Amazon Rekognition, a code-free automated machine learning (AutoML) service from Amazon Web Services (AWS), showed impeccable diagnostic performance in categorizing various retinal diseases using optical coherence tomography (OCT) scans. This blog post details the steps to use Amazon Rekognition Custom Labels to train a model that categorizes retinal diseases and the process of training and fine-tuning convolutional neural networks (CNNs), the standard deep learning methodology.
At the end of 2022, Northwestern University’s Kellogg School of Management had a decision to make. The on-premises SQL server used by faculty and students had reached the end of its life, and the school needed to identify a cost-effective way forward while ensuring that the datasets would remain highly available for researchers to use on demand. After weighing various options, Kellogg worked with Amazon Web Services (AWS) to create a data lake that fit its unique needs.
To improve safety and convenience, transportation agencies amass a substantial volume of data. However, these organizations encounter challenges in data accuracy validation due to issues related to data quality and occasional missing information. With the incorporation of new artificial intelligence and machine learning capabilities from Amazon Web Services (AWS), they can take advantage of no-code solutions to identify and address data gaps.
This quarter, AWS released 34 new or updated datasets on the Register of Open Data. What will you build with these datasets? Read through this blog post for inspiration.
This quarter, AWS released 36 new or updated datasets. As July 16 is Artificial Intelligence (AI) Appreciation Day, the AWS Open Data team is highlighting three unique datasets that are analysis-ready for AI. What will you build with these datasets?
The National Institute on Aging Genetics of Alzheimer’s Disease Data Storage Site (NIAGADS DSS), powered by AWS, is a genomic database that provides access to publicly available datasets for Alzheimer’s disease and related neuropathologies. Created to make Alzheimers-genetics knowledge more accessible to researchers, NIAGADS has genomics data on 172,701 samples from 98 datasets and is now 1.3 petabytes (PB) in total size. NIAGADS is creating a system that promotes scientific discovery through data sharing with a large cadre of institutions.
The NYUMets team, led by Dr. Eric Oermann at NYU Langone Medical Center, is collaborating with AWS Open Data, NVIDIA, and Medical Open Network for Artificial Intelligence (MONAI), to develop an open science approach to support researchers to help as many patients with metastatic cancer as possible. With support from the AWS Open Data Sponsorship Program, the NYUMets: Brain dataset is now openly available at no cost to researchers around the world.
Advances in technology are transforming the way health research can be conducted. It is now possible to integrate data from siloed sources into a data lake, a central repository where health data are aggregated and analyzed at scale. Now, more than ever, there are opportunities for collaborative research to accelerate life-saving medical innovation – and that’s exactly what JDRF International, the leading global Type 1 Diabetes research and advocacy organization, is doing with AWS.
Security is priority number one at AWS. Data stored in Amazon Simple Storage Service (Amazon S3) is private by default. However, some datasets are made to be shared. In this blog post, we cover the no-cost mechanisms data providers can utilize to create access control policies for their highly distributed open datasets.
Companies and asset managers looking to protect their financial investments from climate change-related risks, and invest in more sustainable solutions, can now access a new dataset on the Amazon Web Services (AWS) Cloud to help inform their decision making. Amazon announced that the Legal Entity Identifier (LEI) dataset is now available and free for anyone to access in the cloud. The dataset includes key reference information that supports clear and unique identification of legal entities participating in financial transactions, and each LEI contains information about an entity’s ownership structure, including ‘who is who’ and ‘who owns whom’.