Gastroenterology and Artificial Intelligence: 3rd Annual Artificial Intelligence Summit (On-Demand) | September 2021-2-Computer Vision in Medicine

2-Computer Vision in Medicine_Bhotika

Pdf Summary

The document discusses the use of computer vision and health artificial intelligence (AI) services provided by Amazon Web Services (AWS). It covers the various services and capabilities offered by AWS in the field of AI and machine learning. The document also emphasizes the importance of building models for specific tasks as a domain expert, instead of requiring expertise in machine learning. It mentions the use of multimodal representations to handle different types of data in healthcare.<br /><br />Some of the specific services mentioned include Amazon Rekognition for facial recognition and analysis, Amazon Textract for extracting text and structure from documents, and Amazon Lookout for Vision for automated quality inspection. The document highlights the benefits of these services, such as their ease of use and the ability to work with limited amounts of training data.<br /><br />The document also discusses the concept of the "long tail" of computer vision problems, where each use case may require specialized training data. It introduces the concept of using customer feedback to improve models, reducing the need for extensive labeling efforts. It also mentions the use of AI for mining unstructured healthcare data, such as medical notes and images.<br /><br />Overall, the document presents an overview of the services and capabilities provided by AWS in the domains of computer vision and health AI, emphasizing the ease of use and the ability for domain experts to leverage these technologies without extensive machine learning expertise.

Keywords

computer vision

health artificial intelligence

Amazon Web Services

AWS

AI services

machine learning

multimodal representations

Amazon Rekognition

Amazon Textract

Amazon Lookout for Vision