Skin cancer, the most common human malignancy, is diagnosed mainly visually, with an initial clinical screening accompanied by dermoscopic diagnosis, a biopsy, and histopathological examination.Deep convolutional neural networks (CNNs) have shown promise in a variety of fine-grained object categories for general and highly variable tasks.This model shows how to classify skin lesions with a single CNN that was trained end-to-end from images and disease labels as inputs.Dataset of 129,450 clinical images was used in training the model.Model's performance is tested against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: malignant carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi.
Input variables : Skin Lesion Image
Output Variables : Malignant or benign skin cancer
Visit Model : github.com
Additional links : nature.com
| Model Category | : | Public |
| Date Published | : | January, 2017 |
| Healthcare Domain | : |
Medical Technology
Provider |
| Code | : | github.com |
| Health Risk Management |
| Disease Detection |