Skip to Main Content

An official website of the United States government

Development of tools for segmentation and classification of lung imaging data

Principal Investigator
Name
Amir Amini
Degrees
Ph.D.
Institution
University of Louisville Research Foundation, Inc.
Position Title
Professor and Endowed Chair in Bioimaging
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-410
Initial CDAS Request Approval
May 7, 2018
Title
Development of tools for segmentation and classification of lung imaging data
Summary
Fatality caused by lung cancer has signi cant proportions; it is estimated that
1.1 million people die of lung cancer each year [1]. Fortunately, screening high
risk patients with low-dose 3-D X-ray computer tomorgraphy. Tomography (CT) has shown signi cant
reduction of lung cancer mortality rate [2]. As a consequence of the benefi ts
provided by this modality, it is being implemented in large scale, resulting in
signi cant increase of reading e orts for the radiologists. Computer-Aided De-
tection (CAD) systems have come to assist the radiologists in the reading and
interpretation by detecting, segmenting, and keeping track of nodule changes in
CT scans and making the process more ecient. As part of this project, we will test, develop, and apply
a variety of computerized methods for segmentation and quantification of lung CT data with the main objective being
use of radiomics for characterization of lung nodules.
Aims

1. Design and develop mathematical image analysis methods for analysis of lung CT data
2. Use and/or develop machine learning and Deep Learning techniques for the purpose of ascertaining
maligancy based on radiomics.

Collaborators

Collaborators are Hichem Frigui (CECS), Albert Seow (Radiology), and Neal Dunlap and Brian Wang (Radiation Oncology) at the University of Louisville.

Related Publications
  • Joint Learning for Deformable Registration and Malignancy Classification of Lung Nodules
    Aryan Ghazipour , Medical Imaging Lab, University of Louisville, Louisville, KY, USA , Benjamin Veasey , Medical Imaging Lab, University of Louisville, Louisville, KY, USA , Albert Seow , University of Louisville, Louisville, KY, USA , Amir A. Amini , Medical Imaging Lab, University of Louisville, Louisville, KY, USA
    IEEE. 2021 May 25; Pages 1807-1811
  • 3D U-net for registration of lung nodules in longitudinal CT scans
    Aryan Ghazipour, Benjamin Veasey, Albert Seow, Amir Amini
    SPIE Medical Imaging. 2021 Feb 15; Volume 11597
  • Lung Nodule Malignancy Classification Based ON NLSTx Data
    Benjamin Veasey , Medical Imaging Lab, University of Lousiville, Louisville, KY, USA , M. Mehdi Farhangi , U.S. Food and Drug Administration, Silver Spring, MD, USA , Hichem Frigui , Multimedia Lab, University of Lousiville, Louisville, KY, USA , Justin Broadhead , University of Lousiville, Louisville, KY, USA , Michael Dahle , University of Lousiville, Louisville, KY, USA , Aria Pezeshk , U.S. Food and Drug Administration, Silver Spring, MD, USA , Albert Seow , University of Lousiville, Louisville, KY, USA , Amir A. Amini , Medical Imaging Lab, University of Lousiville, Louisville, KY, USA
    IEEE. 2020; Pages pp. 1870-1874
  • Lung Nodule Malignancy Prediction From Longitudinal CT Scans With Siamese Convolutional Attention Networks
    Benjamin P. Veasey , University of Louisville, Louisville, KY, USA , Justin Broadhead , University of Louisville, Louisville, KY, USA , Michael Dahle , University of Louisville, Louisville, KY, USA , Albert Seow , University of Louisville, Louisville, KY, USA , Amir A. Amini , University of Louisville, Louisville, KY, USA
    IEEE. 2020 Sep 11; Volume 1: Pages 257 - 264