Limits...
Quantification of fibrous cap thickness in intracoronary optical coherence tomography with a contour segmentation method based on dynamic programming.

Zahnd G, Karanasos A, van Soest G, Regar E, Niessen W, Gijsen F, van Walsum T - Int J Comput Assist Radiol Surg (2015)

Bottom Line: In the context of preoperative planning and perioperative decision making, intracoronary optical coherence tomography imaging can provide a very detailed characterization of the arterial wall structure.However, visual interpretation of the images is laborious, subject to variability, and therefore not always sufficiently reliable for immediate decision of treatment.Validated on a dataset of 179 images from 21 patients, the present framework could successfully extract the fibrous cap contours.

View Article: PubMed Central - PubMed

Affiliation: Biomedical Imaging Group Rotterdam, Departments of Radiology and Medical Informatics, Erasmus Medical Center, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands, g.zahnd@erasmusmc.nl.

ABSTRACT

Objectives: Fibrous cap thickness is the most critical component of plaque stability. Therefore, in vivo quantification of cap thickness could yield valuable information for estimating the risk of plaque rupture. In the context of preoperative planning and perioperative decision making, intracoronary optical coherence tomography imaging can provide a very detailed characterization of the arterial wall structure. However, visual interpretation of the images is laborious, subject to variability, and therefore not always sufficiently reliable for immediate decision of treatment.

Methods: A novel semiautomatic segmentation method to quantify coronary fibrous cap thickness in optical coherence tomography is introduced. To cope with the most challenging issue when estimating cap thickness (namely the diffuse appearance of the anatomical abluminal interface to be detected), the proposed method is based on a robust dynamic programming framework using a geometrical a priori. To determine the optimal parameter settings, a training phase was conducted on 10 patients.

Results: Validated on a dataset of 179 images from 21 patients, the present framework could successfully extract the fibrous cap contours. When assessing minimal cap thickness, segmentation results from the proposed method were in good agreement with the reference tracings performed by a medical expert (mean absolute error and standard deviation of 22 ± 18 μm) and were similar to inter-observer reproducibility (21 ± 19 μm, R = .74), while being significantly faster and fully reproducible.

Conclusion: The proposed framework demonstrated promising performances and could potentially be used for online identification of high-risk plaques.

No MeSH data available.


Related in: MedlinePlus

Mean absolute segmentation error of the fibrous cap abluminal interface, between the automatic framework and the manual tracings of the analyst , in function of the parameter settings . In each panel, the location of the minimal error is indicated by the black dot
© Copyright Policy - OpenAccess
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4563002&req=5

Fig3: Mean absolute segmentation error of the fibrous cap abluminal interface, between the automatic framework and the manual tracings of the analyst , in function of the parameter settings . In each panel, the location of the minimal error is indicated by the black dot

Mentions: Aiming to accurately extract the abluminal contour of the fibrous cap, the optimal parameter settings were determined by means of a training phase. In this purpose, a training set was generated by randomly selecting a subsample of pullbacks among the cohort of 31 participants. During the training phase, the proposed framework was repeatedly applied to the training set, with 1000 different sets of parameter settings, as displayed in Table 1. The number of reachable neighbors was equal to 41 to reduce the search space while still allowing the path to follow the curvature of the analyzed interface. A score was then attributed to each set of parameter settings, by calculating, for every frame of the training set, the mean error between the reference abluminal contour manually traced by and the corresponding segmentation contour resulting from the proposed framework. Finally, the optimal set of parameter settings was determined by visually inspecting the contours of the 10 best ranked sets and selecting the configuration yielding the contours with the most realistic appearance. The selected configuration was the ninth best ranked set, with a mean absolute error of . The parameters corresponding to the chosen set were as follows: smoothness parameters, and ; standard deviation of the Gaussian filter, . For comparison purpose, the mean absolute error corresponded to for the best ranked set , and to for the worst ranked set . Moreover, the difference between the error distributions corresponding to the chosen set and the best ranked set yielded a zero bias and a 95 % confidence interval equal to . By defining a zone of clinical indifference equal to (i.e., pixel), we can conclude that the accuracy of the chosen set is statistically equivalent to the accuracy of the best ranked set. Resulting errors in function of the parameter settings are displayed in Fig. 3.Table 1


Quantification of fibrous cap thickness in intracoronary optical coherence tomography with a contour segmentation method based on dynamic programming.

Zahnd G, Karanasos A, van Soest G, Regar E, Niessen W, Gijsen F, van Walsum T - Int J Comput Assist Radiol Surg (2015)

Mean absolute segmentation error of the fibrous cap abluminal interface, between the automatic framework and the manual tracings of the analyst , in function of the parameter settings . In each panel, the location of the minimal error is indicated by the black dot
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4563002&req=5

Fig3: Mean absolute segmentation error of the fibrous cap abluminal interface, between the automatic framework and the manual tracings of the analyst , in function of the parameter settings . In each panel, the location of the minimal error is indicated by the black dot
Mentions: Aiming to accurately extract the abluminal contour of the fibrous cap, the optimal parameter settings were determined by means of a training phase. In this purpose, a training set was generated by randomly selecting a subsample of pullbacks among the cohort of 31 participants. During the training phase, the proposed framework was repeatedly applied to the training set, with 1000 different sets of parameter settings, as displayed in Table 1. The number of reachable neighbors was equal to 41 to reduce the search space while still allowing the path to follow the curvature of the analyzed interface. A score was then attributed to each set of parameter settings, by calculating, for every frame of the training set, the mean error between the reference abluminal contour manually traced by and the corresponding segmentation contour resulting from the proposed framework. Finally, the optimal set of parameter settings was determined by visually inspecting the contours of the 10 best ranked sets and selecting the configuration yielding the contours with the most realistic appearance. The selected configuration was the ninth best ranked set, with a mean absolute error of . The parameters corresponding to the chosen set were as follows: smoothness parameters, and ; standard deviation of the Gaussian filter, . For comparison purpose, the mean absolute error corresponded to for the best ranked set , and to for the worst ranked set . Moreover, the difference between the error distributions corresponding to the chosen set and the best ranked set yielded a zero bias and a 95 % confidence interval equal to . By defining a zone of clinical indifference equal to (i.e., pixel), we can conclude that the accuracy of the chosen set is statistically equivalent to the accuracy of the best ranked set. Resulting errors in function of the parameter settings are displayed in Fig. 3.Table 1

Bottom Line: In the context of preoperative planning and perioperative decision making, intracoronary optical coherence tomography imaging can provide a very detailed characterization of the arterial wall structure.However, visual interpretation of the images is laborious, subject to variability, and therefore not always sufficiently reliable for immediate decision of treatment.Validated on a dataset of 179 images from 21 patients, the present framework could successfully extract the fibrous cap contours.

View Article: PubMed Central - PubMed

Affiliation: Biomedical Imaging Group Rotterdam, Departments of Radiology and Medical Informatics, Erasmus Medical Center, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands, g.zahnd@erasmusmc.nl.

ABSTRACT

Objectives: Fibrous cap thickness is the most critical component of plaque stability. Therefore, in vivo quantification of cap thickness could yield valuable information for estimating the risk of plaque rupture. In the context of preoperative planning and perioperative decision making, intracoronary optical coherence tomography imaging can provide a very detailed characterization of the arterial wall structure. However, visual interpretation of the images is laborious, subject to variability, and therefore not always sufficiently reliable for immediate decision of treatment.

Methods: A novel semiautomatic segmentation method to quantify coronary fibrous cap thickness in optical coherence tomography is introduced. To cope with the most challenging issue when estimating cap thickness (namely the diffuse appearance of the anatomical abluminal interface to be detected), the proposed method is based on a robust dynamic programming framework using a geometrical a priori. To determine the optimal parameter settings, a training phase was conducted on 10 patients.

Results: Validated on a dataset of 179 images from 21 patients, the present framework could successfully extract the fibrous cap contours. When assessing minimal cap thickness, segmentation results from the proposed method were in good agreement with the reference tracings performed by a medical expert (mean absolute error and standard deviation of 22 ± 18 μm) and were similar to inter-observer reproducibility (21 ± 19 μm, R = .74), while being significantly faster and fully reproducible.

Conclusion: The proposed framework demonstrated promising performances and could potentially be used for online identification of high-risk plaques.

No MeSH data available.


Related in: MedlinePlus