Some of our datasets

VAIPE-Pill is a large dataset of pill images for automated pill identification. The dataset contains more than 50,000 pill images with annotations that are collected under real-world settings. To the best of our knowledge, the VAIPE-Pill is currently the largest pill image dataset for object detection tasks.

We introduce a large-scale dataset of prescriptions for visual-based clinical applications. It contains more than 50,000 images collected from multiple hospitals in Vietnam. To the best of our knowledge, this is the first and the largest dataset for understanding prescriptions from images in Vietnamese.

Tools and Services

MONAI is a freely available, community-supported, PyTorch-based framework for deep learning in healthcare imaging. It provides domain-optimized foundational capabilities for developing healthcare imaging training workflows in a native PyTorch paradigm. Project MONAI was originally started by NVIDIA & King’s College London to establish an inclusive community of AI researchers for the development and exchange of best practices for AI in healthcare imaging across academia and enterprise researchers.

napari is a community-built, Python-based, open-source tool for browsing, annotating, and analyzing large multi-dimensional images. It is built on inclusive, community-driven, and collaborative values and aims to serve scientific applications focused on visualization with simple, readable implementations. This framework is a fast, interactive, multi-dimensional image viewer for Python. napari is a collaboration across CZI, CZI grantees, the Chan Zuckerberg Biohub, and many other scientists and computational biologists who have contributed to its growth.

TorchIO is an open-source Python library for efficient loading, preprocessing, augmentation and patch-based sampling of 3D medical images in deep learning. It includes multiple intensity and spatial transforms for data augmentation and preprocessing. These transforms include typical computer vision operations such as random affine transformations and also domain-specific ones such as simulation of intensity artifacts due to MRI magnetic field inhomogeneity (bias) or k-space motion artifacts.