While skin cancer is the most diagnosed form of cancer in menand women, with more cases diagnosed each year than all othercancers combined, sufficiently early diagnosis results in very goodprognosis and as such makes early detection crucial. While radiomicshave shown considerable promise as a powerful diagnostictool for significantly improving oncological diagnostic accuracy andefficiency, current radiomics-driven methods have largely rely onpre-defined, hand-crafted quantitative features, which can greatlylimit the ability to fully characterize unique cancer phenotype thatdistinguish it from healthy tissue. Recently, the notion of discoveryradiomics was introduced, where a large amount of custom, quantitativeradiomic features are directly discovered from the wealth ofreadily available medical imaging data. In this study, we presenta novel discovery radiomics framework for skin cancer detection,where we leverage novel deep multi-column radiomic sequencersfor high-throughput discovery and extraction of a large amount ofcustom radiomic features tailored for characterizing unique skincancer tissue phenotype. The discovered radiomic sequencer wastested against 9,152 biopsy-proven clinical images comprising ofdifferent skin cancers such as melanoma and basal cell carcinoma,and demonstrated sensitivity and specificity of 91% and 75%, respectively,thus achieving dermatologist-level performance andhence can be a powerful tool for assisting general practitionersand dermatologists alike in improving the efficiency, consistency,and accuracy of skin cancer diagnosis.
Skin cancer detection using non-invasive techniques
