The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I-II and stage III-IV colorectal cancer

Abstract

Objectives: To investigative the predictive ability of radiomics signature for preoperative staging (I-IIvs.III-IV) of primary colorectal cancer (CRC).

Methods: This study consisted of 494 consecutive patients (training dataset: n=286; validation cohort, n=208) with stage I-IV CRC. A radiomics signature was generated using LASSO logistic regression model. Association between radiomics signature and CRC staging was explored. The classification performance of the radiomics signature was explored with respect to the receiver operating characteristics(ROC) curve.

Results: The 16-feature-based radiomics signature was an independent predictor for staging of CRC, which could successfully categorize CRC into stage I-II and III-IV (p <0.0001) in training and validation dataset. The median of radiomics signature of stage III-IV was higher than stage I-II in the training and validation dataset. As for the classification performance of the radiomics signature in CRC staging, the AUC was 0.792(95%CI:0.741-0.853) with sensitivity of 0.629 and specificity of 0.874. The signature in the validation dataset obtained an AUC of 0.708(95%CI:0.698-0.718) with sensitivity of 0.611 and specificity of 0.680.

Conclusions: A radiomics signature was developed and validated to be a significant predictor for discrimination of stage I-II from III-IV CRC, which may serve as a complementary tool for the preoperative tumor staging in CRC.

Keywords: colorectal cancer; computed tomography; predictor; radiomics signature; stage.

Figure 1. Receiver operating characteristic (ROC) curves of the radiomics signature in the training dataset and validation dataset

Figure 1a-1b. represents the ROC curves of radiomics signature for training dataset, validation dataset, respectively.

Figure 2. Signature scores for each patient regarding the classification of tumor stage (I-II vs. III-IV) in the training dataset and validation dataset

Figure 2a-2b. represents the signature scores distribution in the training (2a) and validation (2b) dataset. The blue marks indicate stage I-II CRC patients, while the gold marks indicate stage III-IV CRC patients. The solid line presents the best cutoff of radiomics signature for the discrimination of stage I-II and stage III-IV CRC patients, below which patients are discriminated to be stage I-II CRC patients and above which patients are discriminated to be CRC stage III-IV patients. The cutoff value is 0.392.

Figure 3. Receiver operating characteristic (ROC) curves of the maximum diameter, clinical model and combined model

Figure 3a-3f. represents the ROC curves of maximum diameter (training: Figure 3a.; validation: Figure 3b.), clinical model (training: Figure 3c.; validation: Figure 3d.) and combined model (training: Figure 3e.; validation: Figure 3f.).

Figure 4

Figure 4a-4f. represents the ROC curves of radiomics signature for each subgroup when stratified by gender (male: Figure 4a.; female: Figure 4b.), age (<=65: Figure 4c.; >65: Figure 4d.), histological grade (poorly differentiated: 4e; well-moderately differentiated: 4f).

Figure 5. Signature scores for each patient regarding the classification of tumor stage (I-II vs. III-IV) in subgroups

The blue marks indicate stage I-II CRC patients, while the gold marks indicate stage III-IV CRC patients. The solid line presents the best cutoff of radiomics signature for the discrimination of stage I-II and stage III-IV CRC patients, below which patients are discriminated to be stage I-II CRC patients and above which patients are discriminated to be CRC stage III-IV patients. The cutoff values for the discrimination in subgroups were as follow: male, 0.391; female, 0.425; age <= 65, 0.325; age > 65, 0.477; poorly differentiated, 0.391; well-moderately differentiated, 0.392, respectively).