Publications

BibTex format

@article{Zhang:2017:10.1117/1.JMI.4.1.015001,
author = {Zhang, Y and Wirkert, SJ and Iszatt, J and Kenngott, H and Wagner, M and Mayer, B and Stock, C and Clancy, NT and Elson, DS and Maier-Hein, L},
doi = {10.1117/1.JMI.4.1.015001},
journal = {Journal of Medical Imaging},
title = {Tissue classification for laparoscopic image understanding based on multispectral texture analysis.},
url = {http://dx.doi.org/10.1117/1.JMI.4.1.015001},
volume = {4},
year = {2017}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Intraoperative tissue classification is one of the prerequisites for providing context-aware visualization in computer-assisted minimally invasive surgeries. As many anatomical structures are difficult to differentiate in conventional RGB medical images, we propose a classification method based on multispectral image patches. In a comprehensive ex vivo study through statistical analysis, we show that (1) multispectral imaging data are superior to RGB data for organ tissue classification when used in conjunction with widely applied feature descriptors and (2) combining the tissue texture with the reflectance spectrum improves the classification performance. The classifier reaches an accuracy of 98.4% on our dataset. Multispectral tissue analysis could thus evolve as a key enabling technique in computer-assisted laparoscopy.
AU  - Zhang,Y
AU  - Wirkert,SJ
AU  - Iszatt,J
AU  - Kenngott,H
AU  - Wagner,M
AU  - Mayer,B
AU  - Stock,C
AU  - Clancy,NT
AU  - Elson,DS
AU  - Maier-Hein,L
DO  - 10.1117/1.JMI.4.1.015001
PY  - 2017///
SN  - 2329-4310
TI  - Tissue classification for laparoscopic image understanding based on multispectral texture analysis.
T2  - Journal of Medical Imaging
UR  - http://dx.doi.org/10.1117/1.JMI.4.1.015001
UR  - http://www.ncbi.nlm.nih.gov/pubmed/28149926
UR  - http://hdl.handle.net/10044/1/45836
VL  - 4
ER  -

Download

Dr Neil T Clancy

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)