Thyroid nodule ultrasound image analysis and feature extraction

Simple item page
dc.contributor.advisorTrafalis, Theodore
dc.contributor.authorDong, Xiaomeng
dc.contributor.committeeMemberNicholson, Charles
dc.contributor.committeeMemberFagg, Andrew
dc.date.accessioned2018-05-07T14:42:06Z
dc.date.available2018-05-07T14:42:06Z
dc.date.issued2018-05-11
dc.date.manuscript2018-05-04
dc.description.abstractIn this study, I introduce a novel workflow for extracting useful features in thyroid ultrasound images using deep learning and machine learning methods. The methodology combines Convolutional Auto-Encoder, Local Binary Patterns, Histogram of Oriented Gradients and professional image characterization together to extract useful information from medical images. Multiple machine learning classifiers are used to build an effective thyroid tumor diagnosis model from extracted features. The experimental results show that Support Vector Machine with a specifically designed preprocessing scheme and a customized objective function outperforms human on the test set. The final model can effectively reduce the number of unnecessary biopsies and the number of missing malignancies.en_US
dc.identifier.urihttps://hdl.handle.net/11244/299791
dc.languageen_USen_US
dc.subjectDeep Learningen_US
dc.subjectMedical AIen_US
dc.subjectMedical Imagingen_US
dc.thesis.degreeMaster of Scienceen_US
dc.titleThyroid nodule ultrasound image analysis and feature extractionen_US
ou.groupGallogly College of Engineeringen_US
shareok.nativefileaccessrestricteden_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2018_Dong_Xiaomeng_Thesis.pdf
Size:
2.31 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

OU - Theses