Using 3D Convolutional Neural Networks with Visual Insights for Classification of Lung Nodules and Early Detection of Lung Cancer

schedule Aug 8th 03:30 - 04:15 PM place Grand Ball Room 1

Lung cancer is the leading cause of cancer death among both men and women in the U.S., with more than a hundred thousand deaths every year. The five-year survival rate is only 17%; however, early detection of malignant lung nodules significantly improves the chances of survival and prognosis.

This study aims to show that 3D Convolutional Neural Networks (CNNs) which use the full 3D nature of the input data perform better in classifying lung nodules compared to previously used 2D CNNs. It also demonstrates an approach to develop an optimized 3D CNN that performs with state of art classification accuracies. CNNs, like other deep neural networks, have been black boxes giving users no understanding of why they predict what they predict. This study, for the first time, demonstrates that Gradient-weighted Class Activation Mapping (Grad-CAM) techniques can provide visual explanations for model decisions in lung nodule classification by highlighting discriminative regions. Several CNN architectures using Keras and TensorFlow were implemented as part of this study. The publicly available LUNA16 dataset, comprising 888 CT scans with candidate nodules manually annotated by radiologists, was used to train and test the models. The models were optimized by varying the hyperparameters, to reach accuracies exceeding 90%. Grad-CAM techniques were applied to the optimized 3D CNN to generate images that provide quality visual insights into the model decision making. The results demonstrate the promise of 3D CNNs as highly accurate and trustworthy classifiers for early lung cancer detection, leading to improved chances of survival and prognosis.

 
4 favorite thumb_down thumb_up 0 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist
 

Outline/Structure of the Case Study

General outline of the presentation

Introduction:

Brief summary of the background that supports the research problem and explains why this research is important scientifically and societal impact of the research

Research Objective:

Research and develop 3D Convolutional Neural Networks to detect lung nodules in CT scan data with better accuracy and higher trust than existing models and ultimately aid in early detection of lung cancer to improve chances of survival and prognosis.

Research Questions:

Will 3D Convolutional Neural Networks perform better than 2D Convolutional Neural Networks in detecting lung nodules?

Is it possible to derive visual explanations for the internal workings of 3D Convolutional Neural Networks in lung nodule detection using Gradient-weighted Class Activation Mapping techniques?

Procedure:

Dataset, Preprocessing, Splitting, Training, Validating, Testing, Visualization

Tools Used

Results:

Model Performance, Key Metrics

Visual Insights into Model Decision Making

Discussion and Conclusions:

Select References:

Link to Poster:

https://drive.google.com/file/d/1wkoh2d7KKJe4guQWpmyzBraY5eXFYlmo/view?usp=sharing

Learning Outcome

Understand how machine learning methods can be applied to solve high impact medical problems such as lung cancer detection

Understand 3d CNNs and their applications in Lung cancer detection

Understand how Gradient-weighted Class Activation Mapping (Grad-CAM) techniques can be applied to lung data to provide visual insights into model decision making

Target Audience

Data Scientists, Students, Researchers and Medical Professionals interested in applications of machine learning in solving high impact problems in medicine

Prerequisites for Attendees

Basics of machine learning

schedule Submitted 1 month ago

Public Feedback

comment Suggest improvements to the Speaker

    • Liked Viral B. Shah
      keyboard_arrow_down

      Viral B. Shah - Growing a compiler - Getting to ML from the general-purpose Julia compiler

      45 Mins
      Keynote
      Intermediate

      Since we originally proposed the need for a first-class language, compiler and ecosystem for machine learning (ML) - a view that is increasingly shared by many, there have been plenty of interesting developments in the field. Not only have the tradeoffs in existing systems, such as TensorFlow and PyTorch, not been resolved, but they are clearer than ever now that both frameworks contain distinct "static graph" and "eager execution" interfaces. Meanwhile, the idea of ML models fundamentally being differentiable algorithms – often called differentiable programming – has caught on.

      Where current frameworks fall short, several exciting new projects have sprung up that dispense with graphs entirely, to bring differentiable programming to the mainstream. Myia, by the Theano team, differentiates and compiles a subset of Python to high-performance GPU code. Swift for TensorFlow extends Swift so that compatible functions can be compiled to TensorFlow graphs. And finally, the Flux ecosystem is extending Julia’s compiler with a number of ML-focused tools, including first-class gradients, just-in-time CUDA kernel compilation, automatic batching and support for new hardware such as TPUs.

      This talk will demonstrate how Julia is increasingly becoming a natural language for machine learning, the kind of libraries and applications the Julia community is building, the contributions from India (there are many!), and our plans going forward.

    • Liked Anuj Gupta
      keyboard_arrow_down

      Anuj Gupta - Continuous Learning Systems: Building ML systems that keep learning from their mistakes

      Anuj Gupta
      Anuj Gupta
      Scientist
      Intuit
      schedule 2 weeks ago
      Sold Out!
      45 Mins
      Talk
      Beginner

      Won't it be great to have ML models that can update their “learning” as and when they make mistake and correction is provided in real time? In this talk we look at a concrete business use case which warrants such a system. We will take a deep dive to understand the use case and how we went about building a continuously learning system for text classification. The approaches we took, the results we got.

      For most machine learning systems, “train once, just predict thereafter” paradigm works well. However, there are scenarios when this paradigm does not suffice. The model needs to be updated often enough. Two of the most common cases are:

      1. When the distribution is non-stationary i.e. the distribution of the data changes. This implies that with time the test data will have very different distribution from the training data.
      2. The model needs to learn from its mistakes.

      While (1) is often addressed by retraining the model, (2) is often addressed using batch update. Batch updation requires collecting a sizeable number of feedback points. What if you have much fewer feedback points? You need model that can learn continuously - as and when model makes a mistake and feedback is provided. To best of our knowledge there is a very limited literature on this.

    • Liked Anuj Gupta
      keyboard_arrow_down

      Anuj Gupta - NLP Bootcamp

      Anuj Gupta
      Anuj Gupta
      Scientist
      Intuit
      schedule 3 weeks ago
      Sold Out!
      480 Mins
      Workshop
      Beginner

      Recent advances in machine learning have rekindled the quest to build machines that can interact with outside environment like we human do - using visual clues, voice and text. An important piece of this trilogy are systems that can process and understand text in order to automate various workflows such as chat bots, named entity recognition, machine translation, information extraction, summarization, FAQ system, etc.

      A key step towards achieving any of the above task is - using the right set of techniques to represent text in a form that machine can understand easily. Unlike images, where directly using the intensity of pixels is a natural way to represent the image; in case of text there is no such natural representation. No matter how good is your ML algorithm, it can do only so much unless there is a richer way to represent underlying text data. Thus, whatever NLP application you are building, it’s imperative to find a good representation for your text data.

      In this bootcamp, we will understand key concepts, maths, and code behind the state-of-the-art techniques for text representation. We will cover mathematical explanations as well as implementation details of these techniques. This bootcamp aims to demystify, both - Theory (key concepts, maths) and Practice (code) that goes into building these techniques. At the end of this bootcamp participants would have gained a fundamental understanding of these schemes with an ability to implement them on datasets of their interest.

      This would be a 1-day instructor-led hands-on training session to learn and implement an end-to-end deep learning model for natural language processing.

    • 480 Mins
      Workshop
      Intermediate

      In this session, data scientists from CellStrat AI Lab will present demos and presentations on cutting-edge AI solutions in :-

      • Computer Vision - Image Segmentation with FCN/UNets/DeepLab/ESPNet, Image Processing, Pose Estimation with DensePose
      • Natural Language Processing (NLP) - Latest NLP and Text Analytics with BERT, NER, Neural Language Translation etc to solve problems such as text summarization, QnA systems, video captioning etc.
      • Reinforcement Learning (RL) - Train Atari Video Games with RL, Augmented Random Search, Deep Q Learning etc. Apply RL techniques for gaming, financial portfolios, driverless cars etc. Train Robots with MuJoCo simulator.
      • Driverless Cars - Demo on multi-class roads datasets, path planning and navigation control for cars etc.
      • Neural Network Architectures - Faster and Smaller Neural Networks with MorphNet
    • 45 Mins
      Talk
      Intermediate

      This session will discuss Reinforcement Learning (RL) algorithms such as Policy Gradients, TD Learning and Deep-Q Learning. We will discuss how emerging RL algorithms can be used to train games, driverless cars, financial decision models and home automation systems.

    • Liked Sriram P
      keyboard_arrow_down

      Sriram P - Application Blueprint for Creating and using Predictive insights to drive business outcomes

      45 Mins
      Case Study
      Intermediate

      Predictive analytics is now the #1 feature on application roadmaps. Companies are responding to customer demands, competitive & market threats, defending their price & market segment by adding innovative predictive use cases to their applications.

      Every predictive analytics project comes with a set of challenges that one has to overcome to be able to incorporate insights into their existing application. This session will share some of the best practices and lessons learned in working with many customers to incorporate Predictive Analytics into their existing application. This session will highlight the challenges one would encounter before, during and after model creation & ways to address them to have a successful business application.

    • Liked Aditya Singh Tomar
      keyboard_arrow_down

      Aditya Singh Tomar - Building Your Own Data Visualization Platform

      45 Mins
      Demonstration
      Beginner

      Ever thought about having a mini interactive visualization tool that caters to your specific requirements. That is the product I created when I started independent consulting. 2 years since, and I have now decided to make it public – even the source code.

      This session will give you an overview about creating a custom, personalized version of a visualization platform built on R and Shiny. We will focus on a mix of structure and flexibility to address the varying requirements. We will look at the code itself and the various components involved while exploring the customization options available to ensure that the outcome is truly a personal product.

    • Liked Deepak Mukunthu
      keyboard_arrow_down

      Deepak Mukunthu - Automated Machine Learning

      45 Mins
      Talk
      Beginner

      Intelligent experiences powered by AI can seem like magic to users. Developing them, however, is pretty cumbersome involving a series of sequential and interconnected decisions along the way that is pretty time-consuming. What if there was an automated service that identifies the best machine learning pipelines for a given problem/data? Automated Machine Learning does exactly that!

      With the goal of accelerating AI for data scientists by improving their productivity and democratizing AI for other data personas who want to get into machine learning, Automated ML comes in many different flavors and experiences. Automated ML is one of the top 5 AI trends this year. This session will cover concepts of Automated ML, how it works, different variations of it and how you can use it for your scenarios.

    • Liked Deepak Mukunthu
      keyboard_arrow_down

      Deepak Mukunthu - Democratizing & Accelerating AI through Automated Machine Learning

      90 Mins
      Workshop
      Beginner

      Intelligent experiences powered by AI can seem like magic to users. Developing them, however, is pretty cumbersome involving a series of sequential and interconnected decisions along the way that is pretty time-consuming. What if there was an automated service that identifies the best machine learning pipelines for a given problem/data? Automated Machine Learning does exactly that!

      Automated ML is based on a breakthrough from our Microsoft Research division. The approach combines ideas from collaborative filtering and Bayesian optimization to search an enormous space of possible machine learning pipelines intelligently and efficiently. It's essentially a recommender system for machine learning pipelines. Similar to how streaming services recommend movies for users, Automated ML recommends machine learning pipelines for data sets.

      Just as important, Automated ML accomplishes all this without having to see the customer’s data, preserving privacy. Automated ML is designed to not look at the customer’s data. Customer data and execution of the machine learning pipeline both live in the customer’s cloud subscription (or their local machine), which they have complete control of. Only the results of each pipeline run are sent back to the Automated ML service, which then makes an intelligent, probabilistic choice of which pipelines should be tried next.

      By making Automated ML available through the Azure Machine Learning service (Python-based SDK), we're empowering data scientists with a powerful productivity tool. We also have Automated ML available through PowerBI so that business analysts and BI professionals can also take advantage of machine learning. For developers familiar with Visual Studio and C#, we now have Automated ML available in C#.Net. If you are a SQL data engineer, we have a solution for you as well. And stay tuned as we continue to incorporate it into other product channels to bring the power of Automated ML to everyone!

      This session will provide an overview of Automated machine learning, how it works and how you can get started! We will walk through real-world use cases, build ML models using Automated ML and go through the E2E ML process of training, deployment, inferencing and operationalization of models.