Related Experiment Video
Updated: Jun 27, 2025
Non-Invasive PET/MR Imaging in an Orthotopic Mouse Model of Hepatocellular Carcinoma
Published on: August 31, 2022
The Diagnostic Accuracy Between Radiomics Model and Non-radiomics Model for Preoperative of Microvascular Invasion of
Junjiu Gou1, Jingqi Li1, Yingfeng Li1
1The Clinical Medical College, Guizhou Medical University, Guiyang 550004, Guizhou Province, China.
Non-radiomic methods showed better accuracy than radiomic methods for predicting microvascular invasion (MVI) in solitary hepatocellular carcinoma (HCC). However, significant study heterogeneity necessitates cautious interpretation of these findings for MVI detection.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
- Hepatocellular Carcinoma (HCC) Research
Background:
- Microvascular invasion (MVI) is a critical prognostic indicator in hepatocellular carcinoma (HCC).
- Accurate preoperative detection of MVI is essential for optimal treatment planning in solitary HCC.
- Existing predictive models for HCC can be enhanced by incorporating detailed tumor characteristics.
Purpose of the Study:
- To compare the diagnostic performance of radiomic and non-radiomic methods for detecting MVI in solitary HCC before surgery.
- To evaluate the accuracy of different predictive models in identifying MVI in HCC patients.
Main Methods:
- A systematic review and meta-analysis of studies published until April 7, 2023, from major databases (PubMed, Embase, Web of Science, Cochrane Library).
- Calculation of pooled sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) using random-effects models.
- Assessment of diagnostic accuracy via summary receiver-operating characteristic (SROC) curves and area under the curve (AUC); meta-regression and subgroup analyses were conducted.
Main Results:
- The meta-analysis included 26 studies with 3539 patients with solitary HCC.
- Non-radiomic models demonstrated a higher AUC (0.88) compared to radiomic models (0.85), with non-radiomic models showing higher specificity (0.88) versus radiomic models (0.78).
- Subgroup analyses indicated higher accuracy for preoperative MRI, larger tumors, and functional imaging compared to preoperative CT, smaller tumors, and conventional imaging.
Conclusions:
- Non-radiomic methods exhibited superior performance over radiomic methods in the preoperative detection of MVI in solitary HCC.
- Significant heterogeneity was observed across the included studies, warranting careful interpretation of the results.
- Further research may be needed to standardize methodologies and reduce heterogeneity for more robust conclusions.
More Related Videos
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018