Atherosclerosis Detection using Autoencoders Applied to MR Images
Main Article Content
Abstract
The early detection of atherosclerosis has been the interest of researchers in order to prevent diseases progression. And, most of cases diagnosed with atherosclerosis in late stages resulted of subjective ways of diagnosis in the healthcare sector.
Consequently, in order to help cardiologists diagnose atherosclerosis in early stages with an objective, fast and accurate way, we are proposing a machine learning model based on autoencoders that enables atherosclerosis detection from MRI images of murine subjects.
This novel way of automated system consists of applying various image processing techniques on the input MRI images. Then, after training, testing and validation it will be capable of classifying the images as atherosclerotic or not based on a specific threshold for the reconstruction error calculated from the autoencoders' output.
An autoencoder is a feed-forward neural network that has its input neurons equal to the output neuron. The classification works by comparing the reconstructed images to the original input images and evaluating loss between them. Since the autoencoder is trained on healthy images, reconstruction error of the healthy images would be low while that of atherosclerotic subjects would be higher. By setting a threshold for the loss, we can classify the images as healthy or atherosclerotic.
The pre-processing of these images was made using a Block Matching 3D (BM3D) filter to remove the noise in the images prior to application of a Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the contrast. The next step included introducing the dataset into the autoencoder to start training on the healthy images, after increasing the images number with augmentation.
The results showed a reconstruction loss of 0.018 while using the stacked architecture of the autoencoder and 0.0366 when using the convolutional autoencoder architecture.
Article Details
The Medical Research Archives grants authors the right to publish and reproduce the unrevised contribution in whole or in part at any time and in any form for any scholarly non-commercial purpose with the condition that all publications of the contribution include a full citation to the journal as published by the Medical Research Archives.
References
2. Cleveland Clinic. Atherosclerosis: Risk Factors, Symptoms & Treatment. Retrieved from https://my.clevelandclinic.org/health/diseases/16753-atherosclerosis-arterial-disease
3. WebMD. Atherosclerosis. Retrieved from https://www.webmd.com/heart-disease/what-is-atherosclerosis
4. Erbel R, Lehmann N, Möhlenkamp S, et al. Subclinical coronary atherosclerosis predicts cardiovascular risk in different stages of hypertension. Hypertension. 2012; 59(1):44-53. doi:10.1161/hypertensionaha.111.180489
5. Bentzon JF, Otsuka F, Virmani R, Falk E. Mechanisms of plaque formation and rupture. Circulation Research. 2014; 114(12):1852-1866. doi:10.1161/CIRCRESAHA.114.302721
6. Rossi A, Merkus D, Klotz E, et al. Stress-induced changes of myocardial perfusion imaging in patients undergoing computed tomography- and catheter-based invasive coronary angiography. European Heart Journal Cardiovascular Imaging. 2013; 14(7):624-631. doi:10.1093/ehjci/jet315
7. Rudd JHF, Myers KS, Bansilal S, et al. Atherosclerosis inflammation imaging with 18F-FDG PET: Carotid, iliac, and femoral uptake reproducibility, quantification methods, and recommendations. Journal of Nuclear Medicine. 2008; 49(6):871-878. doi:10.2967/jnumed.107.050294
8. Mintz GS, Popma JJ, Pichard AD, Kent KM, Satler LF. Intravascular ultrasound: clinical, angiographic, and intravascular ultrasound parameters. American Heart Journal. 2001; 142(2):200-203.
9. Nair A, Kuban BD, Tuzcu EM, Schoenhagen P, Nissen SE. Coronary plaque classification with intravascular ultrasound radiofrequency data analysis. Circulation. 2002; 106(17):2200-2206.
10. Stein JH, Korcarz CE, Hurst RT, et al. Use of carotid ultrasound to identify subclinical vascular disease and evaluate cardiovascular disease risk: a consensus statement from the American Society of Echocardiography Carotid Intima-Media Thickness Task Force. Journal of the American Society of Echocardiography. 2008; 21(2):93-111.
11. Vernhet H. Carotid Doppler ultrasound investigation of the vessel wall. European Journal of Vascular and Endovascular Surgery. 2009; 37(3):268-275.
12. ten Kate GL, van den Oord SC, Sijbrands EJ, et al. Current status and future developments of contrast-enhanced ultrasound of carotid atherosclerosis. Journal of Vascular Surgery. 2012; 56(6):1651-1658.
13. Tutar O, Turhan H, Ertas F, et al. Assessment of plaque stiffness by shear wave elastography in patients with stable and unstable carotid artery disease. Medical Science Monitor. 2016; 22:2537-2544.
14. Falk E. Pathogenesis of atherosclerosis. Journal of the American College of Cardiology. 2013; 41(7):S7-S12.
15. White CW, Wright CB, Doty DB, et al. Does visual interpretation of the coronary arteriogram predict the physiologic importance of a coronary stenosis? New England Journal of Medicine. 1984; 310(13) :819-824.
16. Mintz GS, Popma JJ, Pichard AD, Kent KM, Satler LF. Intravascular ultrasound: clinical, angiographic, and intravascular ultrasound parameters. American Heart Journal. 2001; 142(2):200-203.
17. Tearney GJ, Regar E, Akasaka T, et al. Consensus standards for acquisition, measurement, and reporting of intravascular optical coherence tomography studies: a report from the International Working Group for Intravascular Optical Coherence Tomography Standardization and Validation. Journal of the American College of Cardiology. 2012; 59(12):1058-1072.
18. Goldstein JA, Gallagher MJ, O'Neill WW, et al. A randomized controlled trial of multi-slice coronary computed tomography for evaluation of acute chest pain. JACC: Cardiovascular Imaging. 2007; 50(7):581-586.
19. Maffei E, Seitun S, Martini C, Cademartiri F. Coronary CT angiography in the assessment of coronary artery disease: current and emerging applications. BioMed Research International. 2012; 2012.
20. Budoff MJ, Shaw LJ, Liu ST, et al. Long-term prognosis associated with coronary calcification: observations from a registry of 25,253 patients. Journal of the American College of Cardiology. 2006; 47(11):2229-2237.
21. Raff GL, Gallagher MJ, O'Neill WW, Goldstein JA, O'Neil BJ. Diagnostic accuracy of noninvasive coronary angiography using 64-slice spiral computed tomography. Journal of the American College of Cardiology. 2005; 46(3):552-557.
22. Fayad ZA, Mani V, Woodward M. Molecular imaging of atherosclerosis: clinical state-of-the-art. Heart. 2008; 94(7):949-959.
23. Saam T, Ferguson MS, Yarnykh VL, et al. Quantitative evaluation of carotid plaque composition by in vivo MRI. Arteriosclerosis, Thrombosis, and Vascular Biology. 2005; 25(1):234-239.
24. Botnar RM, Fayad ZA. Molecular imaging of atherosclerosis. In: Handbook of Experimental Pharmacology. Springer; 2008:455-487.
25. Saam T, Hatsukami TS, Takaya N, et al. The vulnerable, or high-risk, atherosclerotic plaque: noninvasive MR imaging for characterization and assessment. Radiology. 2007; 244(1):64-77.
26. Zhao XQ, Yuan C, Hatsukami TS, Phan BA. Imaging atherosclerosis with MRI: present and future. Journal of Magnetic Resonance Imaging. 2011; 34(6):1323-1336.
27. Yuan C, Kerwin WS, Yarnykh VL, et al. MRI of atherosclerosis in clinical trials. NMR in Biomedicine. 2006; 19(6):636-654.
28. Sabbah MM, Abou Adla YA, Kasab MW, Al-Ghourabi MI, Diab MO, Aloulou NJ. Murine atherosclerosis detection using machine learning under Magnetic Resonance Imaging. 2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES). Published online 2021. doi:10.1109 /iecbes48179.2021.9398816
29. Terrada O, Cherradi B, Raihani A, Bouattane O. Classification and prediction of atherosclerosis diseases using machine learning algorithms. 2019 5th International Conference on Optimization and Applications (ICOA). Published online 2019. doi:10.1109/ icoa.2019.8727688
30. Bank D, Koenigstein N, Giryes R. Autoencoders. 2021.
31. Shvetsova N, Bakker B, Fedulova I, Schulz H, Dylov DV. Anomaly detection in medical imaging with deep perceptual autoencoders. IEEE Access. 2021; 9:118571-118583.
32. Suganuma M, Ozay M, Okatani T. Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search. 2018.
33. Kingma DP, Welling M. An introduction to variational autoencoders. Foundations and Trends® in Machine Learning. 2019; 12(4):307-392.
34. Seyfiog˘lu MS, O¨ zbayog˘lu AM, Gu¨rbu¨z SZ. Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities. IEEE Transactions on Aerospace and Electronic Systems. 2018; 54(4):1709-1723.
35. Addo D, Zhou S, Jackson JK, et al. Evae-net: An ensemble variational autoencoder deep learning network for covid-19 classification based on chest x-ray images. Diagnostics. 2022; 12(11).
36. Zhuang F, Qi Z, Duan K, et al. A comprehensive survey on transfer learning. 2020.
37. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2015.
38. Ferguson M, ak R, Lee YT, Law K. Automatic localization of casting defects with convolutional neural networks. 2017; 12:1726–1735.
39. Gohel P, Singh P, Mohanty M. Explainable ai: current status and future directions. 2021.
40. Amann J, Blasimme A, Vayena E, et al. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC medical informatics and decision making. 2020; 20(1):1-9.
41. Alsaid H, Sabbah M, Bendahmane Z, et al. High-resolution contrast-enhanced MRI of atherosclerosis with digital cardiac and respiratory gating in mice.
42. Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3D transform-domain collaborative filtering.
43. Pizer SM, Amburn EP, Austin JD, et al. Adaptive histogram equalization and its variations.