A biomarker is a characteristic that can be objectively detected and evaluated and can be used as an indicator of normal biological processes, pathological processes, or pharmacological responses to therapeutic interventions. In the clinical aspect, biomarkers a vital role in the early diagnosis and classification of diseases, the judgement of the extent of disease, the inspection of treatment effects, and the prevention of diseases. With the development of image algorithms and artificial intelligence, the automatic identification and classification of biomarkers have made great progress, and they have been widely used in the research of biomarker detection.
Traditional biomarker detection methods based on manual experimental methods are complicated, inefficient, and expensive. With the widespread application of sequencing technology and digital imaging technology in biomarker detection, digital multi-omics data and medical images can be quickly and massively acquired, providing the possibility for the system to detect the characterization and pathological causes of disease biomarkers as well as a data basis for algorithm-based automated biomarker detection. It is particularly important to integrate multi-omics data and medical images and to design algorithms that can efficiently identify biomarkers so as to find more valuable biomarkers, and ultimately provide research foundations for researchers and doctors by systematic combination of both these new technologies and traditional biotechnology systems.
This Research Topic welcomes the latest findings of both Original Research and Review articles on novel feature extraction and feature selection algorithms for machine learning and deep learning models based on medical imaging (Magnetic resonance imaging, X-ray, CT, PET and SPECT, Ultrasound imaging, Functional imaging, Optical imaging, microscopy and infrared imaging, Dermatological imaging) and/or Omics (Genome, Transcriptome, Epigenome, Proteome, Metabolome) data. The authors need to release the tools of their algorithms, so that the readers may easily utilize their algorithms on other datasets. Integrated biomarker detection algorithms using both imaging and Omic data are highly preferred. For article submissions to Frontiers in Genetics - Computational Genomics, "studies focused on comparative transcriptomic analysis, re-analysis of existing genomic or transcriptomic data to identify a disease biomarker, and descriptive studies that merely define gene families and expression profiles will not be considered for review, unless they are extended to provide meaningful insights into gene/protein function and/or the biology of the subject described. Studies relating to the prediction of clinical outcome require some validation of findings."
Topic Editors Jie Li and Feng Liu hold patents related to the Research Topic subject. All other Topic Editors declare no competing interests.
A biomarker is a characteristic that can be objectively detected and evaluated and can be used as an indicator of normal biological processes, pathological processes, or pharmacological responses to therapeutic interventions. In the clinical aspect, biomarkers a vital role in the early diagnosis and classification of diseases, the judgement of the extent of disease, the inspection of treatment effects, and the prevention of diseases. With the development of image algorithms and artificial intelligence, the automatic identification and classification of biomarkers have made great progress, and they have been widely used in the research of biomarker detection.
Traditional biomarker detection methods based on manual experimental methods are complicated, inefficient, and expensive. With the widespread application of sequencing technology and digital imaging technology in biomarker detection, digital multi-omics data and medical images can be quickly and massively acquired, providing the possibility for the system to detect the characterization and pathological causes of disease biomarkers as well as a data basis for algorithm-based automated biomarker detection. It is particularly important to integrate multi-omics data and medical images and to design algorithms that can efficiently identify biomarkers so as to find more valuable biomarkers, and ultimately provide research foundations for researchers and doctors by systematic combination of both these new technologies and traditional biotechnology systems.
This Research Topic welcomes the latest findings of both Original Research and Review articles on novel feature extraction and feature selection algorithms for machine learning and deep learning models based on medical imaging (Magnetic resonance imaging, X-ray, CT, PET and SPECT, Ultrasound imaging, Functional imaging, Optical imaging, microscopy and infrared imaging, Dermatological imaging) and/or Omics (Genome, Transcriptome, Epigenome, Proteome, Metabolome) data. The authors need to release the tools of their algorithms, so that the readers may easily utilize their algorithms on other datasets. Integrated biomarker detection algorithms using both imaging and Omic data are highly preferred. For article submissions to Frontiers in Genetics - Computational Genomics, "studies focused on comparative transcriptomic analysis, re-analysis of existing genomic or transcriptomic data to identify a disease biomarker, and descriptive studies that merely define gene families and expression profiles will not be considered for review, unless they are extended to provide meaningful insights into gene/protein function and/or the biology of the subject described. Studies relating to the prediction of clinical outcome require some validation of findings."
Topic Editors Jie Li and Feng Liu hold patents related to the Research Topic subject. All other Topic Editors declare no competing interests.