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

Example of manual contour correction, on four frames from different pullbacks. The top, middle, and bottom rows display the original image, the automatic segmentation contour of the fibrous cap (orange line), and the corrected segmentation contour (magenta line), respectively. In the bottom row, the control points that were manually indicated by the analyst are represented by the black dots
© Copyright Policy - OpenAccess
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4563002&req=5

Fig6: Example of manual contour correction, on four frames from different pullbacks. The top, middle, and bottom rows display the original image, the automatic segmentation contour of the fibrous cap (orange line), and the corrected segmentation contour (magenta line), respectively. In the bottom row, the control points that were manually indicated by the analyst are represented by the black dots

Mentions: Reviewing the resulting abluminal interface segmentation contours of the testing set, the expert performed a correction of the automatic contours with which he disagreed, as detailed in “Manual correction of the abluminal contour”. A total of 20 frames out of 179 were corrected, corresponding to seven pullbacks out of 21. For all these corrected frames, the mean number of manually added control points was (range 1–4). The two main factors motivating this manual corrections were (1) image artifacts hampering the automatic segmentation and (2) the presence of several interface-like structures attracting the contour. Examples of such manual correction of erroneous contours are depicted in Fig. 6. Assessing the fibrous cap with the corrected contours yielded an overall reduced cap thickness (bias of , Bland-Altman  limits of agreement of ). Comparing, for the 20 corrected frames, the bias (and 95 % limits of agreement) of the cap thickness estimation resulting from the automatic segmentation and the manually corrected segmentation, it decreased from to when evaluated against the reference tracings of , but increased from to with . This discrepancy, reflecting the subjectivity of human analysts, is also visible through the bias between the two experts, which was equal to in these 20 frames.Fig. 6


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)

Example of manual contour correction, on four frames from different pullbacks. The top, middle, and bottom rows display the original image, the automatic segmentation contour of the fibrous cap (orange line), and the corrected segmentation contour (magenta line), respectively. In the bottom row, the control points that were manually indicated by the analyst are represented by the black dots
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

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

Fig6: Example of manual contour correction, on four frames from different pullbacks. The top, middle, and bottom rows display the original image, the automatic segmentation contour of the fibrous cap (orange line), and the corrected segmentation contour (magenta line), respectively. In the bottom row, the control points that were manually indicated by the analyst are represented by the black dots
Mentions: Reviewing the resulting abluminal interface segmentation contours of the testing set, the expert performed a correction of the automatic contours with which he disagreed, as detailed in “Manual correction of the abluminal contour”. A total of 20 frames out of 179 were corrected, corresponding to seven pullbacks out of 21. For all these corrected frames, the mean number of manually added control points was (range 1–4). The two main factors motivating this manual corrections were (1) image artifacts hampering the automatic segmentation and (2) the presence of several interface-like structures attracting the contour. Examples of such manual correction of erroneous contours are depicted in Fig. 6. Assessing the fibrous cap with the corrected contours yielded an overall reduced cap thickness (bias of , Bland-Altman  limits of agreement of ). Comparing, for the 20 corrected frames, the bias (and 95 % limits of agreement) of the cap thickness estimation resulting from the automatic segmentation and the manually corrected segmentation, it decreased from to when evaluated against the reference tracings of , but increased from to with . This discrepancy, reflecting the subjectivity of human analysts, is also visible through the bias between the two experts, which was equal to in these 20 frames.Fig. 6

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