TY - GEN
T1 - CRF-based segmentation of human tear meniscus obtained with optical coherence tomography
AU - Tsechpenakis, Gabriel
AU - Wang, Jianhua
PY - 2007
Y1 - 2007
N2 - The dynamic variation of the human tear meniscus (tears around the eye lids) is very critical in visual function, maintenance of corneal integrity, and ocular comfort. The quantitative measuring of the tear menisci around the eyelids is though a challenging task. In our work, tear meniscus images are obtained with our custom-built Optical Coherence Tomography (OCT) and are processed using our novel segmentation method. For the latter, we use an implicit deformable model driven by a Conditional Random Field (CRF). The evolution of the model is solved as MAP estimation. The target conditional probability is decomposed using a simple graphical model, where the probability field of the pixel labels given the image observations is estimated using a discriminative CRF. Our results show that our segmentation approach successfully handles clutter and boundary ambiguities of the tear menisci, which makes our integrated system reliable for the every day medical practice.
AB - The dynamic variation of the human tear meniscus (tears around the eye lids) is very critical in visual function, maintenance of corneal integrity, and ocular comfort. The quantitative measuring of the tear menisci around the eyelids is though a challenging task. In our work, tear meniscus images are obtained with our custom-built Optical Coherence Tomography (OCT) and are processed using our novel segmentation method. For the latter, we use an implicit deformable model driven by a Conditional Random Field (CRF). The evolution of the model is solved as MAP estimation. The target conditional probability is decomposed using a simple graphical model, where the probability field of the pixel labels given the image observations is estimated using a discriminative CRF. Our results show that our segmentation approach successfully handles clutter and boundary ambiguities of the tear menisci, which makes our integrated system reliable for the every day medical practice.
KW - CRF-based segmentation
KW - Deformable models
KW - Optical coherence tomography
KW - Tear meniscus
UR - http://www.scopus.com/inward/record.url?scp=48149097875&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=48149097875&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2007.4379877
DO - 10.1109/ICIP.2007.4379877
M3 - Conference contribution
AN - SCOPUS:48149097875
SN - 1424414377
SN - 9781424414376
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - V509-V512
BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
PB - IEEE Computer Society
T2 - 14th IEEE International Conference on Image Processing, ICIP 2007
Y2 - 16 September 2007 through 19 September 2007
ER -