First online AI Privacy course

Privacy and Compliance for AI has been the topic of a few of our recent blog posts. It is a field that is well known and studied in the academic arena, but still relatively new in the industrial world.

3rd Newsletter of iToBoS project

The third issue of the iToBoS newsletter was released!

The presence of iToBoS on social networks

iToBoS project is constantly active, not only in the development of the total body scanner and the Artificial Intelligence (AI) system, but also attending conferences, presenting the project in specialized congresses, conferences, or publishing scientific articles, among others. Different information and approaches to interest many types of audiences.

The SaMD (software as medical device) framework

The new regulatory framework for AI / ML-enabled SaMDs is driven by two main concepts.

Medical Regulations in USA for software and artificial intelligence

It is not clear the allocation in U.S.A. of Clinical Decision Support systems into the category of SaMD (software as medical device).

Using machine learning for assessing melanoma risk based on genetic data

The natural progression of a disease depends on genetic inheritance-susceptibility of an individual and several environmental factors. The human genome contains millions of genetic variants (single nucleotide polymorphisms-SNPs).

A new objective skin colour scale for research and clinical practice

A collaboration of scientists from the UK, USA, Australia, and France have proposed a more objective and detailed way to describe the huge variety of skin colour, called the Eumelanin Human Skin Colour Scale (EHSCS) and measured with a simple colourimeter.

Requirements for AI education for medical professionals

The complexity and volume of data in healthcare and increased demands for personalised care means that artificial intelligence (AI) will be increasingly incorporated into medical workflows.

Convolutional Neural Network (CNN)

CNN or ConvNet is a type of ANN that has been widely used to analyse images and sound signals. MLP is not suited to image and sound signals because the trainable parameters are large.

Neural Network based approaches for non-contact dermoscopy: a brief primer

Continuing our blog with introduction to machine learning for iToBoS, we present here a general overview of neural networks. Starting from basic definitions of important concepts, we will give a primer as meant for beginner. We keep discussions only to various types of neural networks. The functionality is also elucidated here.