nach oben

Medical & Biological Engineering & Computing

Erschienen in:

02.01.2020 | Original Article

Localization of common carotid artery transverse section in B-mode ultrasound images using faster RCNN: a deep learning approach

verfasst von: Pankaj K. Jain, Saurabh Gupta, Arnav Bhavsar, Aditya Nigam, Neeraj Sharma

Erschienen in: Medical & Biological Engineering & Computing | Ausgabe 3/2020

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Cardiologists can acquire important information related to patients’ cardiac health using carotid artery stiffness, its lumen diameter (LD), and its carotid intima-media thickness (cIMT). The sonographers primarily concern about the location of the artery in B-mode ultrasound images. Localization using manual methods is tedious and time-consuming and also may lead to some errors. On the other hand, automated approaches are more objective and can provide the localization of the artery at near real time. Above arterial parameters may be determined after localization of the artery in real time.

A novel method of localization of common carotid artery (CCA) transverse section is presented in this work. The method is known as fast region convolutional neural network (FRCNN)-based localization method and is designed using a stack of three layers viz. convolutional layers, fully connected layers, and pooling layers. These organized layers constitute a region proposal network (RPN) and an object class detection network (OCDN). We obtain an outcome as a bounding box along with a score of prediction around the cross-section of the CCA.

B-mode ultrasound image database of CCA is split into training and testing set, to accomplish this, three partition methods K = 2, 5, and 10 are used in our work. The training is extended for 30, 200, and 2000 epochs in order to achieve fine-tuned features from the convolutional neural network. After 2000 epochs, we obtain 95% validation accuracy; however, mean of the accuracies up to 2000 epochs is 89.36% for K = 10 partitions protocol (training 90%, testing 10%). Generated CNN model is tested on a different dataset of 433 images and the acquired accuracy is 87.99%. Thus, the proposed method including an advanced deep learning technique demonstrates promising localization for carotid artery transverse section.

Vorheriger Artikel Gait event detection using inertial measurement units in people with transfemoral amputation: a comparative study

Nächster Artikel Enhancement of blurry retinal image based on non-uniform contrast stretching and intensity transfer

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Kelly BB, Fuster V (2010) Promoting cardiovascular health in the developing world: a critical challenge to achieve global health. National Academies Press, Washington

Nikolaou K, Alkadhi H, Bamberg F, Leschka S, Wintersperger BJ (2011) MRI and CT in the diagnosis of coronary artery disease: indications and applications. Insights Into Imaging 2(1):9–24CrossRef

Saba L, Sanches JM, Pedro LM, Suri JS (2015) Multi-modality atherosclerosis imaging and diagnosis. Springer, New York

Prakash A, Powell AJ, Geva T (2010) Multimodality noninvasive imaging for assessment of congenital heart disease. Circ: Cardiovasc Imaging 3(1):112–125

Xu E, Long Y, Li K, Zeng Q, Tan L, Luo L, Zheng R (2019) Comparison of CT/MRI-CEUS and US-CEUS fusion imaging techniques in the assessment of the thermal ablation of liver tumors. Int J Hyperth 35(1):159–167CrossRef

Saba L, Jain PK, Suri HS, Ikeda N, Araki T, Singh BK, Nicolaides A, Shafique S, Gupta A, Laird JR, Suri JS (2017) Plaque tissue morphology-based stroke risk stratification using carotid ultrasound: a polling-based PCA learning paradigm. J Med Syst 41(6):41–98CrossRef

Araki T, Ikeda N, Shukla D, Jain PK, Londhe ND, Shrivastava VK, Laird JR (2016) PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound: a link between carotid and coronary grayscale plaque morphology. Comput Methods Prog Biomed 128:137–158CrossRef

Núñez F, Martínez-Costa C, Sánchez-Zahonero J, Morata J, Chorro FJ, Brines J (2010) Carotid artery stiffness as an early marker of vascular lesions in children and adolescents with cardiovascular risk factors. Revista Española de Cardiología (English Edition) 63(11):1253–1260CrossRef

Araki T, Jain PK, Suri HS, Londhe ND, Ikeda N, El-Baz A, Laird JR (2017) Stroke risk stratification and its validation using ultrasonic echolucent carotid wall plaque morphology: a machine learning paradigm. Comput Biol Med 80:77–96CrossRef

10.

Říha K and Beneš R (2010) Circle detection in pulsative medical video sequence IEEE 10th International Conference on Signal Processing (ICSP)

11.

Benes R, Karasek J, Barget R, Riha K (2013) Automatically designed machine vision system for the localization of CCA transverse section in ultrasound images. Comput Methods Prog Biomed 109(1):92–103CrossRef

12.

Říha K, Masek J, Benes R, Zavodana E (2013) Novel method for localization of common carotid artery transverse section in ultrasound images using modified Viola-Jones detector. Ultrasound Med Biol 39(10):1887–1902CrossRef

13.

Yang X, Mingyueg D, Liantang L, Ming Y, Qiu W, Yue S (2011) Common carotid artery lumen segmentation in B-mode ultrasound transverse view images. Int J Image, Graphics Signal Process 3(5):15–21CrossRef

14.

Yoon YH, Khan S, Huh J, Ye JC (2017) Deep learning in RF sub-sampled B-mode ultrasound imaging. arXiv preprint arXiv:1712.06096

15.

Vedula S, Senouf O, Bronstein AM, Michailovich OV, Zibulevsky M (2017) Towards CT-quality ultrasound imaging using deep learning. arXiv preprint arXiv:1710.06304

16.

Perdios D, Besson A, Arditi M, Thiran JP (2014) A deep learning approach to ultrasound image recovery. IEEE International In Ultrasonics Symposium (IUS) 1-4

17.

Tajbakhsh N, Shin JY, Gurudu SR, Hurst R, Kendall CB, Gotway MB, Liang J (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299–1312CrossRef

18.

Ma J, Wu F, Zhu J, Kong D (2017) Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images. Med Phys 44(5):1678–1691CrossRef

19.

Sudha S, Jayanthi KB, Rajasekaran C, Madian N, Sunder T (2018) Convolutional neural network for segmentation and measurement of intima media thickness. J Med Syst 42(8):154CrossRef

20.

Řiha K and Igor P (2009) The sequential detection of artery sectional area using optical flow technique 8th WSEAS International Conference on Circuits, systems, electronics, control & signal processing, World Scientific and Engineering Academy and Society (WSEAS)

21.

Řiha K, Peng C, Dongmei F (2008) Detection of artery section area using artificial immune system algorithm. 7th WSEAS International Conference on Circuits, systems, electronics, control & signal processing, World Scientific and Engineering Academy and Society (WSEAS)

22.

Girshick R, Donahue J, Darrell T, Malik J (2015) Region-based convolutional networks for accurate object detectionand segmentation. TPAMI

23.

Girshick R (2015) Fast r-CNN. IEEE international conference on computer vision 1440-1448

24.

He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. European Conference on Computer Vision, Springer, Cham, pp 346–361

25.

Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Proces Syst:91–99

26.

Chan V, Perlas A Basics of ultrasound imaging. Atlas of ultrasound-guided procedures in interventional pain management. Springer, New York, pp 13–19

27.

Soldati G, Smargiassi A, Inchingolo R, Sher S, Valente S, Corbo GM (2013) Ultrasound-guided pleural puncture in supine or recumbent lateral position - feasibility study. Multidiscipl Respiratory Med 8(1):8–18CrossRef

28.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. IEEE conference on computer vision and pattern recognition 770–778

29.

Hosang J, Benenson R, Dollár P, Schiele B (2016) What makes for effective detection proposals? IEEE Trans Pattern Anal Mach Intell 38(4):814–830CrossRef

30.

Ultrasound image data set B-mode ultrasound images of the carotid artery transverse section are downloaded from www.splab.cz (accessed in April 2017)

Titel: Localization of common carotid artery transverse section in B-mode ultrasound images using faster RCNN: a deep learning approach
verfasst von: Pankaj K. Jain
Saurabh Gupta
Arnav Bhavsar
Aditya Nigam
Neeraj Sharma
Publikationsdatum: 02.01.2020
Verlag: Springer Berlin Heidelberg
Erschienen in: Medical & Biological Engineering & Computing / Ausgabe 3/2020
Print ISSN: 0140-0118
Elektronische ISSN: 1741-0444
DOI: https://doi.org/10.1007/s11517-019-02099-3

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Weitere Artikel der Ausgabe 3/2020

Real-time prediction of tumor motion using a dynamic neural network

Gait event detection using inertial measurement units in people with transfemoral amputation: a comparative study

Automatic lesion segmentation and classification of hepatic echinococcosis using a multiscale-feature convolutional neural network

A new method for measurement of motor unit action potential duration based on correlation, a pilot study

A high-fidelity 3D S-FEM stress analysis of a highly heterogeneous swine skull

Effect of stenosis shape on the sound emitted from a constricted blood vessel

Premium Partner