Model Dermatology with RCNN
Check status...

Drop image here
or click to upload.
This is an experimental DEMO for detection malignancy using unprocessed photographs. The submitted image will be transferred, but we do not store the image. It will take 1~2 seconds to upload an image and additional 3~10 seconds to analyze one image.

Instruction and Warning
1. We strongly recommend to use high resolution images over 3000x2000 pixels.
2. Please test with two macro (extreme close-up) and two close-up (distance enough to fill face in the frame) images with different angles. Select the final value as the highest value among the results of four photographs.
3. The secondary changes of the lesion (i.e. laser surgery, curretage) may be a cause of false positive.
4. The diagnostic performance made with images alone was inferior to that of actual practice.

Build 2021 was trained using over 10 million image crops. For the blob detector, yolov5 was used. The algorithm was developed and maintained by Han Seung Seog from I Dermatology Clinic.