Incremental Value of Radiomics Features of Epicardial Adipose Tissue for Detecting the Severity of COVID-19 Infection

Introduction. Epicardial adipose tissue (EAT) is known for its pro-inflammatory properties and association with Coronavirus Disease 2019 (COVID-19) severity. However, existing detection methods for COVID-19 severity assessment often lack consideration of organs and tissues other than the lungs, which limits the accuracy and reliability of these predictive models.
Material and methods. The retrospective study included data from 515 COVID-19 patients (Cohort 1, n=415; Cohort 2, n=100) from two centers (Shanghai Public Health Center and Brazil Niteroi Hospital) between January 2020 and July 2020. Firstly, a three-stage EAT segmentation method was proposed by combining object detection and segmentation networks. Lung and EAT radiomics features were then extracted, and feature selection was performed. Finally, a hybrid model, based on seven machine learning models, was built for detecting COVID-19 severity. The hybrid model’s performance and uncertainty were evaluated in both internal and external validation cohorts.
Results. For EAT extraction, the Dice similarity coefficients (DSC) of the two centers were 0.972 (±0.011) and 0.968 (±0.005), respectively. For severity detection, the area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) of the hybrid model increased by 0.09 (p<0.001), 19.3 % (p<0.05), and 18.0 % (p<0.05) in the internal validation cohort, and by 0.06 (p<0.001), 18.0 % (p<0.05) and 18.0 % (p<0.05) in the external validation cohort, respectively. Uncertainty and radiomics features analysis confirmed the interpretability of increased certainty in case prediction after inclusion of EAT features.
Conclusion. This study proposed a novel three-stage EAT extraction method. We demonstrated that adding EAT radiomics features to a COVID-19 severity detection model results in increased accuracy and reduced uncertainty. The value of these features was also confirmed through feature importance ranking and visualization.

1. Long B, Brady WJ, Koyfman A, Gottlieb M. Cardiovascular complications in COVID-19. The American Journal of Emergency Medicine. 2020;38(7):1504–7. DOI: 10.1016/j.ajem.2020.04.048

2. Zhu F, Zhu Z, Zhang Y, Zhu H, Gao Z, Liu X et al. Severity detection of COVID-19 infection with machine learning of clinical records and CT images. Technology and Health Care. 2022;30(6):1299–314. DOI: 10.3233/THC-220321

3. Nalliah CJ, Bell JR, Raaijmakers AJA, Waddell HM, Wells SP, Bernasochi GB et al. Epicardial Adipose Tissue Accumulation Confers Atrial Conduction Abnormality. Journal of the American College of Cardiology. 2020;76(10):1197–211. DOI: 10.1016/j.jacc.2020.07.017

4. Feng X, Li S, Sun Q, Zhu J, Chen B, Xiong M et al. Immune-Inflammatory Parameters in COVID-19 Cases: A Systematic Review and Meta-Analysis. Frontiers in Medicine. 2020;7:301. DOI: 10.3389/fmed.2020.00301

5. Kim I-C, Han S. Epicardial adipose tissue: fuel for COVID-19-induced cardiac injury? European Heart Journal. 2020;41(24):2334–5. DOI: 10.1093/eurheartj/ehaa474

6. Bihan H, Heidar R, Beloeuvre A, Allard L, Ouedraogo E, Tatulashvili S et al. Epicardial adipose tissue and severe Coronavirus Disease 19. Cardiovascular Diabetology. 2021;20(1):147. DOI: 10.1186/s12933-021-01329-z

7. Hoori A, Hu T, Al-Kindi S, Rajagopalan S, Wilson DL. Automatic Deep Learning Segmentation and Quantification of Epicardial Adipose Tissue in Non-Contrast Cardiac CT scans. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2021;2021:3938–42. DOI: 10.1109/EMBC46164.2021.9630953

8. Commandeur F, Goeller M, Betancur J, Cadet S, Doris M, Chen X et al. Deep Learning for Quantification of Epicardial and Thoracic Adipose Tissue From Non-Contrast CT. IEEE Transactions on Medical Imaging. 2018;37(8):1835–46. DOI: 10.1109/TMI.2018.2804799

9. Begoli E, Bhattacharya T, Kusnezov D. The need for uncertainty quantification in machine-assisted medical decision making. Nature Machine Intelligence. 2019;1(1):20–3. DOI: 10.1038/s42256-018-0004-1

10. Zhao C, Xu Y, He Z, Tang J, Zhang Y, Han J et al. Lung segmentation and automatic detection of COVID-19 using radiomic features from chest CT images. Pattern Recognition. 2021;119:108071. DOI: 10.1016/j.patcog.2021.108071

11. Jocher G, Stoken A, Borovec J, NanoCode012, Chaurasia A, TaoXie et al. ultralytics/yolov5: v5.0 - YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations. 2021. Av. at: https://zenodo.org/records/4679653

12. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. P. 234-241. [DOI: 10.1007/978-3-319-24574-4_28] In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. - Cham: Springer International Publishing, 2015. ISBN: 978-3-319-24573-7

13. Zwanenburg A, Vallières M, Abdalah MA, Aerts HJWL, Andrearczyk V, Apte A et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Imagebased Phenotyping. Radiology. 2020;295(2):328–38. DOI: 10.1148/radiol.2020191145

14. Luo C-L, Rong Y, Chen H, Zhang W-W, Wu L, Wei D et al. A Logistic Regression Model for Noninvasive Prediction of AFP-Negative Hepatocellular Carcinoma. Technology in Cancer Research & Treatment. 2019;18:153303381984663. DOI: 10.1177/1533033819846632

15. Suykens JAK, Vandewalle J. Least Squares Support Vector Machine Classifiers. Neural Processing Letters. 1999;9(3):293–300. DOI: 10.1023/A:1018628609742

16. Belgiu M, Drăguţ L. Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing. 2016;114:24–31. DOI: 10.1016/j.isprsjprs.2016.01.011

17. Bahad P, Saxena P. Study of AdaBoost and Gradient Boosting Algorithms for Predictive Analytics. P. 235-244. [DOI: 10.1007/978-981-15-0633-8_22] In: International Conference on Intelligent Computing and Smart Communication 2019. - Singapore: Springer Singapore, 2020. ISBN: 978-9811506321

18. Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. P. 785-794. [DOI: 10.1145/2939672.2939785] Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. - San Francisco California USA: ACM, 2016. ISBN: 978-1-4503-4232-2

19. Sai MJ, Chettri P, Panigrahi R, Garg A, Bhoi AK, Barsocchi P. An Ensemble of Light Gradient Boosting Machine and Adaptive Boosting for Prediction of Type-2 Diabetes. International Journal of Computational Intelligence Systems. 2023;16(1):14. DOI: 10.1007/s44196-023-00184-y

20. Blagus R, Lusa L. Gradient boosting for high-dimensional prediction of rare events. Computational Statistics & Data Analysis. 2017;113:19–37. DOI: 10.1016/j.csda.2016.07.016

21. Ji X, Ma Y, Shi N, Liang N, Chen R, Liu S et al. Clinical characteristics and treatment outcome of COVID-19 patients with stroke in China: A multicenter retrospective study. Phytomedicine. 2021;81:153433. DOI: 10.1016/j.phymed.2020.153433

22. Liang W, Liang H, Ou L, Chen B, Chen A, Li C et al. Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19. JAMA Internal Medicine. 2020;180(8):1081–9. DOI: 10.1001/jamainternmed.2020.2033

23. Zhao C, Bai Y, Wang C, Zhong Y, Lu N, Tian L et al. Risk factors related to the severity of COVID-19 in Wuhan. International Journal of Medical Sciences. 2021;18(1):120–7. DOI: 10.7150/ijms.47193

24. Zhang R, Xiao Q, Zhu S, Lin H, Tang M. Using different machine learning models to classify patients into mild and severe cases of COVID-19 based on multivariate blood testing. Journal of Medical Virology. 2022;94(1):357–65. DOI: 10.1002/jmv.27352

25. Li K, Fang Y, Li W, Pan C, Qin P, Zhong Y et al. CT image visual quantitative evaluation and clinical classification of coronavirus disease (COVID-19). European Radiology. 2020;30(8):4407–16. DOI: 10.1007/s00330-020-06817-6

26. Klüner LV, Oikonomou EK, Antoniades C. Assessing Cardiovascular Risk by Using the Fat Attenuation Index in Coronary CT Angiography. Radiology: Cardiothoracic Imaging. 2021;3(1):e200563. DOI: 10.1148/ryct.2021200563

27. Milletari F, Navab N, Ahmadi S-A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016 Fourth International Conference on 3D Vision (3DV). P. 565–571. 2016. [DOI: 10.1109/3DV.2016.79]