Data collection for machine learning
Research type
Research Study
Full title
Developing the MARIA® breast imaging system through the collection of data to inform machine learning; a prospective study
IRAS ID
280213
Contact name
Caroline Gillett
Contact email
Sponsor organisation
Micrima Ltd
Clinicaltrials.gov Identifier
Duration of Study in the UK
1 years, 0 months, 0 days
Research summary
The MARIA® breast imaging system uses radio waves to form an image of the breast. The scanning unit is housed under a couch and does not use ionising radiation or compression to create the image. This study is intending to collect data which will be used later to help train the MARIA® system, a process known as 'machine learning'. It is hoped that machine learning will enhance the features of MARIA® by enabling the system to tell the difference between lesions that are cancer and lesions that are benign (non-cancerous). It is also hoped that in the future MARIA® may be able to provide a breast density measurement by recognising the density of breast tissue in a scan image. This study will be open for a recruitment period of up to 12 months. Patients from a breast assessment clinic or a symptomatic clinic who meet the criteria for the study will be approached and invited to participate. If they agree, they will be consented into the study and the scan procedure performed. The scan procedure itself will take about 5 minutes and both breasts will be scanned, where possible. Once this is complete, they will be able to fill out a participant questionnaire of their experience, but this is not compulsory. There are no further visits although information on the participant will be collected subsequently, including information from their medical record on any biopsies, surgery and final diagnosis.
REC name
South West - Frenchay Research Ethics Committee
REC reference
21/SW/0075
Date of REC Opinion
19 Oct 2021
REC opinion
Further Information Favourable Opinion