MRI-Based Radiomics Features to Predict Treatment Response to Neoadjuvant Chemotherapy in Locally Advanced Rectal Cancer: A Single Center, Prospective Study

Abstract

This is a prospective, single center study aimed to evaluate the predictive power of peritumor and intratumor radiomics features assessed using T2 weight image (T2WI) of baseline magnetic resonance imaging (MRI) in evaluating pathological good response to NAC in patients with LARC (including Tany N+ or T3/4a Nany but not T4b). In total, 137 patients with LARC received NAC between April 2014 and August 2020. All patients were undergoing contrast-enhanced MRI and 129 patients contained small field of view (sFOV) sequence which were performed prior to treatment. The tumor regression grade standard was based on pathological response. The training and validation sets (n=91 vs. n=46) were established by random allocation of the patients. Receiver operating characteristic curve (ROC) analysis was applied to estimate the performance of different models based on clinical characteristics and radiomics features obtained from MRI, including peritumor and intratumor features, in predicting treatment response; these effects were calculated using the area under the curve (AUC). The performance and agreement of the nomogram were estimated using calibration plots. In total, 24 patients (17.52%) achieved a complete or near-complete response. For the individual radiomics model in the validation set, the performance of peritumor radiomics model in predicting treatment response yield an AUC of 0.838, while that of intratumor radiomics model is 0.805, which show no statically significant difference between then(P>0.05). The traditional and selective clinical features model shows a poor predictive ability in treatment response (AUC=0.596 and 0.521) in validation set. The AUC of combined radiomics model was improved compared to that of the individual radiomics models in the validation sets (AUC=0.844). The combined clinic-radiomics model yield the highest AUC (0.871) in the validation set, although it did not improve the performance of the radiomics model for predicting treatment response statically (P>0.05). Good agreement and discrimination were observed in the nomogram predictions. Both peritumor and intratumor radiomics features performed similarly in predicting a good response to NAC in patients with LARC. The clinic-radiomics model showed the best performance in predicting treatment response.

Keywords: magnetic resonance imaging radiomics; neoadjuvant chemotherapy; nomogram; rectal cancer; treatment response.

Figure 1

Flow chart of the study.

Figure 2

The segmentation process of the region of interest for intratumor and peritumor. (A) The whole tumor was manually segmented on axial T2-weighted images and labeled as “intratumor” area (the red area). (B) Manually outline the area of the tumor bed (the green area), which is defined as the mesorectal area that the tumor has invaded. (C) Show the outline of the entire tumor. (D–F) The edge link to the “tumor bed” of “tumor” was dilated by 5 mm and subtracted to obtain the “peritumor” tissues (the blue area).

Figure 3

The workflow of the radiomics model construction.

Figure 4

Nomogram based on the clinical characteristics and peritumor radiomics features in the prediction of response to neoadjuvant chemotherapy in locally advanced rectal cancer (LARC). (A) Nomogram based on peritumor radiomics clinical features. (B) The calibration curve for peritumor radiomics and clinical features in predicting treatment response for LARC in the training set. (C) The calibration curve for peritumor radiomics and clinical features in predicting treatment response for LARC in the validation set.

Figure 5

Nomogram based on the clinical characteristics and intratumor radiomics features in the prediction of response to neoadjuvant chemotherapy in locally advanced rectal cancer (LARC). (A) Nomogram based on clinical features and intratumor radiomics. (B) The calibration curve for intratumor radiomics and clinical features in predicting treatment response for LARC in the training set. (C) The calibration curve for intratumor radiomics and clinical features in predicting treatment response for LARC in the validation set.

Figure 6

ROC and nomogram based on the clinical characteristics and intra-peritumor radiomics features in the prediction of response to neoadjuvant chemotherapy in locally advanced rectal cancer (LARC). (A) The receiver operating characteristic curve (ROC) for different models in predicting treatment response for LARC in the training set.(B) The ROC for different models in predicting treatment response for LARC in the validation set. (C) Nomogram based on the clinical characteristics and combined-radiomics features in the prediction of response to neoadjuvant chemotherapy in locally advanced rectal cancer (LARC). (D, E) The calibration curve for the models in predicting treatment response for LARC in the training set and validation set.