Related Experiment Video
Updated: Oct 7, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
7.0K
Extendable and explainable deep learning for pan-cancer radiogenomics research.
1Department of Biochemistry and Medical Genetics, University of Manitoba, Winnipeg, Manitoba, R3E 0W3, Canada; Department of Computer Science, University of Manitoba, Winnipeg, Manitoba, R3E 0W3, Canada; Department of Statistics, University of Manitoba, Winnipeg, Manitoba, R3E 0W3, Canada.
Current Opinion in Chemical Biology
|January 9, 2022
Summary
Deep learning advances radiogenomics by analyzing medical images and genomic data for non-invasive biomarkers. This review explores deep learning
Area of Science:
- Integrative oncology and medical imaging analysis.
- Application of artificial intelligence in precision medicine.
Background:
- Radiogenomics links medical imaging phenotypes with genomic features.
- Identifying non-invasive imaging biomarkers is crucial for clinical decision-making.
- Deep learning offers advanced computational methods for complex data analysis.
Purpose of the Study:
- To review the current applications of deep learning in pan-cancer radiogenomic research.
- To discuss the limitations and future directions of deep learning in this field.
- To summarize key radiogenomic research resources and traditional machine learning approaches.
Main Methods:
- Review of existing literature on deep learning in radiogenomics.
- Analysis of traditional machine learning techniques in radiomics and genomics.
- Identification and summary of pan-cancer radiogenomic research resources.
Main Results:
- Deep learning shows significant potential in analyzing integrated imaging and genomic data.
- Key characteristics of deep learning, extendibility and explainability, are highlighted.
- Traditional machine learning methods in radiogenomics are also briefly covered.
Conclusions:
- Deep learning is a powerful tool for advancing pan-cancer radiogenomic research.
- Further research is needed to address limitations and enhance explainability.
- The integration of deep learning holds promise for discovering novel imaging biomarkers.
