Related Experiment Video
Updated: Jan 10, 2026
08:25
Detection of Cell-Free DNA in Blood Plasma Samples of Cancer Patients
Published on: September 9, 2020
11.7K
From multi-omics to deep learning: advances in cfDNA-based liquid biopsy for multi-cancer screening.
Xinwei Luo1, Sijia Xie1, Feitong Hong1
1Department of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
Biomarker Research
|November 28, 2025
Summary
Early cancer detection is crucial for survival. Liquid biopsy using circulating cell-free DNA (cfDNA) analysis offers a non-invasive method, with machine learning enhancing its diagnostic power for improved cancer monitoring.
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Cancer mortality necessitates improved early detection methods.
- Traditional diagnostics like biopsies are invasive and costly.
- Liquid biopsy using circulating cell-free DNA (cfDNA) presents a non-invasive alternative.
Purpose of the Study:
- To review key cfDNA biomarkers for cancer detection and monitoring.
- To highlight the role of multi-modal cfDNA analysis and machine learning (ML).
- To discuss challenges and future directions in cfDNA-based diagnostics.
Main Methods:
- Review of existing literature on cfDNA biomarkers (mutations, CNVs, methylation, fragmentation, EMs).
- Analysis of feature fusion approaches for enhanced cancer classification.
- Evaluation of machine learning (ML) and deep learning (DL) applications in cfDNA analysis.
Main Results:
- Multi-modal cfDNA biomarkers improve cancer detection and monitoring reliability.
- ML and DL models show strong predictive performance in liquid biopsy.
- Feature fusion stabilizes low-abundance signals, enhancing diagnostic accuracy.
Conclusions:
- cfDNA analysis integrated with ML holds significant promise for non-invasive cancer diagnostics.
- Future work should focus on multi-modal integration, explainable AI (XAI), and cost-effectiveness.
- Advancements aim for earlier diagnosis, accurate prognosis, and personalized cancer treatment strategies.
