Skip to Main Content

An official website of the United States government

Automatic detection and classification of lung abnormalities via deep learning and machine learning

Principal Investigator
Name
Igor Barani
Degrees
MD
Institution
Enlitic
Position Title
CEO
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCO-222
Initial CDAS Request Approval
Aug 24, 2016
Title
Automatic detection and classification of lung abnormalities via deep learning and machine learning
Summary
Algorithms that “read” biomedical images in search of abnormalities hold the promise of more accurate, faster and more accessible diagnoses, and better patient outcomes. However their success to date is limited by the need to laborious “hand engineer” computational image features that characterize the steps in a radiologist’s process. Some of these features take years to create, and some algorithms use thousands of features. In 2012, an algorithm called "deep learning" transformed the field of computer vision via the usage of large neural networks that run on GPUs, that automatically learn the relevant features. We propose the creation of a deep neural network for lung. Such networks would learn the appearance of lung tissue and structure, the variation across people, and the variation of abnormalities. We would also build algorithms that detect lung nodules, and estimate their likelihood of malignancy. 

Past research has shown that machine learning techniques on large numbers of features can be effective in identifying clinically relevant features of lung tumours (Aerts et al, 2014). Other research has shown that deep learning can be effective in generating features for analysing bone lesions (Roth et al, 2014). We plan to test a combination of these approaches, by using machine learning to analyse features built using deep learning to try to identify clinically relevant factors on screening chest X-rays that may suggest malignancy.
Aims

Aim 1: Create a deep neural network of human lungs. 
One limitation of deep learning is that it generally requires a large number of images. Digitized chest radiographs from the PLCO trial provide the largest, curated chest X-ray image database, and thus we believe will be an essential component for generating deep learning models. We plan to create a convolutional neural network (CNN) for chest X-rays to initially detect and then classify detected lesions (benign vs. malignant). The networks will serve multiple goals (see Aims 2 and 3), and also can be correlated with secondary data sources (e.g. clinical outcomes) to serve those goals. We also plan to visualize the networks to learn the hierarchy of features and compare it to human radiologist features.



Aim 2: Automatic identification of suspect regions and estimation of likelihood of malignancy
. In order to accomplish this, we require annotations on a subset of the images. If these annotations are unavailable from PLCO, we may create our own for the purposes of this study. In addition to generating our own annotations, we also plan to use annotated images to create deep learning features using unsupervised training. We will then analyse these features using machine learning.



Aim 3: Determination of malignancy likelihood. We will use the patient diagnoses and outcome data to estimate likelihood that detected lesion represents a malignant vs. benign etiology. We will use a technique similar to that in Beck et al (2011), but using deep learning features in addition to domain specific features.

Collaborators

Kevin Lyman (Enlitic, Inc.)
Brian Basham (Enlitic, Inc.)
Diogo Almeida (Enlitic, Inc.)
Alan Liu (Enlitic, Inc.)
Scott McKinney (Enlitic, Inc.)