156
D. Cabrera DeBuc et al.
The development of automated segmentation software is essential in exploiting the
diagnostic capability of OCT. The clinical segmentation reality of common pathologies could vary across retinal regions and diseases. Therefore, the segmentation
accuracy of the retinal structure is critical for the proper assessment of retinal pathology and current treatment practice. However, the optimal automated segmentation
software for OCT volume data remains to be established. While the need for unbiased
performance evaluation of automated segmentation algorithms is obvious, there does
not exist a suitable dataset with ground truth that reflects the realities of everyday
retinal features observed in clinical settings (e.g. pathologic cases which contain discontinues surfaces and additional abnormalities disrupting the retinal structure). In
addition to the lack of a common ground truth in OCT imaging, minor information of
the retinal tissue from the OCT volume data is commonly revealed besides the thickness of retinal layers [96, 200–202]. Recent advances in OCT technology are adding
the capability to extract information on blood flow and perfusion status of the retinal
tissue as well as on changes in the polarization state of the probing light beam when
interacting with the retinal tissue [203]. Therefore, it is expected that a more complete characterization of the retinal tissue could potentiate the diagnostic capability
of the OCT technology. This chapter has introduced and discussed several important
issues surrounding the diagnostic capabilities of the OCT technology and different
factors should be considered when both obtaining and analyzing the OCT images. In
summary, the use of OCT technology in clinical settings is of great value, but reliable
data analysis and proper diagnosis of the various retinal diseases requires careful considerations when using OCT devices. There is no doubt that further improvements
are warrantee as the technology evolves to help advance the judgment and decision
making processes of OCT developments and clinical applications.
References
1. D. Huang, E.A. Swanson, C.P. Lin, J.S. Schuman, W.G. Stinson, W. Chang, M.R. Hee,
T. Flotte, K. Gregory, C.A. Puliafito et al., Optical coherence tomography. Science 254,
1178–1181 (1991)
2. A.M. Zysk, F.T. Nguyen, A.L. Oldenburg, D.L. Marks et al., Optical coherence tomography: a
review of clinical development from bench to bedside. J. Biomed. Opt. 12(5), 051403 (2007)
3. R. Hamdan, R.G. Gonzalez, S. Ghostine, C. Caussin, Optical coherence tomography: From
physical principles to clinical applications. Arch. Cardiovasc. Dis. 105(10), 529–534 (2012)
4. C.A. Puliafito, Optical coherence tomography: 20 years after. Ophthalmic Surg. Lasers Imaging 41(Suppl(6)), 5 (2010)
5. J.S. Schuman, C.A. Puliafito, J.G. Fujimoto, S.D. Jay, Optical Coherence Tomography of
Ocular Diseases, 3rd edn. (Slack Inc., Thorofare, 2004)
6. G. Staurenghi, S. Sadda, U. Chakravarthy, R.F. Spaide, Proposed lexicon for anatomic landmarks in normal posterior segment spectral-domain optical coherence tomography. The
INOCT consensus. Ophthalmology 121, 1572–1578 (2014)
7. D.J. Browning, Interobserver variability in optical coherence tomography for macular edema.
Am. J. Ophthalmol. 137, 1116–1117 (2004)
D. Cabrera DeBuc et al.
The development of automated segmentation software is essential in exploiting the
diagnostic capability of OCT. The clinical segmentation reality of common pathologies could vary across retinal regions and diseases. Therefore, the segmentation
accuracy of the retinal structure is critical for the proper assessment of retinal pathology and current treatment practice. However, the optimal automated segmentation
software for OCT volume data remains to be established. While the need for unbiased
performance evaluation of automated segmentation algorithms is obvious, there does
not exist a suitable dataset with ground truth that reflects the realities of everyday
retinal features observed in clinical settings (e.g. pathologic cases which contain discontinues surfaces and additional abnormalities disrupting the retinal structure). In
addition to the lack of a common ground truth in OCT imaging, minor information of
the retinal tissue from the OCT volume data is commonly revealed besides the thickness of retinal layers [96, 200–202]. Recent advances in OCT technology are adding
the capability to extract information on blood flow and perfusion status of the retinal
tissue as well as on changes in the polarization state of the probing light beam when
interacting with the retinal tissue [203]. Therefore, it is expected that a more complete characterization of the retinal tissue could potentiate the diagnostic capability
of the OCT technology. This chapter has introduced and discussed several important
issues surrounding the diagnostic capabilities of the OCT technology and different
factors should be considered when both obtaining and analyzing the OCT images. In
summary, the use of OCT technology in clinical settings is of great value, but reliable
data analysis and proper diagnosis of the various retinal diseases requires careful considerations when using OCT devices. There is no doubt that further improvements
are warrantee as the technology evolves to help advance the judgment and decision
making processes of OCT developments and clinical applications.
References
1. D. Huang, E.A. Swanson, C.P. Lin, J.S. Schuman, W.G. Stinson, W. Chang, M.R. Hee,
T. Flotte, K. Gregory, C.A. Puliafito et al., Optical coherence tomography. Science 254,
1178–1181 (1991)
2. A.M. Zysk, F.T. Nguyen, A.L. Oldenburg, D.L. Marks et al., Optical coherence tomography: a
review of clinical development from bench to bedside. J. Biomed. Opt. 12(5), 051403 (2007)
3. R. Hamdan, R.G. Gonzalez, S. Ghostine, C. Caussin, Optical coherence tomography: From
physical principles to clinical applications. Arch. Cardiovasc. Dis. 105(10), 529–534 (2012)
4. C.A. Puliafito, Optical coherence tomography: 20 years after. Ophthalmic Surg. Lasers Imaging 41(Suppl(6)), 5 (2010)
5. J.S. Schuman, C.A. Puliafito, J.G. Fujimoto, S.D. Jay, Optical Coherence Tomography of
Ocular Diseases, 3rd edn. (Slack Inc., Thorofare, 2004)
6. G. Staurenghi, S. Sadda, U. Chakravarthy, R.F. Spaide, Proposed lexicon for anatomic landmarks in normal posterior segment spectral-domain optical coherence tomography. The
INOCT consensus. Ophthalmology 121, 1572–1578 (2014)
7. D.J. Browning, Interobserver variability in optical coherence tomography for macular edema.
Am. J. Ophthalmol. 137, 1116–1117 (2004)