Sahlgrenska Hospital, Region Halland and AI Sweden have decided to lead an effort of applying Federated Learning in practice. For this use case we made use of the SIIM-ISIC 2020 dataset and performed two main tasks. First, melanoma detection, and second, skin lesion image generation.
The main area of interest of the project is research on explainable and interpretable motion prediction approaches of road users in highly interactive scenarios using NuScenes dataset.
Based on our investigation, we propose a self-normalization module in the U2-Net. The improved model, called Self-Normalized Density Map (SNDM), can correct its output density map by itself to accurately predict the total number of microbial colonies in the Petri dish image.
The use of healthcare data in the development of DL models is associated with challenges relating to personal data and regulatory issues. Patient data cannot be freely shared and is therefore limited in its usefulness for creating AI solutions. All of these issues can be addressed using different methods, showing the potential of artificial data for such use cases.
Neural networks can be applied to distinguish between melanoma and non-melanoma cases in a few seconds, which makes it a great help to the diagnosing physician.
The two-stage detector for litter localization and classification is presented, namely, EfficientDet-D2 is used to localize litter, and EfficientNet-B2 to classify the detected waste into seven categories.
We compared the performance of three well-known deep learning approaches for object detection on the AGAR dataset, namely two-stage, one-stage, and transformer-based neural networks.
We introduce an effective strategy to generate an annotated synthetic dataset of microbiological images of Petri dishes that can be used to train deep learning models in a fully supervised fashion.