Using Machine Learning To Diagnose Diabetes
Using Machine Learning to Diagnose Diabetes Using Machine Learning to Diagnose Diabetes Using deep learning, we created a machine learning solution for diagnosing diabetic retinopathy. Sep. 07, 15 Big Data Zone Hortonworks Sandbox for HDP and HDF is your chance to get started on learning, developing, testing and trying out new features. Each download comes preconfigured with interactive tutorials, sample data and developments from the Apache community. What is the difference between these two images? The one on the left has no signs of diabetic retinopathy, while the other one has severe signs of it. If you are not a trained clinician, the chances are, you will find it quite hard to correctly identify the signs of this disease. So, how well can a computer program do it? In July, we took part in a Kaggle competition, where the goal was to classify the severity of diabetic retinopathy in the supplied images of retinas. As weve learned from the organizers, this is a very important task. Diabetic retinopathy is the leading cause of blindness in the working-age population of the developed world. It is estimated to affect over 93 million people. The contest started in February, and over 650 teams took part in it, fighting for the prize pool of $100,000. The contestants were given over 35,000 images of retinas, each having a severity rating. There were 5 severity classes, and the distribution of classes was fairly imbalanced. Most of the images showed no signs of the disease. Only a few percent had the two most severe ratings. The metric with which the predictions were rated was a quadratic weighted kappa, which we will describe later. The contest lasted till the end of July. Our team scored 0.82854 in the private standing, which gave us 6th place. Not too bad, given our quit Continue reading >>
Google's Ai Reads Retinas To Prevent Blindness In Diabetics
Google's artificial intelligence can play the ancient game of Go better than any human. It can identify faces, recognize spoken words, and pull answers to your questions from the web. But the promise is that this same kind of technology will soon handle far more serious work than playing games and feeding smartphone apps. One day, it could help care for the human body. Demonstrating this promise, Google researchers have worked with doctors to develop an AI that can automatically identify diabetic retinopathy, a leading cause blindness among adults. Using deep learning—the same breed of AI that identifies faces, animals, and objects in pictures uploaded to Google's online services—the system detects the condition by examining retinal photos. In a recent study, it succeeded at about the same rate as human opthamologists, according to a paper published today in the Journal of the American Medical Association. "We were able to take something core to Google—classifying cats and dogs and faces—and apply it to another sort of problem," says Lily Peng, the physician and biomedical engineer who oversees the project at Google. But the idea behind this AI isn't to replace doctors. Blindness is often preventable if diabetic retinopathy is caught early. The hope is that the technology can screen far more people for the condition than doctors could on their own, particularly in countries where healthcare is limited, says Peng. The project began, she says, when a Google researcher realized that doctors in his native India were struggling to screen all the locals that needed to be screened. In many places, doctors are already using photos to diagnose the condition without seeing patients in person. "This is a well validated technology that can bring screening services to remote Continue reading >>
Deep-learning Based, Automated Segmentation Of Macular Edema In Optical Coherence Tomography
Deep-learning based, automated segmentation of macular edema in optical coherence tomography 1Department of Ophthalmology, University of Washington, Seattle, Washington, USA 2Department of Ophthalmology, Puget Sound Veteran Affairs, Seattle Washington, USA 4eScience Institute, University of Washington, Seattle, Washington, USA 1Department of Ophthalmology, University of Washington, Seattle, Washington, USA 2Department of Ophthalmology, Puget Sound Veteran Affairs, Seattle Washington, USA 3University of Washington School of Medicine, Seattle, Washington, USA 4eScience Institute, University of Washington, Seattle, Washington, USA Received 2017 May 1; Revised 2017 Jun 17; Accepted 2017 Jun 20. Copyright 2017 Optical Society of America This article has been cited by other articles in PMC. Evaluation of clinical images is essential for diagnosis in many specialties. Therefore the development of computer vision algorithms to help analyze biomedical images will be important. In ophthalmology, optical coherence tomography (OCT) is critical for managing retinal conditions. We developed a convolutional neural network (CNN) that detects intraretinal fluid (IRF) on OCT in a manner indistinguishable from clinicians. Using 1,289 OCT images, the CNN segmented images with a 0.911 cross-validated Dice coefficient, compared with segmentations by experts. Additionally, the agreement between experts and between experts and CNN were similar. Our results reveal that CNN can be trained to perform automated segmentations of clinically relevant image features. OCIS codes: (150.1135) Algorithms, (110.4500) Optical coherence tomography Over the past decade there has been increased interest in deep learning, a promising class of machine learning models that utilizes multiple neural network layers Continue reading >>
Tensorflow Dev Summit
Jeff Dean, Rajat Monga, and Megan Kacholia Jeff Dean, Rajat Monga, and Megan Kacholia deliver the keynote address at the inaugural TensorFlow Dev Summit. They discuss: - Progress since TensorFlows open-source launch - TensorFlows thriving open-source community - TensorFlow applications around the world ... and share some exciting announcements! Speed is everything for effective machine learning, and XLA was developed to reduce training and inference time. In this talk, Chris Leary and Todd Wang describe how TensorFlow can make use of XLA, JIT, AOT, and other compilation techniques to minimize execution time and maximize computing resources. Join Dandelion Mane in this talk as they demonstrate all the amazing things you can do with TensorBoard. You'll learn how to visualize your TensorFlow graphs, monitor training performance, and explore how your models represent your data. TensorFlow allows you to define models using both low- as well as high-level abstractions. In this talk, Martin Wicke will introduce Layers, Estimators, and Canned Estimators for defining models, and show the roadmap for their availability in core TensorFlow. Integrating Keras & TensorFlow: The Keras Workflow, Expanded Keras has the goal to make deep learning accessible to everyone, and it's one of the fastest growing machine learning frameworks. Join Francois Chollet, the primary author of Keras, as he demonstrates how Keras can be used in Tensorflow through a video QA example. In this talk, Daniel Visentin from the DeepMind Applied team talks about DeepMind and TensorFlow. He'll explain the importance of choosing a platform, the team's choice to migrate to TensorFlow, and give a number of examples of how DeepMind uses TensorFlow. Join Brett Kuprel, and see how TensorFlow was used by the artificial
Learn Data Science By Doing Kaggle Competitions: Diabetic Retinopathy Detection
Learn Data Science by Doing Kaggle Competitions: Diabetic Retinopathy Detection We're in room 1530, Canadian Pacific Lecture Room. There is a hard upper limit of 44 people in that room. That is probably just about enough to hold us, but you might want to get there early to be sure to get a spot. We meet every two weeks to learn more about data science by discussing Kaggle competitions ( ). If you want to get better at data wrangling, feature engineering, model selection or just want to have fun solving non-trivial data science problems, this is the right group to join! This time we are discussing the Diabetic Retinopathy Detection ( ) competition. Tyler has kindly agreed to take us through the competition and has promised to update it by throwing some TensorFlow at it. To get the most out of the meetup, please try to look at the competition beforehand. It's OK if you don't understand it all. The meetup is for questions and discussion. At the end of the meeting we will discuss which competitions we want to look at for future meetups. Bring your suggestions! ~7:45 Pick the next competition, then off to a nearby restaurant for food, drinks, and breakout discussion Continue reading >>
Detecting Diabetic Eye Disease With Machine Learning
Detecting diabetic eye disease with machine learning {[drawerToggle.open ? 'Hide Related Articles' : 'Show Related Articles']} Diabetic retinopathy an eye condition that affects people with diabetes is the fastest growing cause of blindness, with nearly 415 million diabetic patients at risk worldwide. The disease can be treated if detected early, but if not, it can lead to irreversible blindness. One of the most common ways to detect diabetic eye disease is to have a specialist examine pictures of the back of the eye and determine whether there are signs of the disease, and if so, how severe it is. While annual screening is recommended for all patients with diabetes, many people live in areas without easy access to specialist care. That means millions of people arent getting the care they need to prevent loss of vision. A few years ago, a Google research team began studying whether machine learning could be used to screen for diabetic retinopathy (DR). Today, in the Journal of the American Medical Association , weve published our results: a deep learning algorithm capable of interpreting signs of DR in retinal photographs, potentially helping doctors screen more patients, especially in underserved communities with limited resources. Examples of retinal photographs that are taken to screen for DR. A healthy retina can be seen on the left; the retina on the right has lesions, which are indicative of bleeding and fluid leakage in the eye. Working with a team of doctors in India and the U.S., we created a dataset of 128,000 images and used them to train a deep neural network to detect diabetic retinopathy. We then compared our algorithms performance to another set of images examined by a panel of board-certified ophthalmologists. Our algorithm performs on par with the opht Continue reading >>
Github - Javathunderman/diabetic-retinopathy-screening: Diabetic Retinopathy Screening W/ Tensorflow.
Diabetic retinopathy screening w/ Tensorflow. If nothing happens, download GitHub Desktop and try again. If nothing happens, download GitHub Desktop and try again. If nothing happens, download Xcode and try again. If nothing happens, download the GitHub extension for Visual Studio and try again. Diabetic retinopathy screening w/ Tensorflow Diabetic retinopathy is one of the leading causes of blindness in the the world and affects up to 40% of diabetic patients, with nearly 100 million cases worldwide as of 2010. However, with proper detection and treatment, the effects of diabetic retinopathy can be properly addressed. For people who are diabetic but are unable to visit an optometrist, due to lack of proper healthcare infrastructure, diagnosing this dangerous condition is often difficult, costly, and time consuming. Additionally, offering a way to more quickly detect diabetic retinopathy in a primary care setting would save time and money as well. Using the freely available machine learning software library Tensorflow, this experiment aims to allow a computerized, preliminary detection based on the retinal image of a patient's eye. This Tensorflow-based implementation uses convolutional neural networks to take a retinal image, analyze it, and learn the characteristics of an eye that shows signs of diabetic retinopathy in order to detect this condition in a primary care setting. Images from Kaggle's Diabetic Retinopathy detection challenge: . A smaller, curated version is available at Note: This is not to be used in any situation other than software testing. This should not be used in any medical circumstances. We are not responsible for any damage that occurs with use of this project. We also have a version of this program to run on the web, and on a desktop. Find them Continue reading >>
Github - Amanrana20/diabetic_retinopathy_detection: Code For The Kaggle Challenge: Diabetic Retinopathy Detection (tensorflow)
data: This folder contains the following folders train: This folder contains the training images. There are 300 RGB images of the original dataset. test: This folder contains the testing images. There are 180 RGB images of the original dataset. trainLabels.csv: This file cotains labels for all the training images. The code for this project is contined within the two files: run.py: This python file is the starting point of the code. It processes the images and uses a custom generator to create batches of any desired size and calls the model.py file for training the model model.py: This file contains code for creation of the Convolutional Neural Network (CNN) model and training based on the training batch passed by run.py file. Note: Since my laptop is not very powerful and I have installed tensorflow usinf conda (no GPU support via anaconda), I have used a small subset of the original dataset for training. I am uploading an even smaller subset of the original kaggle dataset. The original dataset can be downloaded here Continue reading >>
Deep Learning For Detection Of Diabetic Eye Disease
Posted by Lily Peng MD PhD, Product Manager and Varun Gulshan PhD, Research Engineer Diabetic retinopathy (DR) is the fastest growing cause of blindness, with nearly 415 million diabetic patients at risk worldwide. If caught early, the disease can be treated; if not, it can lead to irreversible blindness. Unfortunately, medical specialists capable of detecting the disease are not available in many parts of the world where diabetes is prevalent. We believe that Machine Learning can help doctors identify patients in need, particularly among underserved populations. A few years ago, several of us began wondering if there was a way Google technologies could improve the DR screening process, specifically by taking advantage of recent advances in Machine Learning and Computer Vision. In "Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs", published today in JAMA, we present a deep learning algorithm capable of interpreting signs of DR in retinal photographs, potentially helping doctors screen more patients in settings with limited resources. One of the most common ways to detect diabetic eye disease is to have a specialist examine pictures of the back of the eye (Figure 1) and rate them for disease presence and severity. Severity is determined by the type of lesions present (e.g. microaneurysms, hemorrhages, hard exudates, etc), which are indicative of bleeding and fluid leakage in the eye. Interpreting these photographs requires specialized training, and in many regions of the world there aren’t enough qualified graders to screen everyone who is at risk. Working closely with doctors both in India and the US, we created a development dataset of 128,000 images which were each evaluated by 3-7 ophthalmo Continue reading >>
Googles Ai Program For Diabetic Retinopathy Now In Indian Hospitals
Googles AI program for diabetic retinopathy now in Indian hospitals AIM has talked about Googles new research in machine learning and how it helps in early detection of diabetic retinopathy. Led by Google Brain AI research group, this research will soon start reaping results at hospitals across I ndia . At a recent conference, Google executives revealed the work has already begun on integrating the technology into a chain of eye hospitals in India. Google researchers had worked closely with doctors in India and the US to create a development dataset of 128,000 images which were each evaluated by 3-7 ophthalmologists from a panel of 54 ophthalmologists. This dataset was used to train a deep neural network to detect referable diabetic retinopathy Over 100,000 people subscribe to our newsletter. See stories of Analytics and AI in your inbox. According to Lily Peng, product manager at Google Brain AI research, India is one of the many places around the world where a lack of ophthalmologists means many diabetics dont get the recommended annual screening for diabetic retinopathy. Automated DR screening methods with high accuracy have the strong potential to assist doctors in evaluating more patients and quickly routing those who need help to a specialist. Over the last few years, Google has been working with doctors and clinicians to explore faster treatment of diabetic retinopathy. To fast track detection, Google Research and these issues of limited time and diagnostic variability, researchers have built an automated detection algorithm that can naturally complement pathologists workflow. In a blog , Google explains the algorithm has been designed to be highly sensitive to make it easier for pathologists to find even small instances of breast cancer metastasis in lymph node Continue reading >>
How To Get Started With The Diabetic Retinopathy Project
Head guy at @nomikxyz. Community Leader at @duckduckhack. How to get started with the Diabetic Retinopathy project A few months ago, I decided to begin work on my first machine learning project using Tensorflow, a powerful machine learning framework created by Google. Tensorflow, the uberamazing software package. (Courtesy of the Tensorflow website) What resulted was the Diabetic Retinopathy screening project , which can take a retinal image, run it through an algorithm, and give you a pretty good idea if an eye is showing signs of diabetic retinopathy , an ocular disease that manifests as a result of diabetes, and is one of the leading causes of blindness. A retinal image, much like the ones used in thisproject. In this post, I will walk you through a tutorial on what each file in the project does, and how to use it. All of the code in this project is written in Python, so make sure you know the basics of Python and Tensorflow before attempting this tutorial. Disclaimer: This project and software should not be used in a real world scenario. I am not a physician, and this is not going to definitively tell you whether you have an ocular disease. Dont be stupid, and dont trust your wellbeing or someone elses wellbeing in a random computer program you found online. Also, if you want to try out the algorithm behind this project without all the Python and stuff behind it, I would recommend you check out the retinopathy-server or retinopathy-desktop repositories, as they are much easier to use and require very minimal knowledge of Python. This is a gross oversimplification of how Tensorflow and machine learning works. If you want to know this works in detail, I suggest the Tensorflow for Poets tutorial by Google, which is available here: . The algorithm and files contained i Continue reading >>
Diabetic Retinopathy Detection Through Integration Of Deep Learning Classification Framework
choose from suggestions on the right-side panel publish any web site on the fly in 1-click (bookmarklet) How to grow my audience and develop my traffic? Publishing quality and relevant content you curate on a regular basis will develop your online visibility and traffic. Learn more and get all the tips to boost your topics views Sharing your scoops to your social media accounts is a must to distribute your curated content. Not only will it drive traffic and leads through your content, but it will help show your expertise with your followers. Branding your topics will give more credibility to your content, position you as a professional expert and generate conversions and leads. How to integrate my topics' content to my website? Integrating your curated content to your website or blog will allow you to increase your website visitors engagement, boost SEO and acquire new visitors. By redirecting your social media traffic to your website, Scoop.it will also help you generate more qualified traffic and leads from your curation work. Save time by spreading curation tasks among your team. How can I send a newsletter from my topic? Distributing your curated content through a newsletter is a great way to nurture and engage your email subscribers will developing your traffic and visibility. Creating engaging newsletters with your curated content is really easy. You dont want your Scoop.it page to be public: make it private. You can decide to make it visible only to you or to a restricted audience. We'll suggest content based on your keywords Continue reading >>
Google Working With Aravind Eye Hospital To Train Its Ai In Diabetic Retinopathy Screening
Indias largest eye care provider, Aravind Eye Hospital, has been quietly working for over four years with Google on a project to use artificial intelligence (AI) in ophthalmology. Aravind Eye Hospital, which has branches across India, is headquartered in Madurai, Tamil Nadu. Lily Peng, product manager at Google, who released a paper on the research a year ago, said at the 2017 WIRED Business Conference that Google had just finished a clinical study in India, and that work was underway to get the technology into routine use with patients. India, considered the diabetes capital of the world, has over 70 million diabetes patients who are at risk of blindness due to the disease. Indias largest eye care provider, Aravind Eye Hospital, has been quietly working for over three to four years with Google on a project to use artificial intelligence in ophthalmology At the TensorFlow Dev Summit earlier this year, Peng had said that that Googles machine learning algorithm was very close to an ophthalmologist in terms of performance. This particular project came in around four years ago; then we started looking at how we could develop it, said Dr R Kim, chief medical officer at Aravind Eye Hospital. He said that the hospital has been working on an automated diabetic retinopathy screening since 2003. Its not a fully automated system, it doesnt use AI. Its a semi-automated technology for DR (diabetic retinopathy) screening, he said. According to Dr Kim, Googles AI is far superior to anything he has ever seen in DR screening. With AI, we will be able to grade diabetic retinopathy to a certain level of identification, mainly for screening Dr R Kim, chief medical officer at Aravind Eye Hospital With AI, we will be able to grade diabetic retinopathy to a certain level of identification, m Continue reading >>
What Happened At The Tensorflow Dev Summit 2017 - Part 1/3: Community & Applications
What happened at the Tensorflow Dev Summit 2017 - Part 1/3: Community & Applications On February 15th 2017, Tensorflow , a software framework for artificial neural networks, version 1.0 was released at the Googles TensorFlow Dev Summit in Mountain View, California. During the event, there were presentations and announcements in four different areas of the project: Community, Applications, Deployment Strategies, Tools & Technology. The event was live streamed, and all the videos are available online . With these series of posts, I will highlight what were the most interesting parts and give practical, hands-on advice on the topics covered during the event. The legendary Jeff Dean kicked off the summit by telling us the story of the project. Tensorflow is not the first attempt of the Google Brain team to create a general Machine Learning framework. The previously closed source project was called DistBelief . Tensorflow was open sourced in November of 2015 and from its public release, there has been an impressive adoption internally in Google and by the community. In little more than a year, the open source Github repository became the number one in the machine learning category with over 44 thousand stars, 500 programmers developed and submitted their software with around a thousands commits per month, and 5,500 independent repositories, with the name Tensorflow in them, are now present on Github. Major universities have started teaching Machine Learning using TensorFlow. Many companies also embraced the project. IBM, Movidius , and Qualcomm are working with Google to fully support hardware acceleration of Tensorflow for their platforms. Travis Lanier from Qualcomm showcased the 8x performances of tensorflows InceptionV3 model running on the Hexagon DSP compared to runni Continue reading >>
Detecting Diabetic Retinopathy In Eye Images
The past almost four months I have been competing in a Kaggle competition about diabetic retinopathy grading based on high-resolution eye images. In this post I try to reconstruct my progression through the competition; the challenges I had, the things I tried, what worked and what didn’t. This is not meant as a complete documentation but, nevertheless, some more concrete examples can be found at the end and certainly in the code. In the end I finished fifth of the almost 700 competing teams. Update 02/08/2015: Code and models (with parameters) added. Introduction Introduction Diabetic retinopathy (DR) is the leading cause of blindness in the working-age population of the developed world and is estimated to affect over 93 million people. (From the competition description where some more background information can be found.) The grading process consists of recognising very fine details, such as microaneurysms, to some bigger features, such as exudates, and sometimes their position relative to each other on images of the eye. (This is not an exhaustive list, you can look at, for example, the long list of criteria used in the UK to grade DR (pdf).) Some annotated examples from the literature to get an idea of what this really looks like (the medical details/terminology are not very important for the rest of this post): Example of non-proliferative diabetic retinopathy (NPDR): Thin arrows: hard exudates; Thick arrow: blot intra-retinal hemorrhage; Triangle: microaneurysm. (Click on image for source.) Now let’s look at it as someone who simply wants to try to model this problem. You have 35126 images in the training set that look like this annotated by a patient id and “left” or “right” (each patient has two images, one per eye) and divided into 5 fairly unbalanc Continue reading >>
