Radiomics diagnosed histopathological growth pattern in prediction of response and 1-year progression free survival for colorectal liver metastases patients treated with bevacizumab containing chemotherapy

• Published in: European journal of radiology Vol. 142; p. 109863
• Main Authors: Wei, Shengcai, Han, Yuqi, Zeng, Hanjiang, Ye, Shuai, Cheng, Jin, Chai, Fan, Wei, Jingwei, Zhang, Jianwei, Hong, Nan, Bao, Yudi, Zhou, Jing, Ye, Yingjiang, Meng, Xiaochun, Zhou, Yuwen, Deng, Yanhong, Qiu, Meng, Tian, Jie, Wang, Yi
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.09.2021
• Subjects: Bevacizumab; Colorectal liver metastases; Histopathologic growth pattern; Radiomics; Unresectable; Unresectable; Colorectal liver metastases; Histopathologic growth pattern; Radiomics; Bevacizumab
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2021.109863

To investigate the capability of a radiomics model, which was designed to identify histopathologic growth pattern (HGP) of colorectal liver metastases (CRLMs) based on contrast-enhanced multidetector computed tomography (ceMDCT), to predict early response and 1-year progression free survival (PFS) in patients treated with bevacizumab-containing chemotherapy. Patients with unresectable CRLMs who were treated with bevacizumab-containing chemotherapy were included in this multicenter retrospective study. For each target lesion, the radiomics-diagnosed HGP (RAD_HGP) of desmoplastic (D) pattern or replacement (R) pattern was determined. Logistic regression and receiver operating characteristic (ROC) curves were used to assess lesion- and patient-based responses according to morphologic response criteria. One-year PFS was calculated using Kaplan-Meier curves. Hazard ratios for 1-year PFS were obtained through Cox proportional hazard regression analysis. Among 119 study patients, 206 D pattern and 140 R pattern lesions were identified. In patients with multiple lesions, 52 had D pattern, 31 had R pattern, and 36 had mixed (D + R) pattern. The area under the curve value for RAD_HGP in predicting early response was 0.707 for lesion-based analysis and 0.720 for patient-based analysis. Patients with D pattern had a significantly longer PFS than patients with R pattern or mixed pattern (P < 0.001). RAD_HGP was the only independent predictor of 1-year PFS. HGP diagnosed using a radiomics model could be used as an effective predictor of PFS for patients with CRLMs treated with bevacizumab-containing chemotherapy.