CT angiography-based radiomics as a tool for carotid plaque characterization: a pilot study.
Angiography
Carotid
Plaques
Radiomics
Journal
La Radiologia medica
ISSN: 1826-6983
Titre abrégé: Radiol Med
Pays: Italy
ID NLM: 0177625
Informations de publication
Date de publication:
Jul 2022
Jul 2022
Historique:
received:
16
02
2022
accepted:
20
05
2022
pubmed:
11
6
2022
medline:
27
7
2022
entrez:
10
6
2022
Statut:
ppublish
Résumé
Radiomics is a quantitative method able to analyze a high-throughput extraction of minable imaging features. Herein, we aim to develop a CT angiography-based radiomics analysis and machine learning model for carotid plaques to discriminate vulnerable from no vulnerable plaques. Thirty consecutive patients with carotid atherosclerosis were enrolled in this pilot study. At surgery, a binary classification of plaques was adopted ("hard" vs "soft"). Feature extraction was performed using the R software package Moddicom. Pairwise feature interdependencies were evaluated using the Spearman rank correlation coefficient. A univariate analysis was performed to assess the association between each feature and the plaque classification and chose top-ranked features. The feature predictive value was investigated using binary logistic regression. A stepwise backward elimination procedure was performed to minimize the Akaike information criterion (AIC). The final significant features were used to build the models for binary classification of carotid plaques, including logistic regression (LR), support vector machine (SVM), and classification and regression tree analysis (CART). All models were cross-validated using fivefold cross validation. Class-specific accuracy, precision, recall and F-measure evaluation metrics were used to quantify classifier output quality. A total of 230 radiomics features were extracted from each plaque. Pairwise Spearman correlation between features reported a high level of correlations, with more than 80% correlating with at least one other feature at |ρ|> 0.8. After a stepwise backward elimination procedure, the entropy and volume features were found to be the most significantly associated with the two plaque groups (p < 0.001), with AUCs of 0.92 and 0.96, respectively. The best performance was registered by the SVM classifier with the RBF kernel, with accuracy, precision, recall and F-score equal to 86.7, 92.9, 81.3 and 86.7%, respectively. The CART classification tree model for the entropy and volume features model achieved 86.7% well-classified plaques and an AUC of 0.987. This pilot study highlighted the potential of CTA-based radiomics and machine learning to discriminate plaque composition. This new approach has the potential to provide a reliable method to improve risk stratification in patients with carotid atherosclerosis.
Identifiants
pubmed: 35680773
doi: 10.1007/s11547-022-01505-5
pii: 10.1007/s11547-022-01505-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
743-753Informations de copyright
© 2022. Italian Society of Medical Radiology.
Références
Ooi YC, Gonzalez NR (2015) Management of extracranial carotid artery disease. Cardiol Clin 33:1–35. https://doi.org/10.1016/j.ccl.2014.09.001
doi: 10.1016/j.ccl.2014.09.001
pubmed: 25439328
pmcid: 4694631
Rothwell PM, Eliasziw M, Gutnikov SA et al (2003) Analysis of pooled data from the randomized controlled trials of endarterectomy for symptomatic carotid stenosis. Lancet 361:107–116. https://doi.org/10.1016/s0140-6736(03)12228-3
doi: 10.1016/s0140-6736(03)12228-3
pubmed: 12531577
Redgrave JN, Lovett JK, Gallagher PJ, Rothwell PM (2006) Histological assessment of 526 symptomatic carotid plaques in relation to the nature and timing of ischemic symptoms: the Oxford plaque study. Circulation 113:2320–2328. https://doi.org/10.1161/CIRCULATIONAHA.105.589044
doi: 10.1161/CIRCULATIONAHA.105.589044
pubmed: 16651471
Pletsch-Borba L, Selwaness M, van der Lugt A, Hofman A, Franco OH, Vernooij MW (2018) Change in carotid plaque components: a 4-year follow-up study with serial MR imaging. JACC Cardiovasc Imaging 11:184–192. https://doi.org/10.1016/j.jcmg.2016.12.026
doi: 10.1016/j.jcmg.2016.12.026
pubmed: 28412421
Zavodni AE, Wasserman BA, McClelland RL et al (2014) Carotid artery plaque morphology and composition in relation to incident cardiovascular events: the multiethnic study of atherosclerosis (MESA). Radiology 271:381–389. https://doi.org/10.1148/radiol.14131020
doi: 10.1148/radiol.14131020
pubmed: 24592924
Zhao XQ, Hatsukami TS, Hippe DS et al (2014) Clinical factors associated with high-risk carotid plaque features as assessed by magnetic resonance imaging in patients with established vascular disease (from the AIM-HIGH study). Am J Cardiol 114:1412–1419. https://doi.org/10.1016/j.amjcard.2014.08.001
doi: 10.1016/j.amjcard.2014.08.001
pubmed: 25245415
pmcid: 4195846
Schindler A, Schinner R, Altaf N et al (2020) Prediction of stroke risk by detection of hemorrhage in carotid plaques: meta-analysis of individual patient data. JACC Cardiovasc Imaging 13(2 Pt 1):395–406. https://doi.org/10.1016/j.jcmg.2019.03.028
doi: 10.1016/j.jcmg.2019.03.028
pubmed: 31202755
Gupta A, Baradaran H, Schweitzer AD et al (2013) Carotid plaque MRI and stroke risk: a systematic review and meta-analysis. Stroke 44:3071–3077. https://doi.org/10.1161/STROKEAHA.113.002551
doi: 10.1161/STROKEAHA.113.002551
pubmed: 23988640
Saba L, Saam T, Jäger HR et al (2019) Imaging biomarkers of vulnerable carotid plaques for stroke risk prediction and their potential clinical implications. Lancet Neurol 18:559–572. https://doi.org/10.1016/S1474-4422(19)30035-3
doi: 10.1016/S1474-4422(19)30035-3
pubmed: 30954372
Howard DP, van Lammeren GW, Redgrave JN et al (2013) Histological features of carotid plaque in patients with ocular ischemia versus cerebral events. Stroke 44:734e9. https://doi.org/10.1161/STROKEAHA.112.678672
Finn AV, Nakano M, Narula J et al (2010) Concept of vulnerable/unstable plaque. Arterioscler Thromb Vasc Biol 30:1282e92. https://doi.org/10.1161/ATVBAHA.108.179739
Saba L, Anzidei M, Marincola BC et al (2014) Imaging of the carotid artery vulnerable plaque. Cardiovasc Intervent Radiol 37:572–585. https://doi.org/10.1007/s00270-013-0711-2
doi: 10.1007/s00270-013-0711-2
pubmed: 23912494
Varrassi M, Sferra R, Gravina GL et al (2019) Carotid artery plaque characterization with a wide-detector computed tomography using a dedicated post-processing 3D analysis: comparison with histology. Radiol Med 124:795–803. https://doi.org/10.1007/s11547-019-01026-8
doi: 10.1007/s11547-019-01026-8
pubmed: 30903605
Gupta A, Baradaran H, Mtui EE et al (2015) Detection of symptomatic carotid plaque using source data from MR and CT angiography: a correlative study. Cerebrovasc Dis 39:151–161. https://doi.org/10.1159/000373918
doi: 10.1159/000373918
pubmed: 25721945
U-King-Im JM, Fox AJ, Aviv RI et al (2010) Characterization of carotid plaque hemorrhage: a CT angiography and mr intraplaque hemorrhage study. Stroke 41:1623–1629. https://doi.org/10.1161/STROKEAHA.110.579474
van den Bouwhuijsen QJ, Bos D, Ikram MA et al (2015) Coexistence of calcification, intraplaque hemorrhage and lipid core within the asymptomatic atherosclerotic carotid plaque: the Rotterdam study. Cerebrovasc Dis 39:319–324. https://doi.org/10.1159/000381138
doi: 10.1159/000381138
pubmed: 25966822
Mosleh W, Adib K, Natdanai P et al (2017) High-risk carotid plaques identified by CT-angiogram can predict acute myocardial infarction. Int J Cardiovasc Imaging 33(4):561–568. https://doi.org/10.1007/s10554-016-1019-5
doi: 10.1007/s10554-016-1019-5
pubmed: 27866279
Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169
doi: 10.1148/radiol.2015151169
pubmed: 26579733
Liu Z, Wang S, Dondg D et al (2019) The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges. Theranostics 9(5):1303–1322. https://doi.org/10.7150/thno.30309
doi: 10.7150/thno.30309
pubmed: 30867832
pmcid: 6401507
Seetharam K, Brito D, Farjo PD, Sengupta PP (2020) The role of artificial intelligence in cardiovascular imaging: state of the art review. Front Cardiovasc Med 23(7):618849. https://doi.org/10.3389/fcvm.2020.618849
doi: 10.3389/fcvm.2020.618849
Kolossváry M, De Cecco CN, Feuchtner G, Maurovich-Horvat P (2019) Advanced atherosclerosis imaging by CT: Radiomics, machine learning and deep learning. J Cardiovasc Comput Tomogr 13(5):274–280. https://doi.org/10.1016/j.jcct.2019.04.007
doi: 10.1016/j.jcct.2019.04.007
pubmed: 31029649
Acharya UR, Sree SV, Mookiah MRK et al (2013) Computed tomography carotid wall plaque characterization using a combination of discrete wavelet transform and texture features: a pilot study. Proc Inst Mech Eng H 227:643–654. https://doi.org/10.1177/0954411913480622
doi: 10.1177/0954411913480622
pubmed: 23636747
Kakkos SK, Stevens JM, Nicolaides AN et al (2007) Texture analysis of ultrasonic images of symptomatic carotid plaques can identify those plaques associated with ipsilateral embolic brain infarction. Eur J Vasc Endovasc Surg 33:422–429. https://doi.org/10.1016/j.ejvs.2006.10.018
doi: 10.1016/j.ejvs.2006.10.018
pubmed: 17161964
Zhang R, Zhang Q, Ji A et al (2020) Identification of high-risk carotid plaque with MRI-based radiomics and machine learning. Eur Radiol. https://doi.org/10.1007/s00330-020-07361-z
doi: 10.1007/s00330-020-07361-z
pubmed: 33247346
pmcid: 8547260
Lee EP, Rundo L, Tarkin JM et al (2021) Assessing robustness of carotid artery CT angiography radiomics in the identification of culprit lesions in cerebrovascular events. Sci Rep 11(1):3499. https://doi.org/10.1038/s41598-021-82760-w
doi: 10.1038/s41598-021-82760-w
van Assen M, Varga-Szemes A, Schoepf UJ et al (2019) Automated plaque analysis for the prognostication of major adverse cardiac events. Eur J Radiol 116:76–83. https://doi.org/10.1016/j.ejrad.2019.04.013
doi: 10.1016/j.ejrad.2019.04.013
pubmed: 31153577
Zaccagna F, Ganeshan G, Arca M et al (2021) CT texture-based radiomics analysis of carotid arteries identifies vulnerable patients: a preliminary outcome study. Neuroradiology 63(7):1043–1052. https://doi.org/10.1007/s00234-020-02628-0
doi: 10.1007/s00234-020-02628-0
pubmed: 33392734
Barnett HJM, Taylor DW, Haynes RB et al (1991) Beneficial effect of carotid endarterectomy in symptomatic patients with high-grade carotid stenosis. N Engl J Med 325:445–453. https://doi.org/10.1056/NEJM199108153250701
doi: 10.1056/NEJM199108153250701
pubmed: 1852179
Avril G, Batt M, Guidoin R et al (1991) Carotid endarterectomy plaques: correlations of clinical and anatomic findings. Ann Vasc Surg 5:50–54. https://doi.org/10.1007/BF02021778
doi: 10.1007/BF02021778
pubmed: 1997076
Falk E, Shah PK, Fuster V (1995) Coronary plaque disruption. Circulation 92:657–671. https://doi.org/10.1161/01.cir.92.3.657
doi: 10.1161/01.cir.92.3.657
pubmed: 7634481
Dinapoli N, Alitto AR, Vallati M et al (2015) Moddicom: a complete and easily accessible library for prognostic evaluations relying on image features. Annu Int Conf IEEE Eng Med Biol Soc 771–774. https://doi.org/10.1109/EMBC.2015.7318476
Zwanenburg A, Valli`eres M, Abdalah MA, et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338. https://doi.org/10.1148/radiol.2020191145
doi: 10.1148/radiol.2020191145
pubmed: 32154773
Forghani R, Savadjiev P, Chatterjee A, Muthukrishnan N, Reinhold C, Forghani B (2019) Radiomics and artificial intelligence for biomarker and prediction model development in oncology. Comput Struct Biotechnol J 17:995–1008. https://doi.org/10.1016/j.csbj.2019.07.001
doi: 10.1016/j.csbj.2019.07.001
pubmed: 31388413
pmcid: 6667772
Huang S, Cai N, Pacheco PP, Narrandes S, Wang Y, Xu W (2018) Applications of support vector machine (svm) learning in cancer genomics. Cancer Genomics Proteomics 15:41–51. https://doi.org/10.21873/cgp.20063
doi: 10.21873/cgp.20063
pubmed: 29275361
David V, Sanchez A (2003) Advanced support vector machines and kernel methods. Neurocomputing 55:5–20
doi: 10.1016/S0925-2312(03)00373-4
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees (Wadsworth statistics/probability). Chapman & Hall, Boca Raton
Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Stat Surv 4:40–79
doi: 10.1214/09-SS054
Truijman MTB, Kool ME, van Dijk AC et al (2014) Plaque At RISK (PARISK): prospective multicenter study to improve diagnosis of high-risk carotid plaques. Int J Stroke 9(6):747–754. https://doi.org/10.1111/ijs.12167
doi: 10.1111/ijs.12167
pubmed: 24138596
Saba L, Anzidei M, Cavallo Marincola B et al (2014) Imaging of the carotid artery vulnerable plaque. Cardiovasc Intervent Radiol 37:572–585. https://doi.org/10.1007/s00270-013-0711-2
doi: 10.1007/s00270-013-0711-2
pubmed: 23912494
Naylor AR, Ricco JB, de Borst GJ et al (2017) Management of atherosclerotic carotid and vertebral artery disease: 2017 clinical practice guidelines of the European society for vascular surgery (ESVS). Eur J Vasc Endovasc Surg 55:3–81. https://doi.org/10.1016/j.ejvs.2017.06.021
doi: 10.1016/j.ejvs.2017.06.021
pubmed: 28851594
Zuccagna F, Ganeshan B, Arca M et al (2021) CT texture-based radiomics analysis of carotid arteries identifies vulnerable patients: a preliminary outcome study. Neuroradiology 63(7):1043–1052. https://doi.org/10.1007/s00234-020-02628-0
doi: 10.1007/s00234-020-02628-0
Le EPV, Rundo L, Tarkin JM et al (2021) Assessing robustness of carotid artery CT angiography radiomics in the identification of culprit lesions in cerebrovascular events. Scientifc Reports 11:3499. https://doi.org/10.1038/s41598-021-82760-w
doi: 10.1038/s41598-021-82760-w
Zhang R, Zhang Q, Ji A et al (2021) Identification of high-risk carotid plaque with MRI-based radiomics and machine learning. Eur Radiol 31:3116–3126. https://doi.org/10.1007/s00330-020-07361-z
doi: 10.1007/s00330-020-07361-z
pubmed: 33068185
Ouhlous M, Flach HZ, de Weert TT (2005) Carotid plaque composition and cerebral infarction: MR imaging study. Am J Neuroradiol 26:1044–1049
pubmed: 15891157
pmcid: 8158591
Saba L, Sanfilippo R, Sannia S et al (2012) Association between carotid artery plaque volume, composition, and ulceration: a retrospective assessment with MDCT. AJR Am J Roentgenol 199:151–15670. https://doi.org/10.2214/AJR.11.6955
doi: 10.2214/AJR.11.6955
pubmed: 22733906
Lu M, Peng P, Cui Y et al (2018) Association of progression of carotid artery wall volume and recurrent transient ischemic attack or stroke: a magnetic resonance imaging study. Stroke 49:614–620. https://doi.org/10.1161/STROKEAHA.117.019422
doi: 10.1161/STROKEAHA.117.019422
pubmed: 29382804
Yip C, Landau D, Lozarski R et al (2014) Primary esophageal cancer: heterogeneity as potential prognostic biomarker in patients treated with definitive chemotherapy and radiation therapy. Radiology 270:141–148. https://doi.org/10.1148/radiol.13122869
doi: 10.1148/radiol.13122869
pubmed: 23985274
Zhang H, Graham CM, Elci O et al (2013) Locally advanced squamous cell carcinoma of the head and neck: CT texture and histogram analysis allow independent prediction of overall survival in patients treated with induction chemotherapy. Radiology 269:801–809. https://doi.org/10.1148/radiol.13130110
doi: 10.1148/radiol.13130110
pubmed: 23912620
de Weert TT, Ouhlous M, Meijering E et al (2006) In vivo characterization and quantification of atherosclerotic carotid plaque components with multidetector computed tomography and histopathological correlation. Arterioscler Thromb Vasc Biol 26(10):2366–2372. https://doi.org/10.1161/01.ATV.0000240518.90124.57
doi: 10.1161/01.ATV.0000240518.90124.57
pubmed: 16902158
Saba L, Montisci R, Sanfilippo R, Mallarini G (2009) Multidetector row CT of the brain and carotid artery: a correlative analysis. Clin Radiol 64(8):767–778. https://doi.org/10.1016/j.crad.2009.03.009
doi: 10.1016/j.crad.2009.03.009
pubmed: 19589415
Nandalur KR, Baskurt E, Hagspiel KD et al (2005) Calcified carotid atherosclerosic plaque is associated less with ischemic symptoms than is noncalcified plaque on MDCT. AJR Am J Roentgenol 184:295–298. https://doi.org/10.2214/ajr.184.1.01840295
doi: 10.2214/ajr.184.1.01840295
pubmed: 15615991
pmcid: 2955331