Stanford in the news today with another deep-learning breakthrough in cancer diagnostics: Deep learning algorithm diagnoses skin cancer as well as seasoned dermatologists
First, the impressive results:
The final product, the subject of a paper in the Jan. 25 issue of Nature, was tested against 21 board-certified dermatologists. In its diagnoses of skin lesions, which represented the most common and deadliest skin cancers, the algorithm matched the performance of dermatologists.
Interestingly enough, the training dataset was built from pictures on the internet. Most approached we've seen to date use specialist-generated inputs.
Together, this interdisciplinary team worked to classify the hodgepodge of internet images. Many of these, unlike those taken by medical professionals, were varied in terms of angle, zoom and lighting. In the end, they amassed about 130,000 images of skin lesions representing over 2,000 different diseases.
However, they switched to expert data for the testing phase
During testing, the researchers used only high-quality, biopsy-confirmed images provided by the University of Edinburgh and the International Skin Imaging Collaboration Project that represented the most common and deadliest skin cancers – malignant carcinomas and malignant melanomas.
Following on the heels of Google's December Paper on Deep Learning for Detection of Diabetic Eye Disease we are finally seeing Deep Learning jump from theoretical applications to real-world proven applications. This is the first of many more breakthroughs to come.