Related Experiment Video
Updated: Jun 23, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Deep learning in cancer genomics and histopathology
Michaela Unger1, Jakob Nikolas Kather2,3,4
1Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany. michaela.unger@tu-dresden.de.
Deep learning (DL) offers new ways to analyze cancer histopathology and genomic data, improving precision oncology. Researchers must be aware of DL model biases and limitations for reliable healthcare applications.
Area of Science:
- Oncology
- Computational Biology
- Pathology
Background:
- Precision oncology relies on histopathology and genomic profiling for cancer patient care.
- Traditional analysis involves manual slide review and computational pipelines for genomic data.
- Artificial intelligence, particularly machine learning (ML) and deep learning (DL), presents novel data analysis approaches.
Purpose of the Study:
- To review current and emerging applications of deep learning (DL) in cancer histopathology and genomics.
- To explore DL's potential in basic diagnostic and advanced prognostic tasks.
- To discuss the implications of DL for future oncology workflows and research.
Main Methods:
- Review of existing literature on deep learning applications in cancer pathology and genomics.
- Analysis of studies detailing diagnostic and prognostic tasks using DL.
- Examination of evidence regarding the impact of DL on cancer research and clinical workflows.
Main Results:
- Deep learning (DL) shows significant potential to augment and potentially replace traditional methods in analyzing histopathology slides and genomic data.
- DL applications span basic diagnostic functions to advanced prognostic predictions in oncology.
- Evidence suggests DL can form the basis for novel workflows in cancer research and clinical practice.
Conclusions:
- Deep learning (DL) is poised to revolutionize cancer research and precision oncology by extracting deeper insights from histopathology and genomic data.
- Awareness and mitigation of biases and flaws within DL models are crucial for their safe and effective implementation in healthcare.
- Addressing DL limitations is essential for establishing trust and ensuring the responsible advancement of AI in oncology.
More Related Videos
Related Concept Videos
Cancer
Cancers Originate from Somatic Mutations in a Single Cell
Tumor Progression
Colon cancer is one of the best-documented examples of tumor progression. Early mutation in the APC gene in colon cells causes a small growth on the colon wall called a polyp. With time, this polyp grows into a benign, pre-cancerous tumor. Further...
Cancer-Critical Genes II: Tumor Suppressor Genes
When the function of certain critical genes, especially those involved in cell cycle regulation and cell growth signaling cascades, gets disrupted, it upsets the cell cycle progression. Such cells with unchecked cell cycles start proliferating uncontrollably and eventually develop into tumors.
Such genes that act...
Cancers Originate from Somatic Mutations in a Single Cell
Cancer-Critical Genes II: Tumor Suppressor Genes
When the function of certain critical genes, especially those involved in cell cycle regulation and cell growth signaling cascades, gets disrupted, it upsets the cell cycle progression. Such cells with unchecked cell cycles start proliferating uncontrollably and eventually develop into tumors.
Such genes that act...

