With Watson, we can all make a difference.

 

Watson’s ability to learn from unstructured data means every bit of information helps – even social media posts. You can help increase Watson’s knowledge by sharing your story, particularly if you’ve been affected by melanoma.

Simply use the hashtag #outthinkmelanoma to post on social media any way you like (either through text or images), and Watson will do the rest.

See Australians all over the country who have already joined Watson in the fight against melanoma.

Watson is looking to learn about:

  • Your age
  • Location
  • Ethnicity
  • Any moles previously diagnosed as Melanoma
  • Any family history of melanoma
  • Any changes you’ve noticed in your moles or skin


Our partners

MoleMap

MoleMap partnership
IBM is partnering with MoleMap to advance innovation to help in the early detection of melanoma. MoleMap is the world's most advanced melanoma skin cancer detection program, designed to protect you and your family from the deadly effects of melanoma. 

With over 20 clinics in Australia, and no referral necessary, make a booking with MoleMap today.

Melanoma Institute partnership

Melanoma Institute Australia partnership
Melanoma Institute Australia is the world’s only research institute with a single focus on melanoma treatment and cure. It manages the largest melanoma research database in the world. We are proud to partner with MIA to help improve the early identification of melanoma in Australia.

To support Melanoma Institute Australia’s life changing research, get involved in Melanoma March.

IBM

How Watson is learning to identify melanoma

Watson is learning to use 6 key data points to analyse images and determine the probability of melanoma.

Colour

Watson analyses a skin mole and searches for the presence of any of the six suspicious colours, which range from tan to black. The more colours are identified, the higher the risk of melanoma.

Border irregularity

Watson divides skin moles into 8 regions, and assesses the irregularity of their borders and assigns them a score. A total score is then calculated for the entire mole. The higher the score, the higher the likelihood of melanoma.

Asymmetry level

Watson analyses the major and minor axes of a skin mole to determine whether it is fully symmetrical, half symmetrical or fully asymmetrical. The more asymetrical the mole, the higher the risk of melanoma.


Globule and network

Watson inspects the skin mole for the presence of any globular or network pattern, two patterns that are indicative of a potential melanoma, and calculates a percentage. The higher the percentage, the higher the risk.

Similar images

Watson searches the database for an image similar to the skin mole being analysed, and considers the prior diagnosis of this image.

Melanoma score

Watson scours through thousands of historical images in the database in a matter of seconds and uses an algorithm to assign a melanoma score to the skin mole being analysed. The higher the score, the higher the likelihood of melanoma.