JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Radiomics Beyond Radiology: Literature Review on Prediction of Future Liver Remnant Volume and Function Before Hepatic Surgery

  • 0Department of Life Sciences, Health and Health Professions, Link Campus University, 00165 Rome, Italy.
Journal of Clinical Medicine +

|

August 14, 2025

|

August 14, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Radiomics models show promise for predicting post-hepatectomy liver failure (PHLF) and future liver remnant (FLR) before major liver surgery. Further validation in larger cohorts is needed for clinical integration.

Area Of Science

  • Radiology
  • Oncology
  • Artificial Intelligence

Background

  • Post-hepatectomy liver failure (PHLF) is a critical complication after liver resection, significantly impacting patient mortality.
  • Accurate prediction of PHLF and assessment of future liver remnant (FLR) are vital for surgical planning and patient outcomes.
  • Current methods for FLR assessment and PHLF prediction face limitations, necessitating advanced predictive tools.

Purpose Of The Study

  • To review current CT-based radiomics and artificial intelligence approaches for surgical risk stratification in liver resection.
  • To identify limitations hindering the clinical translation of these predictive models.
  • To assess the potential of radiomics and deep learning in predicting PHLF and FLR.

Main Methods

  • A comprehensive literature analysis was conducted using the PubMed Dataset.
  • Keywords included "Artificial intelligence," "radiomics," "machine learning," "deep learning," "neural network," "texture analysis," "liver resection," and "CT."
  • Reviewed articles focused on the prediction of PHLF and FLR using machine learning (ML) and deep learning (DL) algorithms.

Main Results

  • 153 relevant papers were identified, with a focus on studies predicting PHLF and FLR.
  • Machine learning and deep learning models were developed using automated algorithms.
  • Radiomics models demonstrated potential in integrating imaging and clinical data for predictive purposes.

Conclusions

  • Radiomics models appear reliable for preoperative prediction of PHLF and FLR in patients undergoing major liver surgery.
  • These models show applicability in clinical practice for surgical risk stratification.
  • Larger validation cohorts are essential to further confirm the reliability and generalizability of these findings.

Keywords: