Privacy risk assessment of AI models

31/03/2024.

The need to analyze personal data to drive business, alongside the requirement to preserve the privacy of data subjects, creates a known tension.

Generative AI for Specialized Dataset Enhancement and Expansion

30/03/2024.

An important challenge for applying machine and deep learning methods in applications where data collection is difficult, or costly is the reduced amount of annotated data.

Empowering HITers for Melanoma annotation tasks: Training and Selection Process

28/03/2024.

Precision and expertise are necessary to reach 100% quality in data annotation. The process of selecting image annotators, called HITers at isahit, for projects like iToBoS involves rigorous criteria to ensure the highest quality in final annotations.

Scaled Dot-Product Attention

27/03/2024.

Self-attention is the core mechanism behind Transformer models, which have provided state-of-the-art results in various scientific fields (i.e. Natural Language Processing).

AI in Digital Pathology

26/03/2024.

What benefits does AI offer digital pathologists? How can it revolutionize the field and what are its biggest challenges?

Tanorexia, another face of sun exposure

25/03/2024.

Tanorexia is the tanning dependence. It is a syndrome related to a physical or psychological dependence on sunbathing or using ultraviolet tanning beds.

Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

22/03/2024.

Large language models have achieved a good performance on different tasks and different data types. However, they often lack of content fidelity and new context creation. These features could help to generate images in a more personalized way.

Seeing is Believing: How AI might transform skin cancer education

20/03/2024.

The integration of digital technologies, e.g., smartphone apps, has been shown to represent an impactful advancement in training for melanoma diagnosis.1

Multi-Head Attention

19/03/2024.

Expanding the concept of Scaled Dot-Product Attention, Vaswani et al proposed the multi-head attention mechanism.

Conformal prediction in AI

16/03/2024.

Conformal prediction offers a solution in uncertainty quantification and simultaneously provides a method for instance classification.