Analysis of the Relationship between Image and Blood Examinations in an Artificial Intelligence System for the Molecular Diagnosis of Breast Cancer

• DOI: 10.4236/ojapps.2021.119074
• Publication Date: 2021-09-16T06:10:09Z
• Authors: Natsumi Wada; Maoko Nakashima; Yoshikazu Uchiyama
• Keywords: 03 medical and health sciences; 0302 clinical medicine; 3. Good health

Molecular subtype classification based on tumor genotype has recently been used for differential diagnosis of breast cancer. The shift from conventional tissue to molecular genetics-based is primarily because objective genetic information can ensure a biologically clear system and patient groups may be created given set diagnoses suitable treatments. Given the stressful nature biopsy, radiomic studies are conducted determine cancer subtypes using non-invasive imaging tests. Minimally invasive blood tests microRNAs (miRNAs) contained in exosomes have developed. We investigated usefulness features miRNAs distinguishing triple-negative (TNBC) other types. Fat suppression T2-weighted magnetic resonance images 60 cases (9 TNBC 51 others) were retrieved Cancer Genome Atlas Breast Invasive Carcinoma. Six six selected by least absolute shrinkage selection operator. Linear discriminant analysis was employed distinguish between others. With miRNAs, others completely separated, whereas with features, overlapped types Receiver operating characteristic curve results showed that area under 0.85 1.0, respectively. higher discrimination performance than features. Although gene expensive facilities performing it limited, useful artificial intelligence systems