Radiomics and Artificial Neural Networks Modelling for Identification of High-risk Carotid Plaques

Overview

Journal Front Cardiovasc Med

Specialty Cardiology & Vascular Diseases

Date 2023 Jul 24

PMID 37485276

Authors

Chengzhi Gui

Chen Cao

Xin Zhang

Jiaxin Zhang

Guangjian Ni

Dong Ming

Affiliations

Soon will be listed here.

Abstract

Objective: In this study, we aimed to investigate the classification of symptomatic plaques by evaluating the models generated via two different approaches, a radiomics-based machine learning (ML) approach, and an end-to-end learning approach which utilized deep learning (DL) techniques with several representative model frameworks.

Methods: We collected high-resolution magnetic resonance imaging (HRMRI) data from 104 patients with carotid artery stenosis, who were diagnosed with either symptomatic plaques (SPs) or asymptomatic plaques (ASPs), in two medical centers. 74 patients were diagnosed with SPs and 30 patients were ASPs. Sampling Perfection with Application-optimized Contrasts (SPACE) by using different flip angle Evolutions was used for MRI imaging. Repeated stratified five-fold cross-validation was used to evaluate the accuracy and receiver operating characteristic (ROC) of the trained classifier. The two proposed approaches were investigated to train the models separately. The difference in the model performance of the two proposed methods was quantitatively evaluated to find a better model to differentiate between SPs and ASPs.

Results: 3D-SE-Densenet-121 model showed the best performance among all prediction models (AUC, accuracy, precision, sensitivity, and F1-score of 0.9300, 0.9308, 0.9008, 0.8588, and 0.8614, respectively), which were 0.0689, 0.1119, 0.1043, 0.0805, and 0.1089 higher than the best radiomics-based ML model (MLP). Decision curve analysis showed that the 3D-SE-Densenet-121 model delivered more net benefit than the best radiomics-based ML model (MLP) with a wider threshold probability.

Conclusion: The DL models were able to accurately differentiate between symptomatic and asymptomatic carotid plaques with limited data, which outperformed radiomics-based ML models in identifying symptomatic plaques.

References

Sauerbrei W, Royston P, Binder H . Selection of important variables and determination of functional form for continuous predictors in multivariable model building. Stat Med. 2007; 26(30):5512-28. DOI: 10.1002/sim.3148. View

Huang Z, Cheng X, Liu H, Bi X, Liu Y, Lv W . Relation of Carotid Plaque Features Detected with Ultrasonography-Based Radiomics to Clinical Symptoms. Transl Stroke Res. 2021; 13(6):970-982. DOI: 10.1007/s12975-021-00963-9. View

Roth H, Lu L, Liu J, Yao J, Seff A, Cherry K . Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation. IEEE Trans Med Imaging. 2015; 35(5):1170-81. PMC: 7340334. DOI: 10.1109/TMI.2015.2482920. View

Barnett H, Taylor D, Eliasziw M, Fox A, Ferguson G, Haynes R . Benefit of carotid endarterectomy in patients with symptomatic moderate or severe stenosis. North American Symptomatic Carotid Endarterectomy Trial Collaborators. N Engl J Med. 1998; 339(20):1415-25. DOI: 10.1056/NEJM199811123392002. View

van Griethuysen J, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77(21):e104-e107. PMC: 5672828. DOI: 10.1158/0008-5472.CAN-17-0339. View

Kakkos S, Stevens J, Nicolaides A, Kyriacou E, Pattichis C, Geroulakos G . Texture analysis of ultrasonic images of symptomatic carotid plaques can identify those plaques associated with ipsilateral embolic brain infarction. Eur J Vasc Endovasc Surg. 2006; 33(4):422-9. DOI: 10.1016/j.ejvs.2006.10.018. View

Le E, Rundo L, Tarkin J, Evans N, Chowdhury M, Coughlin P . Assessing robustness of carotid artery CT angiography radiomics in the identification of culprit lesions in cerebrovascular events. Sci Rep. 2021; 11(1):3499. PMC: 7876096. DOI: 10.1038/s41598-021-82760-w. View

Turan T, Rumboldt Z, Granholm A, Columbo L, Welsh C, Lopes-Virella M . Intracranial atherosclerosis: correlation between in-vivo 3T high resolution MRI and pathology. Atherosclerosis. 2014; 237(2):460-3. PMC: 4262631. DOI: 10.1016/j.atherosclerosis.2014.10.007. View

Sacchetti D, Cutting S, McTaggart R, Chang A, Hemendinger M, Mac Grory B . Perfusion imaging and recurrent cerebrovascular events in intracranial atherosclerotic disease or carotid occlusion. Int J Stroke. 2018; 13(6):592-599. DOI: 10.1177/1747493018764075. View

10.

Hwang J, Seo J, Kim J, Park S, Kim Y, Kim K . Comparison between Deep Learning and Conventional Machine Learning in Classifying Iliofemoral Deep Venous Thrombosis upon CT Venography. Diagnostics (Basel). 2022; 12(2). PMC: 8871174. DOI: 10.3390/diagnostics12020274. View

11.

Chen S, Liu C, Chen X, Liu W, Ma L, Zha Y . A Radiomics Approach to Assess High Risk Carotid Plaques: A Non-invasive Imaging Biomarker, Retrospective Study. Front Neurol. 2022; 13:788652. PMC: 8957977. DOI: 10.3389/fneur.2022.788652. View

12.

Leng X, Wong K, Liebeskind D . Evaluating intracranial atherosclerosis rather than intracranial stenosis. Stroke. 2014; 45(2):645-51. PMC: 3957430. DOI: 10.1161/STROKEAHA.113.002491. View

13.

Anzidei M, Napoli A, Cavallo Marincola B, Nofroni I, Geiger D, Zaccagna F . Gadofosveset-enhanced MR angiography of carotid arteries: does steady-state imaging improve accuracy of first-pass imaging? Comparison with selective digital subtraction angiography. Radiology. 2009; 251(2):457-66. DOI: 10.1148/radiol.2512081197. View

14.

Kopczak A, Schindler A, Bayer-Karpinska A, Koch M, Sepp D, Zeller J . Complicated Carotid Artery Plaques as a Cause of Cryptogenic Stroke. J Am Coll Cardiol. 2020; 76(19):2212-2222. DOI: 10.1016/j.jacc.2020.09.532. View

15.

Jiang Y, Zhu C, Peng W, Degnan A, Chen L, Wang X . Ex-vivo imaging and plaque type classification of intracranial atherosclerotic plaque using high resolution MRI. Atherosclerosis. 2016; 249:10-6. PMC: 4879074. DOI: 10.1016/j.atherosclerosis.2016.03.033. View

16.

Cao C, Liu Z, Liu G, Jin S, Xia S . Ability of weakly supervised learning to detect acute ischemic stroke and hemorrhagic infarction lesions with diffusion-weighted imaging. Quant Imaging Med Surg. 2022; 12(1):321-332. PMC: 8666772. DOI: 10.21037/qims-21-324. View

17.

Zhang R, Zhang Q, Ji A, Lv P, Zhang J, Fu C . Identification of high-risk carotid plaque with MRI-based radiomics and machine learning. Eur Radiol. 2020; 31(5):3116-3126. DOI: 10.1007/s00330-020-07361-z. View

18.

Li H, Liu J, Dong Z, Chen X, Zhou C, Huang C . Identification of high-risk intracranial plaques with 3D high-resolution magnetic resonance imaging-based radiomics and machine learning. J Neurol. 2022; 269(12):6494-6503. DOI: 10.1007/s00415-022-11315-4. View

19.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

20.

Naghavi M, Libby P, Falk E, Casscells S, Litovsky S, Rumberger J . From vulnerable plaque to vulnerable patient: a call for new definitions and risk assessment strategies: Part I. Circulation. 2003; 108(14):1664-72. DOI: 10.1161/01.CIR.0000087480.94275.97. View