 0.849 and the AUC of the validation set is 0.781, which can better predict the lymphovascular invasion status of patients with rectal cancer before surgery.…”

“…The results showed that the clinical-radiomics combined model had the best effect in predicting lymph node metastasis of rectal cancer before surgery, and the AUC in the validation set was 0.929 (95% CI: 0.72-0.94). Wu et al [16] extracted radiomics features from…”

Differential diagnosis of gallbladder neoplastic polyps and cholesterol polyps with radiomics of dual modal ultrasound: a pilot study

“…We used ICC and the LASSO to select extracted features based on dual-modality images. By reducing the dimension of the extracted features and removing redundant information and irrelevant features [17][18][19][20][21], a subset of features useful for diagnosis of PLGs were selected. Firstly, two investigators independently outlined the ROIs of all the images.…”