Skip to main content

Advertisement

SpringerLink
Log in

Development of an Expert-Level Right Ventricular Abnormality Detection Algorithm Based on Deep Learning

  • Original research article
  • Published:
Interdisciplinary Sciences: Computational Life Sciences Aims and scope Submit manuscript

Abstract

Purpose

Studies relating to the right ventricle (RV) are inadequate, and specific diagnostic algorithms still need to be improved. This essay is designed to make exploration and verification on an algorithm of deep learning based on imaging and clinical data to detect RV abnormalities.

Methods

The Automated Cardiac Diagnosis Challenge dataset includes 20 subjects with RV abnormalities (an RV cavity volume which is higher than 110 mL/m2 or RV ejection fraction which is lower than 40%) and 20 normal subjects who suffered from both cardiac MRI. The subjects were separated into training and validation sets in a ratio of 7:3 and were modeled by utilizing a nerve net of deep-learning and six machine-learning algorithms. Eight MRI specialists from multiple centers independently determined whether each subject in the validation group had RV abnormalities. Model performance was evaluated based on the AUC, accuracy, recall, sensitivity and specificity. Furthermore, a preliminary assessment of patient disease risk was performed based on clinical information using a nomogram.

Results

The deep-learning neural network outperformed the other six machine-learning algorithms, with an AUC value of 1 (95% confidence interval: 1–1) on both training group and validation group. This algorithm surpassed most human experts (87.5%). In addition, the nomogram model could evaluate a population with a disease risk of 0.2–0.8.

Conclusions

A deep-learning algorithm could effectively identify patients with RV abnormalities. This AI algorithm developed specifically for right ventricular abnormalities will improve the detection of right ventricular abnormalities at all levels of care units and facilitate the timely diagnosis and treatment of related diseases. In addition, this study is the first to validate the algorithm’s ability to classify RV abnormalities by comparing it with human experts.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Availability of Data and Materials

The published datasets ACDC involved in the study are available from the original authors upon request. The artificial intelligence model code used in the study should be obtained by contacting the authors (panxiangbin@fuwaihospital.org).

Abbreviations

ACDC:

Automated cardiac diagnosis challenge

ANN:

Artificial neural network

AUC:

Area under the receiver operating characteristic curve

DCA:

Survival decision curve

EF:

Ejection fraction

LASSO:

Least absolute shrinkage and selection operator

MRI:

Magnetic resonance imaging

NMR:

Nuclear magnetic resonance

RV:

Right ventricle

SGD:

Stochastic gradient descent

XGBoost:

EXtreme gradient boost

References

  1. Harvey W (1975) Classic pages in obstetrics and gynecology. Exercitatio anatomica de motu cordis et sanguinis in animalibus. Am J Obstet Gynecol 121(7):1007. https://doi.org/10.1097/00000441-192904000-00020

    Article  CAS  PubMed  Google Scholar 

  2. Haddad F, Hunt S, Rosenthal DN, Murphy DJ (2008) Right ventricular function in cardiovascular disease, part I: Anatomy, physiology, aging, and functional assessment of the right ventricle. Circulation 117(11):1436–1448. https://doi.org/10.1161/CIRCULATIONAHA.107.653576

    Article  PubMed  Google Scholar 

  3. Haddad F, Doyle R, Murphy DJ, Hunt SA (2008) Right ventricular function in cardiovascular disease, part II: pathophysiology, clinical importance, and management of right ventricular failure. Circulation 117(13):1717–1731. https://doi.org/10.1161/CIRCULATIONAHA.107.653584

    Article  PubMed  Google Scholar 

  4. Sayed A, Pal S, Poplawska M et al (2020) Arrhythmogenic right ventricular cardiomyopathy diagnosis. Cardiol Rev 28(6):319–324. https://doi.org/10.1097/CRD.0000000000000292

    Article  PubMed  Google Scholar 

  5. Gemayel C, Pelliccia A, Thompson PD (2001) Arrhythmogenic right ventricular cardiomyopathy. J Am Coll Cardiol 38(7):1773–1781. https://doi.org/10.1016/s0735-1097(01)01654-0

    Article  CAS  PubMed  Google Scholar 

  6. Castaños-Gutiérrez SL, Kamel IR, Zimmerman SL (2016) Current concepts on diagnosis and prognosis of arrhythmogenic right ventricular cardiomyopathy/dysplasia. J Thorac Imaging 31(6):324–335. https://doi.org/10.1097/RTI.0000000000000171

    Article  PubMed  Google Scholar 

  7. Busse A, Rajagopal R, Yücel S et al (2020) Cardiac MRI-update 2020. Radiologe 60(Suppl 1):33–40. https://doi.org/10.1007/s00117-020-00687-1

    Article  PubMed  Google Scholar 

  8. Russo V, Lovato L, Ligabue G (2020) Cardiac MRI: technical basis. Radiol Med 125(11):1040–1055. https://doi.org/10.1007/s11547-020-01282-z

    Article  PubMed  Google Scholar 

  9. Bernard O, Lalande A, Zotti C et al (2018) Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans Med Imaging 37(11):2514–2525. https://doi.org/10.1109/TMI.2018.2837502

    Article  PubMed  Google Scholar 

  10. Nishie A, Kakihara D, Nojo T et al (2015) Current radiologist workload and the shortages in Japan: how many full-time radiologists are required? Jpn J Radiol 33(5):266–272. https://doi.org/10.1007/s11604-015-0413-6

    Article  PubMed  Google Scholar 

  11. Pinker S (2000) Private MRI clinics flourishing in Quebec. CMAJ 163(10):1326

    CAS  PubMed  PubMed Central  Google Scholar 

  12. Ouyang D, He B, Ghorbani A et al (2020) Video-based AI for beat-to-beat assessment of cardiac function. Nature 580(7802):252–256. https://doi.org/10.1038/s41586-020-2145-8

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Chattopadhyay S, Dey A, Singh PK, Oliva D, Cuevas E, Sarkar R (2022) MTRRE-Net: a deep learning model for detection of breast cancer from histopathological images. Comput Biol Med 150:106155. https://doi.org/10.1016/j.compbiomed.2022.106155

    Article  PubMed  Google Scholar 

  14. Basu A, Sheikh KH, Cuevas E, Sarkar R (2022) COVID-19 detection from CT scans using a two-stage framework. Expert Syst Appl 193:116377. https://doi.org/10.1016/j.eswa.2021.116377

    Article  PubMed  PubMed Central  Google Scholar 

  15. Van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77(21):e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Tibshirani R (1997) The lasso method for variable selection in the Cox model. Stat Med 16(4):385–395. https://doi.org/10.1002/(sici)1097-0258(19970228)16:4%3c385::aid-sim380%3e3.0.co;2-3

    Article  CAS  PubMed  Google Scholar 

  17. Schober P, Boer C, Schwarte LA (2018) Correlation coefficients: appropriate use and interpretation. Anesth Analg 126(5):1763–1768. https://doi.org/10.1213/ANE.0000000000002864

    Article  PubMed  Google Scholar 

  18. Kriegeskorte N, Golan T (2019) Neural network models and deep learning. Curr Biol 29(7):R231–R236. https://doi.org/10.1016/j.cub.2019.02.034

    Article  CAS  PubMed  Google Scholar 

  19. Li XL (2018) Preconditioned stochastic gradient descent. IEEE Trans Neural Netw Learn Syst 29(5):1454–1466. https://doi.org/10.1109/TNNLS.2017.2672978

    Article  PubMed  Google Scholar 

  20. Peterson LE (2009) K-nearest neighbor. Scholarpedia 4(2):1883. https://doi.org/10.4249/scholarpedia.1883

    Article  Google Scholar 

  21. Stoltzfus JC (2011) Logistic regression: a brief primer. Acad Emerg Med 18(10):1099–1104. https://doi.org/10.1111/j.1553-2712.2011.01185.x

    Article  PubMed  Google Scholar 

  22. Black JE, Kueper JK, Williamson TS (2022) An introduction to machine learning for classification and prediction. Fam Pract 40(1):200–204. https://doi.org/10.1093/fampra/cmac104

    Article  Google Scholar 

  23. Inoue T, Ichikawa D, Ueno T et al (2020) XGBoost, a machine learning method, predicts neurological recovery in patients with cervical spinal cord injury. Neurotrauma Rep 1(1):8–16. https://doi.org/10.1089/neur.2020.0009

    Article  PubMed  PubMed Central  Google Scholar 

  24. Biau G, Scornet E (2016) A random forest guided tour. TEST 25(2):197–227. https://doi.org/10.1007/s11749-016-0481-7

    Article  Google Scholar 

  25. Hwang EJ, Park S, Jin KN et al (2019) Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs. JAMA Netw Open 2(3):e191095. https://doi.org/10.1001/jamanetworkopen.2019.1095

    Article  PubMed  PubMed Central  Google Scholar 

  26. Al-Antari MA, Hua CH, Bang J, Lee S (2021) Fast deep learning computer-aided diagnosis of COVID-19 based on digital chest x-ray images. Appl Intell (Dordr) 51(5):2890–2907. https://doi.org/10.1007/s10489-020-02076-6

    Article  PubMed  Google Scholar 

  27. Liu Z, Li W, Li H et al (2023) Automated deep neural network-based identification, localization, and tracking of cardiac structures for ultrasound-guided interventional surgery. J Thorac Dis 15(4):2129–2140. https://doi.org/10.21037/jtd-23-470

    Article  PubMed  PubMed Central  Google Scholar 

  28. Castelvecchi D (2016) Can we open the black box of AI? Nature 538(7623):20–23. https://doi.org/10.1038/538020a

    Article  CAS  PubMed  Google Scholar 

  29. Kim S, Kim T-S, Lee WH (2022) Accelerating 3D convolutional neural network with channel bottleneck module for EEG-based emotion recognition. Sensors 22:6813. https://doi.org/10.3390/s22186813

    Article  PubMed  PubMed Central  Google Scholar 

  30. Samee NA, Atteia G, Meshoul S, Al-antari MA, Kadah YM (2022) Deep learning cascaded feature selection framework for breast cancer classification: hybrid CNN with univariate-based approach. Mathematics 10:3631. https://doi.org/10.3390/math10193631

    Article  Google Scholar 

  31. Al-Antari MA, Al-Masni MA, Kim TS (2020) Deep learning computer-aided diagnosis for breast lesion in digital mammogram. Adv Exp Med Biol 1213:59–72. https://doi.org/10.1007/978-3-030-33128-3_4

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This study benefits from the high-quality data of previous studies whose true generosity has advanced cardiovascular medicine.

Funding

This evaluation study was supported by the following aspects: the Fundamental Research Funds for the Central Universities (2019PT350005); National Natural Science Foundation of China (81970444); Beijing Municipal Science and Technology Project (Z201100005420030); National high level talents special support plan (2020-RSW02); CAMS Innovation Fund for Medical Sciences (2021-I2M-1–065); Sanming Project of Medicine in Shenzhen (SZSM202011013).

Author information

Authors and Affiliations

  1. Department of Structural Heart Disease, National Center for Cardiovascular Disease, China and Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100037, China

    Zeye Liu, Hang Li, Fengwen Zhang, Wenbin Ouyang, Shouzheng Wang & Xiangbin Pan

  2. National Health Commission Key Laboratory of Cardiovascular Regeneration Medicine, Beijing, 100037, China

    Zeye Liu, Hang Li, Fengwen Zhang, Wenbin Ouyang, Shouzheng Wang & Xiangbin Pan

  3. Key Laboratory of Innovative Cardiovascular Devices, Chinese Academy of Medical Sciences, Beijing, 100037, China

    Zeye Liu, Hang Li, Fengwen Zhang, Wenbin Ouyang, Shouzheng Wang & Xiangbin Pan

  4. National Clinical Research Center for Cardiovascular Diseases, Fuwai Hospital, Chinese Academy of Medical Sciences, Beijing, 100037, China

    Zeye Liu, Hang Li, Fengwen Zhang, Wenbin Ouyang, Shouzheng Wang & Xiangbin Pan

  5. Pediatric Cardiac Surgery, Henan Provincial People’s Hospital, Huazhong Fuwai Hospital, Zhengzhou University People’s Hospital, Zhengzhou, 450000, China

    Wenchao Li

  6. Department of Medical Imaging, Fuwai Yunnan Cardiovascular Hospital, Kunming, 650000, China

    Aihua Zhi

Authors
  1. Zeye Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wenchao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fengwen Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wenbin Ouyang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shouzheng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Aihua Zhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiangbin Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, methodology, software, validation, visualization, writing—original draft, ZL; resources, validation, visualization, WL; resources, validation, visualization, HL; resources, validation, visualization, FZ; resources, validation, visualization, WO; resources, validation, visualization, SW; resources, validation, visualization, AZ; conceptualization, methodology, writing—original draft, project administration, resources, writing—review editing, conceptualization, validation, XP.

Corresponding author

Correspondence to Xiangbin Pan.

Ethics declarations

Conflict of Interest

All the authors disclosed no relevant relationships.

Ethical Approval and Consent to Participate

Not applicable.

Role of the Funder/Sponsor

The funders had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Z., Li, H., Li, W. et al. Development of an Expert-Level Right Ventricular Abnormality Detection Algorithm Based on Deep Learning. Interdiscip Sci Comput Life Sci 15, 653–662 (2023). https://doi.org/10.1007/s12539-023-00581-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12539-023-00581-z

Keywords

Search

Navigation