In the clinical analysis of Intravascular ultrasound (IVUS) images, the lumen size is an important indicator of coronary atherosclerosis, and is also the premise of coronary artery disease diagnosis and interventional treatment. In this study, a fully automatic method based on deep learning model and handcrafted features is presented for the detection of the lumen borders in IVUS images. First, 193 handcrafted features are extracted from the IVUS images. Then hybrid feature vectors are constructed by combining handcrafted features with 64 high-level features extracted from U-Net. In order to obtain the feature subsets with larger contribution, we employ the extended binary cuckoo search for feature selection. Finally, the selected 36-dimensional hybrid feature subset is used to classify the test images using dictionary learning based on kernel sparse coding. The proposed algorithm is tested on the publicly available dataset and evaluated using three indicators. Through ablation experiments, mean value of the experimental results (Jaccard: 0.88, Hausdorff distance: 0.36, Percentage of the area difference: 0.06) prove to be effective improving lumen border detection. Furthermore, compared with the recent methods used on the same dataset, the proposed method shows good performance and high accuracy.
ZhangXMckayCR.Tissue characterization in intravascular ultrasound images. IEEE Trans Med Imaging. 1998;17:889-99.
3.
WallerBFPinkertonCASlackJD.Intravascular ultrasound: a histologic study of vessels during life. Circulation. 1992;85:2305-10.
4.
Lo VercioLOrlandoJIdel FresnoMLarrabideI.Assessment of image features for vessel wall segmentation in intravascular ultrasound images. Int J Comput Ass Rad. 2016;11:1397-1407.
5.
BaloccoSGattaCCiompiFWahleARadevaPCarlierS, et al. Standardized evaluation methodology and reference database for evaluating IVUS image segmentation. Comput Med Imag Grap. 2014;38:70-90.
6.
KatouzianAAngeliniEDCarlierSGSuriJSNavabNLaineAF.A state-of-the-art review on segmentation algorithms in intravascular ultrasound (IVUS) images. IEEE T Inf Technol B. 2012;16:823-34.
7.
NobleJABoukerrouiD.Ultrasound image segmentation: a survey. IEEE T Med Imaging. 2006;25:987-1010.
8.
SwarnalathaAManikandanM.Review of segmentation techniques for intravascular ultrasound (IVUS) images. In: Fourth International Conference on Signal Processing, Communication and Networking; IEEE; 2017. pp. 1-4.
9.
SonkaMZhangXSiebesMBissingMSDeJongSCCollinsSM, et al. Segmentation of intravascular ultrasound images: a knowledge-based approach. IEEE T Med Imaging. 1995;14:719-32.
10.
ShekharRCothrenRMVinceDGChandraSThomasJDCornhillJF.Three-dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images. Comput Med Imag Grap. 1999;23:299-309.
11.
FinetGMaurincommeEReiberJCSavalleLMagninIBeauneJ.Evaluation of an automatic intraluminal edge detection technique for intravascular ultrasound images. Jpn Circulation J. 1998;62:115-21.
12.
BrusseauEDe-KorteCLMastikFSchaarJVan-Der-SteenAF.Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach. IEEE T Med Imaging. 2004;23:554-66.
13.
GilDHernándezARodriguezOMauriJRadevaP.Statistical strategy for anisotropic adventitia modelling in IVUS. IEEE T Med Imaging. 2006;25:768-78.
14.
HammoucheACloutierGTardifJCMeunierJ.Space curve approach for IVUS image segmentation. In: 2018 IEEE Life Sciences Conference; IEEE; 2018. pp. 37-40.
15.
SainiKDewalMLRohitM.Ultrasound imaging and image segmentation in the area of ultrasound: a review. Int J Adv Sci Tec. 2010;24.
16.
ChenFMaRLiuJZhuMLiaoH.Lumen and media-adventitia border detection in IVUS images using texture enhanced deformable model. Comput Med Imag Grap. 2018;66:1-13.
17.
CiompiFPujolOGattaCAlbertiMBaloccoSCarrilloX, et al. HoliMAb: a holistic approach for Media-Adventitia border detection in intravascular ultrasound. Med Image Anal. 2012;16:1085-100.
18.
WangYQiuCJiangJXiaS.Detecting the media-adventitia border in intravascular ultrasound images through a classification-based spproach. Ultrason Imaging. 2019;41:78-93.
19.
EasleyGLabateDLimWQ.Sparse directional image representations using the discrete shearlet transform. Appl Comput Harmon A. 2008;25:25-46.
20.
ZhouSShiJZhuJCaiYWangR.Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image. Biomed Signal Proces. 2013;8:688-96.
21.
LiuTXieSYuJNiuLSunW.Classification of thyroid nodules in ultrasound images using deep model based transfer learning and hybrid features. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing; IEEE; 2017. pp. 919-23.
22.
OrlandoJIProkofyevaEdel-FresnoMBlaschkoMB.An ensemble deep learning based approach for red lesion detection in fundus images. Comput Meth Prog Bio. 2018;153: 115-27.
23.
RonnebergerOFischerPBroxT.U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention; Springer; 2015. pp. 234-41.
24.
ZhaoZMorstatterFSharmaSAlelyaniSAnandALiuH. Advancing feature selection research. ASU Featur Sel Repos. 2010:1-28.
25.
WangYYPengWXQiuCHJiangJXiaSR.Fractional-order Darwinian PSO-based feature selection for media-adventitia border detection in intravascular ultrasound images. Ultrasonics. 2019;92:1-7.
26.
YangXSDebS.Cuckoo search via Lévy flights. In: 2009 World Congress on Nature & Biologically Inspired Computing; IEEE; 2009. pp. 210-4.
27.
CiviciogluPBesdokE.A conceptual comparison of the cuckoo search, particle swarm optimization, differential evolution and artificial bee colony algorithms. Artif Intell Rev. 2013;39:315-46.
GandomiAHYangXAlaviAHAlaviAH.Cuckoo search algorithm: a metaheuristic approach to solve structural optimization problems. Eng Comput. 2013;29:17-35.
30.
Duarte-CarvajalinoJMSapiroG.Learning to sense sparse signals: simultaneous sensing matrix and sparsifying dictionary optimization. IEEE T Image Process. 2009;18:1395-408.
31.
YangJYuKGongYHuangTS. Linear spatial pyramid matching using sparse coding for image classification. Proc CVPR IEEE. 2009:1794-801.
32.
ZhangTGhanemBLiuSXuCSAhujaN.Low-rank sparse coding for image classification. In: Proceedings of the IEEE International Conference on Computer Vision; 2013. pp. 281-8.
33.
ChenPCPavlidisT.Segmentation by texture using a co-occurrence matrix and a split-and-merge algorithm. Comput Vision Graph. 1979;10:172-82.
34.
SohLKTsatsoulisC.Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE T Geosci Remote. 1999;37:780-95.
35.
OjalaTPietikainenMMaenpaaT.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE T Pattern Anal. 2002;24:971-87.
36.
DalalNTriggsB. Histograms of oriented gradients for human detection. In: 2005 IEEE Comput Soc Conf Comput Vis Pattern Recognit; 2015:886-893.
37.
KutyniokGLimWReisenhoferR.ShearLab 3D: faithful digital shearlet transforms based on compactly supported shearlets. ACM T Math Software. 2016:42:1-42.
38.
LongJShelhamerEDarrellT. Fully convolutional networks for semantic segmentation. In: Proc IEEE Conf Comput Vis Pattern Recognit; 2015:3431-3440.
39.
BahetiBInnaniSGajreSTalbarS.Semantic scene segmentation in unstructured environment with modified DeepLabV3+. Pattern Recogn Lett. 2020;138:223-9.
40.
SalesiSCosmaG.A novel extended binary cuckoo search algorithm for feature selection. In: 2017 2nd International Conference on Knowledge Engineering and Applications; IEEE; 2017. pp. 6-12.
41.
ManjónJVCoupéPMartí-BonmatíLCollinsD-LRoblesM.Adaptive non-local means denoising of MR images with spatially varying noise levels. Jmri-J Magn Reson Im. 2010;31: 192-203.
42.
EladMAharonM.Image denoising via sparse and redundant representations over learned dictionaries. IEEE T Image Process. 2006;15:3736-45.
43.
BrytOEladM.Compression of facial images using the K-SVD algorithm. J Vis Commun Image R. 2008;19:270-82.
44.
DongWZhangLShiG.Centralized sparse representation for image restoration. In: 2011 International Conference on Computer Vision; IEEE; 2011. p. 1259-66.
45.
SivaramGSNemalaSKElhilaliMTranTDHermanskyH. Sparse coding for speech recognition. In: 2010 IEEE Int Conf Acoust Speech Signal Process; 2010:4346-4349. http://doi.org/10.1109/ICASSP.2010.5495649.
46.
TongJZhaoYZhangPChenLJiangL.MRI brain tumor segmentation based on texture features and kernel sparse coding. Biomed Signal Proces. 2019;47:387-92.
47.
TongJZhangPWengYZhuD.Kernel sparse representation for MRI image analysis in automatic brain tumor segmentation. Front Inform Tech El. 2018;19:471-80.
48.
CristianiniNShawe-TaylorJ.An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, 2000.
49.
Lo VercioLFresnoMDLarrabideI.Lumen-intima and media-adventitia segmentation in IVUS images using supervised classifications of arterial layers and morphological structures. Comput Meth Prog Bio. 2019;177:113-21.
50.
SuSHuZLinQHauWKGaoZZhangH.An artificial neural network method for lumen and media-adventitia border detection in IVUS. Comput Med Imag Grap. 2016;57:29.
51.
FarajiMChengINaudinIBasuA.Segmentation of arterial walls in intravascular ultrasound cross-sectional images using extremal region selection. Ultrasonics. 2018;84:356-65.
52.
KermaniAAyatollahiA.A new nonparametric statistical approach to detect lumen and Media-Adventitia borders in intravascular ultrasound frames. Comput Biol Med. 2019;104: 10-28.
53.
HammoucheACloutierGTardifJHammoucheKMeunierJ.Automatic IVUS lumen segmentation using a 3D adaptive helix model. Comput Biol Med. 2019;107:58-72.
54.
JodasDSPereiraASTavaresJMR. Automatic segmentation of the lumen region in intravascular images of the coronary artery. Med Image Anal. 2017;40:60-79.
55.
UnalGBucherSCarlierSGSlabaughGGFangTTanakaK.Shape-driven segmentation of the arterial wall in intravascular ultrasound images. IEEE T Inf Technol B. 2008;12:335-47.
56.
CasellesVKimmelRSapiroG.Geodesic active contours. Int J Comput Vision. 1997;22:61-79.
57.
Mendizabal-RuizEGRiveraMKakadiarisIA.Segmentation of the luminal border in intravascular ultrasound B-mode images using a probabilistic approach. Med Image Anal. 2013; 17:649-70.
58.
GoodfellowIJPouget-AbadieJMirzaMXuBWarde-FarleyDOzairS, et al. Generative adversarial nets. NIPS. 2014.
