Develop and validate AI in existing patient processes for skin cancer

Computer Vision

Skin cancer is one of the most common cancers in Sweden. Nearly 4,500 cases of aggressive skin melanoma are detected annually, about 500 people die every year from the disease. Primary care has limited competence to diagnose melanoma, at the same time there is a shortage of dermatologists. This leads to long waiting times even though early detection of melanoma is the most important factor for survival.

Parts of the above needs and challenges can be handled using AI products as support for dermatologists in their diagnosis and this is exactly what the project intends to develop and validate. The product idea is to develop algorithms that handle multiple skin cancer diagnoses. These will then be implemented in a teledermatoscopic process and validated in clinical activities by dermatologists and research group at Skånes University Hospital. The project covers everything from initial requirements analysis, data analysis, image processing, algorithm development to APIs, user interface, testing and finally validation by dermatologists in the daily clinical work.

Photo: Dermicus 

Read more:

More projects

PLA bio-based plastics from secondary raw materials

The purpose of this project is to develop a techno-economically viable production route for PLA, Polylactic acid, from second generation raw materials such as side streams from the…



In this project we place the users of the product pass and their needs in the centre. The aim is to increase the insight regarding what product information that is relevant, for th…


AutoWEEEdakt II – Automatic AI based WEEE recognition system

In 2020, the EU recycled 4.7 million tons of electronic waste with a low collection rate. In the AutoWEEEdakt II project, we employ artificial intelligence to enhance sorting and i…