Improving AI models with XAI

In the past years, Deep Neural Networks (DNNs) have shown exceptional results across multiple domains, including general image classification tasks, winning Atari games or even detecting skin cancer by lesion classification. These networks are commonly trained on large datasets, such as ImageNet (millions of images of several classes) or ISIC 2019 (images of skin lesions).

AI-Assisted diagnostic support

A manual examination of skin lesions with a dermatoscope is the current standard procedure and state of the art in dermatoscopy. This is a highly laborious process, often limited to a small selection of lesions which excludes registering the state of off-lesion skin regions.

Designing the whole imaging system

An introduction to building the blocks of the iToBoS solution: from fundamentals to camera testing. As we are designing the whole imaging system from scratch, many parameters regarding the imaging system of the total body scanner needed to be specified. 

Differential value of iToBoS

iToBoS tackles the limitations of currently available systems, by designing a novel tool that will help practitioners during the diagnostic process. The diagnosis for a given exploration will be enhanced with all the data available for the patient, including, but not being limited to, genomics, clinical history, previous dermoscopy, etc. The result will be a cognitive assistant that integrates information from several sources to provide a personalized diagnostic for each patient.

Introduction to iToBoS from the Leibniz University of Hannover

Leibniz University of Hannover (LUH) is located in Hannover in northern Germany Lower Saxony with about 30.000 students. LUH is part of a number of excellence clusters namely PhoenixD, hearing for all, rebirth, quantum frontiers. LUH is also part of several other European projects like ERC Grants, Horizon2020, EFRE- and ESF funded projects. As a part of that the LUH is a proud partner of the iToBoS EU- project.

No other interest can take precedence - a patient’s perspective on oncology drug development

My husband’s diagnosis with melanoma and our struggle to access effective therapy challenged what I had learnt about medical research. I have since founded a patient network, becoming avocal advocate for patient- centric drug development. Herein, I discuss some of the lessons I have learnt. 

Lumps and bumps

As we age, our skin acquires all sorts of mysterious lumps and bumps – some might be cancers, but most are benign. Here are some of the most common types that iToBoS will be learning to distinguish from melanoma. Article written by the Skin Cancer Genomics and Biomarker Discovery Group - Dermatology Research Centre - The University of Queensland Diamantina Institute.

From good to great: what patients can do for your medical research

Melanoma Patient Network Europe has a lot of experience in connecting researchers with patients, including organizing patient-led conferences. The group’s founder explains how productive interaction can be transformative to research.

The rise of privacy tech

When I started to work on privacy technologies at IBM Research almost 15 years ago, virtually no-one was talking about privacy or the rights of data subjects with regard to their data. There were a few academic conferences out there focused (at least partially) on privacy, but it was a very niche domain with little interest outside of the small community working on it directly.