Deep artificial neural networks for lung nodule detection and classification
Principal Investigator
Name
Giovanni Montana
Degrees
PhD in Statistics
Institution
King's College London
Position Title
Professor
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-150
Initial CDAS Request Approval
Aug 7, 2015
Title
Deep artificial neural networks for lung nodule detection and classification
Summary
In computer vision, in very recent years, biologically-inspired convolutional neural networks (CNN) have shown the ability to learn hierarchically-organised, low- to high-level features from raw images, and yield state-of-the-art performance in the
classification and segmentation of both natural and medical images. In this project we will develop convolutional neural networks for the automated interpretation of CT scans of the lungs. A computer-aided diagnostic (CAD) system will be developed for the detection of potential abnormalities, including the presence of a nodule, its position, and its likely characterisation. The system will leverage high-performance computing technology and provide a suggested diagnosis in near real-time.
Aims
The specific aim of this project is to develop a computer vision system for the automated interpretation of CT scans and, in particular, for the detection and classification of lung nodules. The imaging datasets and associated clinical information will be used for training and testing the algorithms.
Collaborators
Prof Gary Cook, King's College London
Prof Vicky Goh, King's College London