IMPACT OF DATA SHAPE, FIDELITY, AND INTER-OBSERVER REPRODUCIBILITY ON CARDIAC MAGNETIC RESONANCE IMAGE PIPELINES

Access to IIT electronic theses and dissertations is restricted to IIT community members with a valid iit.edu email address. Please log in using your iit.edu email address and password. Requests for external users are handled through inter-library loan and can be emailed to iitmyillms@iit.edu.

Description

Artificial Intelligence (AI) holds a great promise in the healthcare. It provides a variety of advantages with its application in clinical diagnosis, disease prediction, and treatment, with such interests intensifying in the medical image field. AI can automate various cumbersome data processing... Show moreArtificial Intelligence (AI) holds a great promise in the healthcare. It provides a variety of advantages with its application in clinical diagnosis, disease prediction, and treatment, with such interests intensifying in the medical image field. AI can automate various cumbersome data processing techniques in medical imaging such as segmentation of left ventricular chambers and image-based classification of diseases. However, full clinical implementation and adaptation of emerging AI-based tools face challenges due to the inherently opaque nature of such AI algorithms based on Deep Neural Networks (DNN), for which computer-trained bias is not only difficult to detect by physician users but is also difficult to safely design in software development. In this work, we examine AI application in Cardiac Magnetic Resonance (CMR) using an automated image classification task, and thereby propose an AI quality control framework design that differentially evaluates the black-box DNN via carefully prepared input data with shape and fidelity variations to probe system responses to these variations. Two variants of the Visual Geometric Graphics with 19 neural layers (VGG19) was used for classification, with a total of 60,000 CMR images. Findings from this work provides insights on the importance of quality training data preparation and demonstrates the importance of data shape variability. It also provides gateway for computation performance optimization in training and validation time. Show less

Details
Department

BME / Biomedical Engineering

Title

IMPACT OF DATA SHAPE, FIDELITY, AND INTER-OBSERVER REPRODUCIBILITY ON CARDIAC MAGNETIC RESONANCE IMAGE PIPELINES

Institution

Illinois Institute of Technology

Creator(s)

Obioma, Blessing Ngozi

Advisor(s)

Kawaji, Keigo

Date

2020

Description

Artificial Intelligence (AI) holds a great promise in the healthcare. It provides a variety of advantages with its application in clinical diagnosis, disease prediction, and treatment, with such... Show moreArtificial Intelligence (AI) holds a great promise in the healthcare. It provides a variety of advantages with its application in clinical diagnosis, disease prediction, and treatment, with such interests intensifying in the medical image field. AI can automate various cumbersome data processing techniques in medical imaging such as segmentation of left ventricular chambers and image-based classification of diseases. However, full clinical implementation and adaptation of emerging AI-based tools face challenges due to the inherently opaque nature of such AI algorithms based on Deep Neural Networks (DNN), for which computer-trained bias is not only difficult to detect by physician users but is also difficult to safely design in software development. In this work, we examine AI application in Cardiac Magnetic Resonance (CMR) using an automated image classification task, and thereby propose an AI quality control framework design that differentially evaluates the black-box DNN via carefully prepared input data with shape and fidelity variations to probe system responses to these variations. Two variants of the Visual Geometric Graphics with 19 neural layers (VGG19) was used for classification, with a total of 60,000 CMR images. Findings from this work provides insights on the importance of quality training data preparation and demonstrates the importance of data shape variability. It also provides gateway for computation performance optimization in training and validation time. Show less

Type

Thesis

File type

application/pdf

Subject

Artificial intelligence
Medical imaging
Biomedical engineering
Artificial Intelligence
Convolutional Neural Network
Deep Learning
multicenter reproducibility
Myocardial strain measurement
SENC MRI

Access

Restricted Access

Rights

In Copyright
http://rightsstatements.org/page/InC/1.0/

Identifier

http://hdl.handle.net/10560/islandora:1010190

<p></p><p></p>