EfficientNetV2: Smaller Models & Faster Training

EfficientNet was first proposed in the original paper of Mingxing Tan & Quoc V Le in 2019, namely EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.

Exploiting EfficientNet Models: A powerful tool for skin lesion diagnosis

iToBoS is exploring the use of EfficientNet models for pigmented skin lesion classification. This family of models, developed by Google researchers, are deep learning architectures that offer exceptional performance.

Creation of a test dataset for automatic lesion detection

Test datasets serve as a benchmark to evaluate the performance of algorithms and models.

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

I-JEPA [1], the latest self-supervised model from Meta AI, has been officially released: the paper was published in June 2023 at the last CVPR conference, together with their codes that they made open-source.

Spacing of healthy moles hints at site-specific melanoma risk

Naevi (moles) are benign brown or black spots on your skin that sometimes look similar to melanomas, but are completely harmless.

Performance of the gravity-compensated liquid lenses

In two previous blog posts, we explained the coma aberration effect that gravity introduced on the standard liquid lenses from Optotune and how it has been solved in the latest generation of the lenses.

Visual Intelligence for Manufacturing

The experience gained from the use of machine vision technology has allowed Bosch to master the skills to support iToBoS project objectives.

Australasian College of Dermatologists Position Statement on AI in Australian Dermatology Practice

Artificial intelligence has been a buzzword in medicine for some years, but it is only slowly becoming a practical reality in dermatology, with many ethical and practical considerations to iron out first.

iToBoS XAI Workshop

The iToBoS consortium conducted an explainable AI (xAI) workshop at the project’s 6th General Assembly meeting, hosted by Bosch Manufacturing Solutions facility, in Madrid in October 2023.

Solutions for the data economy of tomorrow-creating a secure, trusted environment for handling medical data

Bilbao hosted the technology-focused Tech-X Conference of the Gaia-X initiative, which was co-organized with a Hackathon.