Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer

Abstract

Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, on post-treatment images, this association is influenced by treatment efficacy and varies between responders and non-responders. This study introduces a novel model, called baseline-referenced Delta radiomics, which integrates the association between radiomic features and tumor size into Delta radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) and colorectal cancer (CRC). Materials and Methods: A retrospective study analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients and 84 CRC patients. Among these, 57 BC patients with 106 liver lesions and 37 CRC patients with 109 lesions underwent post-treatment imaging after systemic chemotherapy. Radiomic features were extracted from up to three lesions per patient following manual segmentation. Tumor response was assessed by measuring the longest diameter and classified according to RECIST 1.1 criteria as progressive disease (PD), partial response (PR), or stable disease (SD). Classification models were developed to predict chemotherapy response using pretreatment data only, Delta radiomics, and baseline-referenced Delta radiomics. Model performance was evaluated using confusion matrix metrics. Results: Baseline-referenced Delta radiomics performed comparably or better than established radiomics models in predicting tumor response in chemotherapy-treated patients with liver metastases. The sensitivity, specificity, and balanced accuracy in predicting response ranged from 0.66 to 0.97, 0.81 to 0.97, and 80% to 90%, respectively. Conclusions: By integrating the relationship between radiomic features and tumor size into Delta radiomics, baseline-referenced Delta radiomics offers a promising approach for predicting chemotherapy response in liver metastases from breast and colorectal cancer.

Keywords: Delta radiomics; RECIST 1.1; chemotherapy; computer tomography; liver; metastases; radiomics; response assessment.

Figure 1

Pipeline of this study.

Figure 2

Flowcharts illustrate the construction of the datasets.

Figure 3

Scatter plot demonstration of association between radiomic features and the tumor size. The red line represents the fitted result.

Figure 4

Confusion matrices for pretreatment radiomics, Delta radiomics, and functional radiomics response assessment models computed for patients with liver metastasis from (top) colorectal cancer and (bottom) breast cancer.

Figure 5

Receiver operating characteristic (ROC) curves for predicting chemotherapy response in liver metastases from colorectal cancer (left) and breast cancer (right) using pretreatment radiomics, Delta radiomics, and baseline-referenced Delta radiomics.

Figure 6

Feature significance for pretreatment radiomics, Delta radiomics, and baseline-referenced Delta radiomics response assessment models computed for patients with liver metastasis from (top) colorectal cancer and (bottom) breast cancer.

Figure 7

Change in the value of the three most significant features (Figure 5) for Delta radiomics and baseline-referenced Delta radiomics response assessment models computed for patients with liver metastasis from (top) colorectal cancer and (bottom) breast cancer.

Figure 8

Changes in the value of radiomic features from (top) Delta radiomics and (bottom) baseline-referenced Delta radiomics models in patients with liver metastasis from colorectal cancer treated with chemotherapy alone or chemotherapy in combination with bevacizumab.