BULGED EARDRUM DETECTION FROM 3D DATA

被引：0

作者：

Martinello, Manuel ^{[1
]}

Spinoulas, Leonidas ^{[1
]}

Karygianni, Sofia ^{[2
]}

Frossard, Pascal ^{[2
]}

Haralam, Mary Ann ^{[3
]}

Shope, Timothy R. ^{[3
]}

Shaikh, Nader ^{[3
]}

Hoberman, Alejandro ^{[3
]}

Tosic, Ivana ^{[1
]}

机构：

[1] Ricoh Innovat Corp, Cupertino, CA 95014 USA

[2] Ecole Polytech Fed Lausanne, Lausanne, Switzerland

[3] Childrens Hosp Pittsburgh, Pittsburgh, PA 15213 USA

来源：

2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2018年

关键词：

medical imaging; classification; 3D data; feature extraction; OBJECT RECOGNITION; DIAGNOSIS; IMAGES;

D O I：

暂无

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Bulging is a medical characteristic of the eardrum that is crucial for the diagnosis of acute otitis media. This work proposes a novel classification method for distinguishing bulged eardrums from non-bulged ones. The method uses novel key features extracted from 3D data of the tympanic membrane, captured using a new type of otoscope, the lightfield otoscope, capable of non-invasive 3D imaging of the middle ear. We first introduce a variety of geometrical and statistical descriptors (based on isocontours), and then select the most discriminative ones. Results on clinical data show that, when using the proposed feature descriptors, eardrum bulging can be automatically detected with an average accuracy of approximately 82%.

引用

页码：136 / 140

页数：5

共 17 条

[1]

[Anonymous], 2012, P 26 ANN C NEUR PROC, DOI DOI 10.1002/2014GB005021

[2]

[Anonymous], P AS C COMP VIS

[3]

[Anonymous], J BIOMEDICAL IMAGING

[4]

[Anonymous], 2011, Advances in neural information processing systems