Type:
Educational Exhibit
Keywords:
Artificial Intelligence, MR, Computer Applications-Detection, diagnosis, Cancer
Authors:
M. D. Patel, V. Sawlani; Birmingham/UK
DOI:
10.26044/ecr2019/C-2005
Background
Phenotypic information is routinely being extracted through imaging non-invasively which can be used for precision medicine.2 It is critically important that radiologists lead this artificial intelligence (AI) revolution.
They have developed clinical skills and experience through generations of accumulated knowledge.
Clinically useful,
predictive radiomic properties must be clearly linked to meaningful biologic characteristics and qualitative imaging properties familiar to radiologists.
Radiomics and radiogenomics incorporates several important disciplines,
including radiology (imaging interpretation),
computer vision (quantitative feature extraction) and machine learning (classifier evaluation).3
Radiomics has shown the potential to allow extraction of detailed tumour phenotypic information,
genetics,
expression patterns and functional information from radiological images,
and use these as prognostic and predictive markers.4 Although the radiomic analyses define correlations with the population,
once tested,
the result can be translated to clinical use and applied to individual patients.2 Machine and deep learning-based radiomics has already shown positive results in non-invasive:
- Accuracy of cancer diagnosis
- Tumour grade assessment
- Mutation or subtype status assessment
- Prognosis inference
- Prediction of treatment response
- Disease monitoring,
through longitudinal variations in features (delta-radiomics),
assessed by repeated scans during the course of treatment
Not only does radiomics greatly enhance decision support of precision medicine for patients,
but also permits healthcare cost reductions as radiological images are already available for most patients in oncology and it could reduce the need for costly,
risky and invasive biopsy in some cases.5 Radiomics has been studied in mainly oncology,
however it is potentially applicable to all diseases.2