Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Optimizing immunotherapy in advanced gastric cancer: established and emerging biomarkers for precision patient selection.

Frontiers in immunology·2026
Same author

Efficacy, Safety, and Mechanism of the Qi-Lian-Xiao-Pi Prescription (WW-1) for Chronic Atrophic Gastritis After Helicobacter Pylori Eradication: Protocol for a Multicenter, Randomized, Double-Blind, Placebo-Controlled Trial.

JMIR research protocols·2026
Same author

Dynapenic Abdominal Obesity and the Risk of Non-Neoplastic Digestive System Diseases in Postmenopausal Women: A Prospective Cohort Study.

International journal of women's health·2026
Same author

Yi-Fei formula mitigates influenza virus NS1-induced macrophage dysfunction by activating the NF-κB signaling pathway.

Tissue & cell·2026
Same author

Immune-related core gene identification in irritable bowel syndrome and prediction of regulatory traditional Chinese medicines.

Medicine·2026
Same author

Miller Fisher syndrome: a case report and review of the literature.

Journal of medical case reports·2026

Related Experiment Video

Updated: Feb 28, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K

Multi-Phasic CECT Peritumoral Radiomics Predict Treatment Response to Bevacizumab-Based Chemotherapy in RAS-Mutated

Feiyan Jiao1, Yiming Liu2, Zhongshun Tang2

  • 1Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China.

Bioengineering (Basel, Switzerland)
|February 27, 2026
PubMed
Summary

Pre-treatment radiomic features from multi-phasic computed tomography scans can predict treatment resistance in colorectal liver metastases. Peritumoral and Laplacian of Gaussian filtered features showed the most predictive value for bevacizumab chemotherapy response.

Keywords:
bevacizumabcolorectal cancercomputed tomographymachine-learningmetastasisradiomicstreatment response prediction

More Related Videos

Detection of a Circulating MicroRNA Custom Panel in Patients with Metastatic Colorectal Cancer
08:12

Detection of a Circulating MicroRNA Custom Panel in Patients with Metastatic Colorectal Cancer

Published on: March 14, 2019

6.1K
Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
06:24

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

Published on: April 18, 2015

15.8K

Related Experiment Videos

Last Updated: Feb 28, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K
Detection of a Circulating MicroRNA Custom Panel in Patients with Metastatic Colorectal Cancer
08:12

Detection of a Circulating MicroRNA Custom Panel in Patients with Metastatic Colorectal Cancer

Published on: March 14, 2019

6.1K
Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
06:24

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

Published on: April 18, 2015

15.8K

Area of Science:

  • Radiology
  • Oncology
  • Medical Imaging

Background:

  • Colorectal liver metastases (CRLM) with RAS mutations often exhibit resistance to bevacizumab-based chemotherapy.
  • Predicting treatment response is crucial for optimizing patient management.

Purpose of the Study:

  • To investigate the predictive value of pre-treatment multi-phasic contrast-enhanced computed tomography (CECT) radiomic features for treatment resistance in RAS-mutated CRLMs.
  • To identify radiomic features that can differentiate responders from non-responders to bevacizumab-based chemotherapy.

Main Methods:

  • Seventy-three patients with RAS-mutated CRLMs receiving bevacizumab-based chemotherapy were analyzed.
  • Radiomic features were extracted from arterial phase (AP), portal venous phase (PVP), AP-PVP subtraction, and Delta phase (DeltaP) CECT images, focusing on peritumor, core tumor, and whole-tumor regions.
  • Feature selection was performed using Mann-Whitney U test, K-means clustering, and LASSO algorithm, followed by model development with six machine learning algorithms.

Main Results:

  • Peritumoral radiomic features and those from Laplacian of Gaussian (LoG) filtered images were dominant across machine learning algorithms.
  • Naive Bayes (NB) models achieved the best predictive performance, with an average testing AUC of 0.717.
  • Peritumoral and LoG-filtered features from multi-phasic CECT images were more predictive of treatment response than core tumor features.

Conclusions:

  • Pre-treatment multi-phasic CECT radiomic features, particularly peritumoral and LoG-filtered features, can predict treatment response in RAS-mutated CRLMs receiving bevacizumab-based chemotherapy.
  • These radiomic features offer a non-invasive method to assess potential treatment resistance before therapy initiation.
  • Further validation is warranted to integrate these findings into clinical practice for personalized treatment strategies.