Diagnosis of Medical Imaging

Extracting insights and detecting anomalies from X-rays, CAT scans, MRIs, and other testing modalities (e.g. retinal scanning). Those anomalies could be used for early diagnosis of possible diseases like Cancer, Pneumonia, COVID-19, Diabetes, and more

ROI Examples

Reduce Diagnosis of Brain Tumors from 40 minutes to 3 minutes
AI model trained to find metastasized breast cancer tumors was able to detect 92.4% of the tumors, compared to the human pathologist average of 73.2%
Mammography Screenings: Radiologists’ accuracy increased from 75.3% to 84.8% when they used AI

Data Needed

Understand the Use-case under 5 minutes

Video (4.5 minutes)

Integrating AI into the Radiologist Workflow

A brief explanation for how AI for Medical Imaging works, how it’s used by radiologists, and how it integrates with existing medical health solution

Video (6 minutes)

This AI is Beating Doctors At their own game

Researchers at Stanford University are developing an AI model that can screen X-rays for pneumonia and other diseases, a task that’s usually done by radiologists

Get to know more Business and Technical details about the use-case (15-30 minutes)

Deeper Intro

More detailed introduction covering business and technical aspects

Article (20 minutes)

The Current State of Artificial Intelligence in Medical Imaging and Nuclear Medicine

Brief about the need for AI in medical imaging, current applications, challenges, and key players

Video (15 minutes)

AI in Radiology at Stanford: Rise of the Machines

Orientation of the state of AI today in Radiology, what it can and can’t do, with different examples and elaboration on opportunities, challenges, and some work Stanford are doing

Video (20 minutes)

Imaging AI in Practice - Work with AI

Step by Step guide from RSNA (Radiological Society of North America) for how Radiologists could be working with AI, with a live demonstration for AI solutions

Business Focused

Case studies, Organizational Aspects, Return on Investment examples

Article and Video (40 minutes)

Radiology Experts discuss the Business Case for AI at Leading Medical Centers

Radiology experts share AI use cases from getting up and running to improving patient outcomes, lessons learned, & discuss the influence that radiology has across the care continuum

White Paper (25 minutes)

Medical Imaging in the Age of Artificial Intelligence

Paper by Siemens Helthineers. Exploring the Clinical value of applying AI in Medical Imaging, sets a Framework for adopting AI workflows, and sheds some light on the economic benefits expected

Case Study

Artificial intelligence rivals radiologists in screening X-rays for certain diseases

A new algorithm developed by Stanford researchers can read X-rays for 14 different pathologies and is performing as well as radiologists in most cases.

Tech focused

More details on the technical aspects of the use-case

Video (6.5 minutes)

Building AI with Clara Toolkits for Medical Imaging

Quick explanation and demo for applying AI to medical imaging for organ segmentation using Nvidia’s solution: Clara. Demos show labeling, training, applying transfer learning to pre-trained models, deploying to production, and model usage via an API

Video (11 minutes)

Machine Learning For Medical Image Analysis - How It Works

Provides a simple and intuitive explanation for how Convolutional Neural Networks - the main technique used with medical imaging analysis - works

Video (21 minutes)

Deep Learning in medical imaging – Ben Glocker, Imperial College London

Sharing some successes and challenges applying Deep Learning in analyzing Medical Imagery, specifically in: Brain Lesions, Foetal Imaging, and Cardiac Analysis

Technical resources that will help you implement the use-case (notebooks, tutorials..)

Configurable Solution

NVIDIA Clara Imaging: Models, Tools, Environment, Configured Solution

Publicly available tools from Nvidia (including pre-trained models and configurable solution) for AI medical imaging workflows

Visit

Github Repo

Project InnerEye - Democratizing Medical Imaging AI

This is a deep learning toolbox to train models on medical images (or more generally, 3D images). It integrates seamlessly with cloud computing in Azure.

Visit

Deep Learning for Medical Imaging & Healthcare | NanoNets

Book

Deep Learning in Medical Image Analysis

Presents cutting-edge research and applications of deep learning in a broad range of medical imaging scenarios, such as computer-aided diagnosis, image segmentation, tissue recognition and classification, & others

Visit

Github Repo

CheXNet Implementation. End to End ML Pipeline including utilities & tools

Utilities and Tools implementing CheXNet solution developed by Stanford (14 chest diseases). The repo shows end to end ML pipeline for data processing, model training, deployment, and usage

Visit

Data Sets you can use to build Demos, POCs, or test Algorithms

OASIS-1

MRI images used for Alzheimer's disease diagnosis which consists of a cross-sectional collection of 416 subjects aged 18 to 96

ChestX-ray14

Contains 112,120 frontal-view X-ray images of 30,805 unique patients, images annotated with up to 14 different thoracic pathology labels

Diabetic Retinopathy Dataset

Large set of high-resolution retina images taken under a variety of imaging conditions, dataset separated into 5 files represents the degree of presence of diabetic retinopathy

Off-the-Shelf Products using AI for Diagnosis of Medical Imaging

Got a Question or a Resource to share with the Community? Please do!

Diagnosis of Medical Imaging

1. Get Inspired

Integrating AI into the Radiologist Workflow

This AI is Beating Doctors At their own game

2. Know More

Deeper Intro

The Current State of Artificial Intelligence in Medical Imaging and Nuclear Medicine

AI in Radiology at Stanford: Rise of the Machines

Imaging AI in Practice - Work with AI

Business Focused

Radiology Experts discuss the Business Case for AI at Leading Medical Centers

Medical Imaging in the Age of Artificial Intelligence

Artificial intelligence rivals radiologists in screening X-rays for certain diseases

Tech focused

Building AI with Clara Toolkits for Medical Imaging

Machine Learning For Medical Image Analysis - How It Works

Deep Learning in medical imaging – Ben Glocker, Imperial College London

3. Do

NVIDIA Clara Imaging: Models, Tools, Environment, Configured Solution

Project InnerEye - Democratizing Medical Imaging AI

Deep Learning in Medical Image Analysis

CheXNet Implementation. End to End ML Pipeline including utilities & tools

Data Sets

OASIS-1

ChestX-ray14

Diabetic Retinopathy Dataset

Solutions