Premium
A clinical‐radiomic model for improved prognostication of surgical candidates with colorectal liver metastases
Author(s) -
Shur Joshua,
Orton Matthew,
Connor Ashton,
Fischer Sandra,
Moulton CarolAnne,
Gallinger Steven,
Koh DowMu,
Jhaveri Kartik S.
Publication year - 2020
Publication title -
journal of surgical oncology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.201
H-Index - 111
eISSN - 1096-9098
pISSN - 0022-4790
DOI - 10.1002/jso.25783
Subject(s) - medicine , proportional hazards model , magnetic resonance imaging , hazard ratio , colorectal cancer , radiology , multivariate analysis , retrospective cohort study , pathological , oncology , cancer , confidence interval
Background and Objectives Colorectal cancer with liver metastases is potentially curable with surgical resection however clinical prognostic factors can insufficiently stratify patients. This study aims to assess whether radiomic features are prognostic and can inform clinical decision making. Methods This single‐site retrospective study included 102 patients who underwent colorectal liver metastases resection with preoperative computed tomography (CT), magnetic resonance imaging (MRI) with gadoxetic acid (EOB) and clinical covariates. A lasso‐regularized multivariate Cox proportional hazards model was applied to 114 features (10 clinical, 104 radiomic) to determine association with disease‐free survival (DFS). A prognostic index was derived using the significant Cox regression coefficients and their corresponding input features and a threshold was determined to classify patients into high‐ and low‐risk groups, and DFS compared using log‐rank tests. Results Four covariates were significantly associated with DFS; bilobar disease (hazard ratio [HR]= 1.56; P = .0043), complete pathological response (HR= 0.67; P = .025), minimum pixel value (HR= 1.66; P = .00016), and small area emphasis (HR= 0.62; P = .0013) from the EOB‐MRI data. Radiomic CT features were not prognostic. The prognostic index strongly stratified high‐ and low‐risk prognostic groups (HR = 0.31; P = .00068). Conclusion Radiomic MRI features provided meaningful prognostic information above clinical covariates alone. This merits further validation for potential clinical implementation to inform management.