Radomics classification of colorectal cancer V2
Research type
Research Study
Full title
An integrated radiomics feature classification and genomics approach to define tumour aggressiveness in colorectal cancer
IRAS ID
202036
Contact name
Jamie Murphy
Contact email
Sponsor organisation
Imperial College Healthcare NHS Trust
Duration of Study in the UK
0 years, 9 months, 30 days
Research summary
In the UK alone colorectal cancer affects around 42,000 men and women each year and has poor outcome. Only about fifty-nine percentage of patients live beyond five years after diagnosis. Poor survival is linked to advanced disease stage at presentation, progressive spread of the disease to other parts of the body and frequent development of resistance to chemotherapy. Those patients who received curative treatment have high recurrent rates.
There are numerous scientifically interesting predictive/prognostic biomarkers have been identified, however, none are universally accepted for routine clinical use. It is against this background that we seek to develop a biomarker tool-kit based on the patient’s routine computed tomography and magnetic resonance imaging scans. The tool kit will be able to predict disease aggressiveness (stage and extent) ultimately for use within the multidisciplinary team setting in association with other metrics such as fitness of the patient.
An evolving mathematical feature extraction algorithm, radiomics, can be exploited to assess the manifestation of altered gene/protein expression in human tumours with a sensitivity greater than eight-fold that of the human eye. Radiomics refers to the conversion of biomedical images into mineable high-dimensional data. Biomedical images can be obtained with computed tomography, positron emission tomography or magnetic resonance imaging; we will use computer tomography and magnetic resonance imaging in this case.
Colorectal tumour tissue from same patients will undergo genomic sequencing. Clinical outcomes of the same patient cohort will be analysed to identify any correlation with radiomics study and genomic mutations.
REC name
HSC REC B
REC reference
16/NI/0187
Date of REC Opinion
31 Aug 2016
REC opinion
Favourable Opinion