Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays

Tsiknakis,Nikos; Trivizakis,Eleftherios; Vassalou,Evangelia E.; Papadakis,Georgios Z.; Spandidos,Demetrios A.; Tsatsakis,Aristidis; Sánchez‑García,Jose; López‑González,Rafael; Papanikolaou,Nikolaos; Karantanas,Apostolos H.; Marias,Kostas

doi:10.3892/etm.2020.8797

Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays

Authors:
- Nikos Tsiknakis
- Eleftherios Trivizakis
- Evangelia E. Vassalou
- Georgios Z. Papadakis
- Demetrios A. Spandidos
- Aristidis Tsatsakis
- Jose Sánchez‑García
- Rafael López‑González
- Nikolaos Papanikolaou
- Apostolos H. Karantanas
- Kostas Marias
View Affiliations

Affiliations: Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece, Department of Medical Imaging, University Hospital of Heraklion, 71110 Heraklion, Greece, Laboratory of Clinical Virology, Medical School, University of Crete, 71003 Heraklion, Greece, Department of Forensic Sciences and Toxicology, Medical School, University of Crete, 71003 Heraklion, Greece, QUIBIM S.L., 46021 Valencia, Spain
Published online on: May 27, 2020 https://doi.org/10.3892/etm.2020.8797
Pages: 727-735
Copyright: © Tsiknakis et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

COVID-19 has led to an unprecedented healthcare crisis with millions of infected people across the globe often pushing infrastructures, healthcare workers and entire economies beyond their limits. The scarcity of testing kits, even in developed countries, has led to extensive research efforts towards alternative solutions with high sensitivity. Chest radiological imaging paired with artificial intelligence (AI) can offer significant advantages in diagnosis of novel coronavirus infected patients. To this end, transfer learning techniques are used for overcoming the limitations emanating from the lack of relevant big datasets, enabling specialized models to converge on limited data, as in the case of X‑rays of COVID‑19 patients. In this study, we present an interpretable AI framework assessed by expert radiologists on the basis on how well the attention maps focus on the diagnostically‑relevant image regions. The proposed transfer learning methodology achieves an overall area under the curve of 1 for a binary classification problem across a 5‑fold training/testing dataset.

View Figures

View References

1	Chen N, Zhou M, Dong X, Qu J, Gong F, Han Y, Qiu Y, Wang J, Liu Y, Wei Y, et al: Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: A descriptive study. Lancet. 395:507–513. 2020.PubMed/NCBI View Article : Google Scholar
2	World Health Organization (WHO): Report of the WHO-China joint mission on coronavirus disease 2019 (COVID-19). WHO, Geneva, 2020. https://www.who.int/docs/default-source/coronaviruse/who-china-joint-mission-on-covid-19-final-report.pdf. Accessed February 28, 2020.
3	Petrakis D, Margină D, Tsarouhas K, Tekos F, Stan M, Nikitovic D, Kouretas D, Spandidos DA and Tsatsakis A: Obesity a risk factor for increased COVID 19 prevalence, severity and lethality (Review). Mol Med Rep. 22:9–19. 2020.PubMed/NCBI View Article : Google Scholar
4	Docea AO, Tsatsakis A, Albulescu D, Cristea O, Zlatian O, Vinceti M, Moschos SA, Tsoukalas D, Goumenou M, Drakoulis N, et al: A new threat from an old enemy: Re-emergence of coronavirus (Review). Int J Mol Med. 45:1631–1643. 2020.PubMed/NCBI View Article : Google Scholar
5	Farsalinos K, Niaura R, Le Houezec J, Barbouni A, Tsatsakis A, Kouretas D, Vantarakis A and Poulas K: Editorial: Nicotine and SARS-CoV-2: COVID-19 may be a disease of the nicotinic cholinergic system. Toxicol Rep: Apr 30, 2020 (Epub ahead of print).
6	Calina D, Docea AO, Petrakis D, Egorov AM, Ishmukhametov AA, Gabibov AG, Shtilman MI, Kostoff R, Carvalho F, Vinceti M, et al: Towards effective COVID 19 vaccines: Updates, perspectives and challenges (Review). Int J Mol Med. 46:3–16. 2020.PubMed/NCBI View Article : Google Scholar
7	Skalny AV, Rink L, Ajsuvakova OP, Aschner M, Gritsenko VA, Alekseenko SI, Svistunov AA, Petrakis D, Spandidos DA, Aaseth J, et al: Zinc and respiratory tract infections: Perspectives for COVID-19 (Review). Int J Mol Med. 46:17–26. 2020.PubMed/NCBI View Article : Google Scholar
8	Wong HYF, Lam HYS, Fong AH, Leung ST, Chin TW, Lo CSY, Lui MM, Lee JCY, Chiu KW, Chung T, et al: Frequency and distribution of chest radiographic findings in COVID-19 positive patients. Radiology. 27(201160)2019.PubMed/NCBI View Article : Google Scholar
9	Huang C, Wang Y, Li X, Ren L, Zhao J, Hu Y, Zhang L, Fan G, Xu J, Gu X, et al: Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet. 395:497–506. 2020.PubMed/NCBI View Article : Google Scholar
10	Kong W and Agarwal PP: Chest imaging appearance of COVID-19 infection. Radiol Cardiothorac Imaging. 2(e200028)2020.
11	Bandirali M, Sconfienza LM, Serra R, Brembilla R, Albano D, Ernesto PF and Messina C: Chest radiograph findings in asymptomatic and minimally symptomatic quarantined patients in Codogno, Italy during COVID-19 pandemic. Radiology. 295(E7)2020.PubMed/NCBI View Article : Google Scholar
12	Ai T, Yang Z, Hou H, Zhan C, Chen C, Lv W, Tao Q, Sun Z and Xia L: Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: A Report of 1014 cases. Radiology: Feb 26, 2020 (Epub ahead of print).
13	Hao K: Doctors are using AI to triage covid-19 patients. The tools may be here to stay. MIT Technology Review, 2020. https://www.technologyreview.com/2020/04/23/1000410/ai-triage-covid-19-patients-health-care/. Accessed April 23, 2020.
14	Zhang J, Xie Y, Li Y, Shen C and Xia Y: COVID-19 Screening on chest X-ray images using deep learning based anomaly detection. arXiv: 2003.12338.
15	Narin A, Kaya C and Pamuk Z: Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. arXiv: 2003.10849.
16	Wang L and Wong A: COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images. arXiv: 2003.09871.
17	Afshar P, Heidarian S, Naderkhani F, Oikonomou A, Plataniotis KN and Mohammadi A: COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images. arXiv: 2004.02696.
18	Abbas A, Abdelsamea MM and Gaber MM: Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. arXiv: 2003.13815.
19	Khalifa NEM, Taha MHN, Hassanien AE and Elghamrawy S: Detection of coronavirus (COVID-19) associated pneumonia based on generative adversarial networks and a fine-tuned deep transfer learning model using chest X-ray dataset. arXiv: 2004.01184.
20	Ghoshal B and Tucker A: Estimating uncertainty and interpretability in deep learning for coronavirus (COVID-19) detection. arXiv: 2003.10769.
21	Ucar F and Korkmaz D: COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Med Hypotheses. 140(109761)2020.PubMed/NCBI View Article : Google Scholar
22	Apostolopoulos ID and Mpesiana TA: Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks. Phys Eng Sci Med: https://doi.org/10.1007/s13246-020-00865-4.
23	Loey M, Smarandache F and M. Khalifa NE: Within the lack of chest COVID-19 X-ray dataset: A novel detection model based on GAN and deep transfer learning. Symmetry (Basel). 12(651)2020.
24	He X, Yang X, Zhang S, Zhao J, Zhang Y, Xing E and Xie P: Sample-efficient deep learning for COVID-19 diagnosis based on CT scans. medRxiv: doi: https://doi.org/10.1101/2020.04.13.20063941.
25	Zhao J, Zhang Y, He X and Xie P: COVID-CT-dataset: A CT scan dataset about COVID-19. arXiv: 2003.13865.
26	Wang S, Kang B, Ma J, Zeng X, Xiao M, Guo J, Cai M, Yang J, Li Y, Meng X and Xu B: A deep learning algorithm using CT images to screen for corona virus disease (COVID-19). medRxiv: doi: https://doi.org/10.1101/2020.02.14.20023028.
27	Bai HX, Wang R, Xiong Z, Hsieh B, Chang K, Halsey K, Tran TML, Choi JW, Wang DC, Shi LB, et al: AI augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other etiology on chest CT. Radiology (In Press).
28	Cohen JP, Morrison P and Dao L: COVID-19 image data collection. arXiv: 2003.11597.
29	Jeffrey RB Jr, Manaster BJ, Osborn AG, Rosado-de-Christenson ML and Woodward PJ: Diagnostic Imaging: Emergency. 2nd edition. Lippincott Williams & Wilkins, 2013.
30	Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, McKeown A, Yang G, Wu X, Yan F, et al: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 172:1122–1131.e9. 2018.PubMed/NCBI View Article : Google Scholar
31	Mooney P: Chest X-ray images (Pneumonia). https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia. Accessed March 24, 2018.
32	Szegedy C, Vanhoucke V, Ioffe S, Shlens J and Wojna Z: Rethinking the Inception Architecture for Computer Vision. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, pp2818-2826, 2016.
33	Deng J, Dong W, Socher R, Li LJ, Li K and Li FF: ImageNet: A Large-Scale Hierarchical Image Database. In: Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, pp248-255, 2009.
34	Abràmoff MD, Lou Y, Erginay A, Clarida W, Amelon R, Folk JC and Niemeijer M: Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophthalmol Vis Sci. 57:5200–5206. 2016.PubMed/NCBI View Article : Google Scholar
35	Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D and Batra D: Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In: Proceedings of the IEEE International Conference on Computer Vision. Institute of Electrical and Electronics Engineers Inc., pp618-626, 2017.
36	Kingma DP and Ba J: Adam: A method for stochastic optimization. arXiv: 1412.6980.
37	Chowdhury MEH, Rahman T, Khandakar A, Mazhar R, Kadir MA, Mahbub Z Bin, Islam KR, Khan MS, Iqbal A, Al-Emadi N and Reaz MBI: Can AI help in screening Viral and COVID-19 pneumonia? arXiv: 2003.13145.