nach oben

Journal of Medical Systems

Erschienen in:

01.05.2019 | Image & Signal Processing

Coronary Calcium Detection Based on Improved Deep Residual Network in Mimics

verfasst von: Chen Datong, Liang Minghui, Jin Cheng, Sun Yue, Xu Dongbin, Lin Yueming

Erschienen in: Journal of Medical Systems | Ausgabe 5/2019

Einloggen, um Zugang zu erhalten

Abstract

Coronary calcium detection in medicine image processing is a hot research topic. According to the low resolution and complex background in medicine image, an improved coronary calcium detection algorithm based on the Single Shot MultiBox Detector (SSD) in Mimics is proposed in this paper. The algorithm firstly uses the aggregate channel feature model to preprocess the image to obtain the suspected calcium area, which greatly reduces the time of single-frame image detection. The basic network VGG-16 is replaced by Resnet-50, which introduces the identity mapping to solve the problem of reducing the detection accuracy when the number of network layers are increased. Finally, the powerful and flexible two-parameter loss function is used to optimize the training deep network and improve the network model generalization ability. Qualitative and quantitative experiments show that the performance of the proposed detection algorithm exceeds the existing calcium detection algorithms, and the detection efficiency is improved while ensuring the accuracy of calcium detection.

Mcclelland, R. L., Jorgensen, N. W., Budoff, M. J. et al., 10-year coronary heart disease risk prediction using coronary artery calcium and traditional risk factors: Derivation in the MESA (multi-ethnic study of atherosclerosis) with validation in the HNR (Heinz Nixdorf Recall) study and the DHS (Dallas Heart Study).[J]. J. Am. Coll. Cardiol. 66(15):1643–1653, 2015.CrossRef

Hecht, H. S., Coronary artery calcium scanning: Past, present, and future[J]. JACC Cardiovasc. Imaging 8(5):579–596, 2015.CrossRef

Rahhal, M. M., Bazi, Y., Alhichri, H. S. et al., Deep learning approach for active classification of electrocardiogram signals[J]. Inf. Sci. 345(345):340–354, 2016.CrossRef

Moeskops P, Moeskops P, Wolterink J M, et al. Deep learning for multi-task medical image segmentation in multiple modalities[C]. Medical Image Computing and Computer-Assisted Intervention: 478–486, 2016.

Wolterink, J. M., Leiner, T., Takx, R. A. et al., Automatic coronary calcium scoring in non-contrast-enhanced ECG-triggered cardiac CT with ambiguity detection[J]. IEEE Trans. Med. Imaging 34(9):1867–1878, 2015.CrossRef

Lloydjones, D. M., Coronary artery calcium scoring: Are we there yet?[J]. J. Am. Coll. Cardiol. 66(15):1654–1656, 2015.CrossRef

Araki, T., Ikeda, N., Dey, N. et al., Shape-based approach for coronary calcium lesion volume measurement on intravascular ultrasound imaging and its association with carotid intima-media thickness[J]. J. Ultrasound Med. 34(3):469–482, 2015.CrossRef

Chaikriangkrai, K., Valderrabano, M., Bala, S. K. et al., Abstract 491: Detection of subclinical coronary artery disease by calcium score in patients with atrial fibrillation: Potential clinical implications[J]. Arterioscler. Thromb. Vasc. Biol., 2015.

Vonder, M., Pelgrim, G. J., Huijsse, S. E. et al., Feasibility of spectral shaping for detection and quantification of coronary calcifications in ultra-low dose CT[J]. Eur. Radiol. 27(5):2047–2054, 2017.CrossRef

10.

Qanadli, S. D., Qanadli, S. D., Jouannic, A. et al., CT attenuation values of blood and myocardium: Rationale for accurate coronary artery calcifications detection with multi-detector CT.[J]. PLoS ONE 10(4), 2015.CrossRef

11.

Antonopoulos, A. S., Sanna, F., Sabharwal, N. et al., Detecting human coronary inflammation by imaging perivascular fat[J]. Sci. Transl. Med. 9(398), 2017.CrossRef

12.

Greenland, P., Blaha, M. J., Budoff, M. J. et al., Coronary calcium score and cardiovascular risk[J]. J. Am. Coll. Cardiol. 72(4):434–447, 2018.CrossRef

13.

Chang, H., Lin, F. Y., Lee, S. et al., Coronary atherosclerotic precursors of acute coronary syndromes[J]. J. Am. Coll. Cardiol. 71(22):2511–2522, 2018.CrossRef

14.

Suzuki, K., Overview of deep learning in medical imaging[J]. Radiol. Phys. Technol. 10(3):257–273, 2017.CrossRef

15.

Mahabadi, A. A., and Rassaf, T., Imaging of coronary inflammation for cardiovascular risk prediction[J]. Lancet 392(10151):894–896, 2018.CrossRef

16.

Sun, J., Cerebral micro-bleeding identification based on nine-layer convolutional neural network with stochastic pooling, Concurrency and Computation: Practice and Experience, 2019. doi: https://doi.org/10.1002/cpe.5130.

17.

LeCun, Y., Bengio, Y., and Hinton, G., Deep learning[J]. nature 521(7553):436, 2015.CrossRef

18.

Erhan, D., Bengio, Y., Courville, A. et al., Why does unsupervised pre-training help deep learning?[J]. J. Mach. Learn. Res. 11(Feb):625–660, 2010.

19.

Liu, W., Anguelov, D., Erhan, D., et al. Ssd: Single shot multibox detector[C]//European conference on computer vision. Springer, Cham: 21–37, 2016.CrossRef

20.

Han, S., Mao, H., and Dally, W. J., Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding[J]. arXiv preprint arXiv:1510.00149, 2015.

21.

Yang, B., Yan, J., Lei, Z., et al., Aggregate channel features for multi-view face detection[C]//Biometrics (IJCB), 2014 IEEE International Joint Conference on. IEEE, 1–8, 2014.

22.

He, K., Gkioxari, G., Dollár, P., et al., Mask r-cnn[C]//Computer Vision (ICCV), 2017 IEEE International Conference on. IEEE, 2980–2988, 2017.

23.

Szegedy, C., Ioffe, S., Vanhoucke, V., et al., Inception-v4, inception-resnet and the impact of residual connections on learning[C]//AAAI, 4:12, 2017.

24.

Targ, S., Almeida, D., and Lyman, K., Resnet in Resnet: generalizing residual architectures[J]. arXiv preprint arXiv:1603.08029, 2016.

25.

Sünderhauf, N., Shirazi, S., Dayoub, F., et al., On the performance of convnet features for place recognition[C]//Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on. IEEE, 4297–4304, 2015.

26.

Redmon, J., Divvala, S., Girshick, R., et al., You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 779–788, 2016.

27.

Ren, S., He, K., Girshick, R., et al., Faster r-cnn: Towards real-time object detection with region proposal networks[C]//Advances in neural information processing systems. 91–99, 2015.

Titel: Coronary Calcium Detection Based on Improved Deep Residual Network in Mimics
verfasst von: Chen Datong
Liang Minghui
Jin Cheng
Sun Yue
Xu Dongbin
Lin Yueming
Publikationsdatum: 01.05.2019
Verlag: Springer US
Erschienen in: Journal of Medical Systems / Ausgabe 5/2019
Print ISSN: 0148-5598
Elektronische ISSN: 1573-689X
DOI: https://doi.org/10.1007/s10916-019-1218-4

Springer Medizin

Abstract

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 5/2019

IFHDS: Intelligent Framework for Securing Healthcare BigData

Patient-Specific Seizure Detection Method using Hybrid Classifier with Optimized Electrodes

Discussion on the Application of Multi-modal Magnetic Resonance Imaging Fusion in Schizophrenia

Discussion on Patients with Bipolar Disorder and Depressive Episode by Ratio Low Frequency Amplitude Combined with Grey Matter Volume Analysis

A Clinical Support System for Brain Tumor Classification Using Soft Computing Techniques

Design of a Secure Three-Factor Authentication Scheme for Smart Healthcare