MoleCheck live demo
The same model that powers the MoleCheck app, running in your browser. Your photo is analyzed on your device — it is never uploaded, and this site has no server to send it to.
Before you try it — this is not a medical test.
- This is an educational demonstration of image classification. It cannot diagnose skin cancer or any other condition.
- A "lower-risk" result is not reassurance. The model misses roughly 1 in 10 malignant lesions on held-out test data, and real-world photos are harder than the research images it trained on.
- If a mole is new, changing, bleeding, or worrying you in any way, see a dermatologist — regardless of what this page says.
Drop a close-up photo of a single mole here,
or click to choose one
Whatever the score: this tool cannot see what a dermatologist sees. If you're concerned about this mole, get it examined in person.
What happens to my photo?
Nothing leaves your browser. The model (a 21 MB neural network) is downloaded to your device once, and the analysis runs locally via WebAssembly. You can disconnect from the internet after the page loads and it will still work.
Tips for a meaningful result
- One mole per photo, centered and in focus, filling most of the frame.
- Good, even lighting; no shadows across the lesion.
- The model was trained on dermatoscope images, so casual phone photos are outside its comfort zone — treat the score as a rough signal only.