To explore the value of preoperative CT image omics features in predicting posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC) and to establish an image omics nomogram for predicting PHLF.

Clinical data of 51 HCC patients who underwent hemihepatectomy in the First Affiliated Hospital of Sun Yat-sen University from September 2014 to October 2017 were retrospectively analyzed. The informed consents of all patients were obtained and the local ethical committee approval was received. Among them, 44 patients were male and 7 female, aged (48±12) years on average. All patients underwent enhanced CT scan before operation and the HCC CT-imaging features were extracted by A.K. software. The image omics features and clinical variables related to the occurrence of PHLF were screened by univariate Logistic regression, and were included in multivariate analysis to obtain the independent risk factors for the occurrence of PHLF. The nomogram for predicting PHLF in HCC patients was established according to the independent risk factors.

Low intensity small area emphasis (LISAE) and albumin-bilirubin (ALBI) score were the independent factors affecting the occurrence of PHLF (OR=27.93, 15.53; P<0.05). The area under the curve for predicting PHLF by LISAE combined with ALBI score was 0.883, significantly larger than the 0.700 of single ALBI score (Z=-2.460, P<0.05). Nomogram for predicting PHLF in HCC patients was successfully established. The corrected consistency index (C-index) was 0.863. The standard curve was well fitted with the calibrated predictive curve, and the predicted value was highly consistent with the observed value.

LISAE is an independent factor affecting the occurrence of PHLF in HCC patients, which can improve the predictive value of clinical variable ALBI score. The nomogram for predicting PHLF yields high predictive value for PHLF in HCC patients.