AI Case Study
Stanford University trained deep neural networks to predict skin carcinomas from images with the same accuracy as determatologists
Stanford University researchers trained a Convolutional Neural Network (CNN) model on 130 thousand images of skin cancer. The model was tested against 21 board certified dermatologists and its performance was at the same level. The researchers imagine this model becoming a mobile app to extend diagnosis to millions who do not have access to clinics.
Public And Social Sector
Education And Academia
"Deep convolutional neural networks show potential for general and highly variable tasks across many fine-grained object categories... we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs... train a CNN using a dataset of 129,450 clinical images—two orders of magnitude larger than previous datasets—consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi."
The computer performed on par with the dermatologists.
"...the algorithm went head-to-head against 21 board-certified dermatologists. The doctors reviewed hundreds of images of skin lesions, and for each one, determined whether they would conduct further tests on it or assure the patient that it was benign. The algorithm reviewed the same images and gave its diagnoses. Neither the doctors nor the algorithm had seen the images previously. The computer performed on par with the experts. For example, the program was able to distinguish between keratinocyte carcinomas—the most common human skin cancer—and benign skin growths called seborrheic keratoses."
"Stanford built its deep learning algorithm on the architecture of the GoogleNet Inception v3, a convolutional neural network algorithm. Such programs are structured in interconnected layers that are inspired, at a high level, by the way neurons in the brain work."
R And D
Core Research And Development
"Skin cancer, the most common human malignancy is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions.":
"Inception v3 was trained on 1.28 million images from the 2014 ImageNet Large Scale Visual Recognition Challenge, a contest that aimed to improve a computer’s ability to detect and classify objects in images. Stanford researchers then fine-tuned the algorithm with a set of nearly 130,000 images of skin lesions from more than 2000 diseases—the largest dataset used for automated skin cancer classification."