Standardized evaluation methodology and reference database for evaluating IVUS image segmentation

Balocco, Simone; Gatta, Carlo; Ciompi, Francesco; Wahle, Andreas; Radeva, Petia; Carlier, Stéphane; Ünal, Gözde; Sanidas, Elias; Mauri, Josepa; Carillo, Xavier; Kovárník, Tomáš; Wang, Ching-Wei; Chen, Hsiang-Chou; Exarchos, Themis P.; Fotiadis, Dimitrios I.; Destrempes, François; Cloutier, Guy; Pujol, Oriol; Alberti, Marina; Mendizabal-Ruiz, Gerardo; Rivera, Mariano; Aksoy, Timur; Downe, Richard; Kakadiaris, Ioannis A.

doi:10.1016/j.compmedimag.2013.07.001

Cited by 119 publications

(131 citation statements)

References 56 publications

(98 reference statements)

Supporting

Mentioning

128

Contrasting

Order By: Relevance

“…The average algorithmic to experts’ discrepancy as measured with PAD was 0.066 and 0.11 for EEM and lumen contours, respectively (c.f. Tables 9 and 10), whereas in Table 5 of [15], the best values were comparable to our results at 0.10 for both EEM and lumen contours. Lastly, in the present study, JM measures between algorithmic and experts’ contours were 0.815 and 0.896 for EEM and lumen contours, respectively.…”

Section: Summary and Discussionsupporting

confidence: 84%

“…In [15], three other evaluation measures were proposed for assessment of IVUS segmentation algorithms: Hausdorff distance (HD) ( i . e ., maximal distance between two contours), percentage of area difference (PAD), and Jaccard measure (JM).…”

Section: Summary and Discussionmentioning

confidence: 99%

“…To compare discrepancy between algorithmic and experts’ contours with a previous standardization and evaluation study [15], the mean pairwise HD between algorithmic and experts’ EEM and lumen contours were 0.337 and 0.392 mm, respectively, as reported in Tables 9 and 10. In Table 5 of [15], the best of these measures over 8 independent participants of this evaluation study were higher at 1.15 and 1.16 mm, respectively.…”

Section: Summary and Discussionmentioning

confidence: 99%

“…In Table 5 of [15], the best of these measures over 8 independent participants of this evaluation study were higher at 1.15 and 1.16 mm, respectively. The average algorithmic to experts’ discrepancy as measured with PAD was 0.066 and 0.11 for EEM and lumen contours, respectively (c.f.…”

Section: Summary and Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Assessment of Inter-Expert Variability and of an Automated Segmentation Method of 40 and 60 MHz IVUS Images of Coronary Arteries

Destrempes¹,

Cardinal²,

Saijo³

et al. 2017

PLoS ONE

Self Cite

View full text Add to dashboard Cite

The objectives were to compare the performance of a segmentation algorithm, based on the minimization of an uncertainty function, to delineate contours of external elastic membrane and lumen of human coronary arteries imaged with 40 and 60 MHz IVUS, and to use values of this function to delineate portions of contours with highest uncertainty. For 8 patients, 40 and 60 MHz IVUS coronary data acquired pre- and post-interventions were used, for a total of 68,516 images. Manual segmentations of contours (on 2312 images) performed by experts at three core laboratories were the gold-standards. Inter-expert variability was highest on contour points with largest values of the uncertainty function (p < 0.001). Inter-expert variability was lower at 60 than 40 MHz for external elastic membrane (p = 0.013) and lumen (p = 0.024). Average differences in plaque (and atheroma) burden between algorithmic contours and experts’ contours were within inter-expert variability (p < 0.001).

show abstract

Section: Summary and Discussionsupporting

confidence: 84%

Section: Summary and Discussionmentioning

confidence: 99%

Section: Summary and Discussionmentioning

confidence: 99%

Section: Summary and Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Assessment of Inter-Expert Variability and of an Automated Segmentation Method of 40 and 60 MHz IVUS Images of Coronary Arteries

Destrempes¹,

Cardinal²,

Saijo³

et al. 2017

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Solid modelers or 3D CAD software are often used, and increasingly geometric reconstructions are derived from medical image based sequences such as Intravascular Ultrasound (IVUS) (Balocco et al 2014), (Zheng and Mengchan 2013), angiography or Computerized Tomography (CT). One major feature of FEA is that it allows for neglect of irrelevant mechanical forms.…”

Section: Pre-processingmentioning

confidence: 99%

Stent Deployment Computer Based Simulations for Health Care Treatment of Diseased Arteries

Karanasiou

Tripoliti

Edelman

et al. 2014

Concepts and Trends in Healthcare Information Systems

Self Cite

View full text Add to dashboard Cite

Endovascular stent deployment is one of the most commonly used techniques for the treatment of diseased arterial segments. Though these devices have eliminated the problem with recoil seen with balloon angioplasty alone there are idiosyncratic reactions that remain and mandate further definition and examination so as these can be eliminated. Chief amongst these problems are loss of lumen patency to clot, stent thrombosis (acute, subacute, late and very late), or to tissue overgrowth, instent restenosis (ISR). While these effects are to some extent class-related, each individual design and implantation procedures impacts outcome. The magnitude and diversity of the parameters that determine safety and efficacy defies empiric validation and limits how much experimentation can add to optimization. Differences in design, materials, arterial geometries, implantation procedures and local, regional and systemic forces and flows cannot be evaluated across the domains of interest and in reasonable time but they can be considered in computational models. High speed computer resources can solve complex coupled equations that cover an almost infinite range of perturbations and combinations of conditions and have become an invaluable tool in the armamentarium of

show abstract

Supervised machine learning for coronary artery lumen segmentation in intravascular ultrasound images

Cui

Xia

Zhang

2020

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Intravascular ultrasound (IVUS) has been widely used to capture cross sectional lumen frames of inner wall of coronary arteries. This kind of medical imaging modalities is capable of providing detailed and significant information of lumen contour shape, which is very important for clinical diagnosis and analysis of cardiovascular diseases. Numerous learning based techniques have recently become very popular for coronary artery segmentation due to their impressive results. In this work, a supervised machine learning method for coronary artery lumen segmentation with high accuracy and minimal user interaction is designed. The fully discriminative lumen segmentation method jointly learning a classifier the weak learners rely on and the features of the classifier is developed. Additionally, the theoretical supports of the Gradient Boosting framework used in this work and its quadratic approximation are presented. The proposed algorithm is tested on the public datasets of boundary detection of lumen in IVUS challenge held in MICCAI 2011 and achieves a higher average Jaccard similarity of 96.8% and a lower mean error distance of 0.55 (in Cartesian coordinates), which shows higher accuracy compared to the existing learning based methods. Moreover, three real patient IVUS datasets are used to evaluate the performance of the proposed coronary artery lumen segmentation algorithm, which is shown to achieve lower percent error of lumen area of 1.861% ± 0.965%, 1.968% ± 0.864%, and 1.671% ± 0.584%, respectively, compared to the manually measured lumen area (ground truth). The proposed lumen segmentation method is found to be superior to the latest learning based segmentation techniques. Given the efficiency and robustness, our method has great potential in IVUS images processing and coronary artery segmentation and quantification.Novelty StatementThe main contributions are summarized in the following aspects: A detailed review of related work about learning based coronary artery lumen segmentation in intravascular ultrasound images is presented. A fully discriminative lumen segmentation method jointly learning a classifier our weak learners rely on and the features of the classifier is developed. The theoretical supports of the Gradient Boosting framework and its quadratic approximation used in this work are presented.

show abstract

Standardized evaluation methodology and reference database for evaluating IVUS image segmentation

Cited by 119 publications

References 56 publications

Assessment of Inter-Expert Variability and of an Automated Segmentation Method of 40 and 60 MHz IVUS Images of Coronary Arteries

Assessment of Inter-Expert Variability and of an Automated Segmentation Method of 40 and 60 MHz IVUS Images of Coronary Arteries

Stent Deployment Computer Based Simulations for Health Care Treatment of Diseased Arteries

Supervised machine learning for coronary artery lumen segmentation in intravascular ultrasound images

Contact Info

Product

Resources

About