Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Principal Investigator
Name
Zachary Hendlin
Degrees
BA (statistics) MA (in progress)
Institution
M.I.T.
Position Title
Graduate Student
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-39
Initial CDAS Request Approval
Oct 17, 2013
Title
A Machine Learning Approach for Localizing Cancerous Nodules
Summary
We propose the application of statistical machine learning approaches to (1) the primary identification of atypical nodules in medical imaging data, and (2) supplemental verification of atypical clinical results.

Unlike image recognition and classification approaches which rely on pre-specified feature sets (e.g. shape, color intensity, symmetry) we explore the applicability of a more generalizable approach which aims to better develop nuanced hierarchical feature sets from medical images to facilitate the development of higher performance models for the recognition of atypical nodules.
Aims

(1) Explore the viability of applying deep machine learning algorithms to unstructured and unnormalized medical imaging data

(2) Determine the statistical properties of various computational models (both supervised and unsupervised statistical learning) for determining atypical nodules

(3) Fine-tune model parameters for more accurate prediction and detection of atypical nodules

(4) Understand key limitations of unsupervised learning and how the introduction of application-specific features can enhance classification ability

Collaborators

Tejas Kulkarni, MIT PhD student
Karthik Rajagopal, MIT PhD student
Ardavan Saeedi, MIT PhD student