Skip to main content
SpringerLink
Log in

Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT

  • Original Article
  • Published:
Japanese Journal of Radiology Aims and scope Submit manuscript

Abstract

Purpose

Imaging diagnosis of stapes fixation (SF) is challenging owing to a lack of definite evidence. We developed a comprehensive machine learning (ML) model to identify SF on ultra-high-resolution CT.

Materials and methods

We retrospectively enrolled 109 participants (143 ears) and divided them into the training set (115 ears) and test set (28 ears). Stapes mobility (SF or non-SF) was determined by surgical inspection. In the ML analysis, rectangular regions of interest were placed on consecutive axial slices in the training set. Radiomic features were extracted and fed into the training session. The test set was analyzed using 7 ML models (support vector machine, k nearest neighbor, decision tree, random forest, extra trees, eXtreme Gradient Boosting, and Light Gradient Boosting Machine) and by 2 dedicated neuroradiologists. Diagnostic performance (sensitivity, specificity and accuracy, with surgical findings as the reference) was compared between the radiologists and the optimal ML model by using the McNemar test.

Results

The mean age of the participants was 42.3 ± 17.5 years. The Light Gradient Boosting Machine (LightGBM) model showed the highest sensitivity (0.83), specificity (0.81), accuracy (0.82) and area under the curve (0.88) for detecting SF among the 7 ML models. The neuroradiologists achieved good sensitivities (0.75 and 0.67), moderate-to-good specificities (0.63 and 0.56) and good accuracies (0.68 and 0.61). This model showed no statistical differences with the neuroradiologists (P values 0.289–1.000).

Conclusions

Compared to the neuroradiologists, the LightGBM model achieved competitive diagnostic performance in identifying SF, and has the potential to be a supportive tool in clinical practice.

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
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

SF:

Stapes fixation

AI:

Artificial intelligence

U-HRCT:

Ultra-high-resolution CT

ML:

Machine learning

ROI:

Region of interest

LASSO:

Least Absolute Shrinkage and Selection Operator

PPV:

Positive predictive value

NPV:

Negative predictive value

ROC:

Receiver operating characteristic

AUC:

Area under the curve

CI:

Confidence interval

References

  1. Nakajima HH, Ravicz ME, Merchant SN, Peake WT, Rosowski JJ. Experimental ossicular fixations and the middle ear’s response to sound: evidence for a flexible ossicular chain. Hear Res. 2005;204(1–2):60–77.

    Article  PubMed  Google Scholar 

  2. Shin YJ, Fraysse B, Deguine O, Cognard C, Charlet JP, Sevely A. Sensorineural hearing loss and otosclerosis: a clinical and radiologic survey of 437 cases. Acta Otolaryngol. 2001;121(2):200–4.

    Article  PubMed  CAS  Google Scholar 

  3. Karosi T, Csomor P, Petko M, Liktor B, Szabo LZ, Pytel J, et al. Histopathology of nonotosclerotic stapes fixations. Otol Neurotol. 2009;30(8):1058–66.

    Article  PubMed  Google Scholar 

  4. Park K, Choung YH. Isolated congenital ossicular anomalies. Acta Otolaryngol. 2009;129(4):419–22.

    Article  PubMed  Google Scholar 

  5. Karosi T, Csomor P, Sziklai I. The value of HRCT in stapes fixations corresponding to hearing thresholds and histologic findings. Otol Neurotol. 2012;33(8):1300–7.

    Article  PubMed  Google Scholar 

  6. Guild SR. Histologic otosclerosis. Ann Otol Rhinol Laryngol. 1944;53:246–67.

    Google Scholar 

  7. Altmann F, Glasgold A, Macduff JP. The incidence of otosclerosis as related to race and sex. Ann Otol Rhinol Laryngol. 1967;76(2):377–92.

    Article  PubMed  CAS  Google Scholar 

  8. Totten DJ, Marinelli JP, Carlson ML. Incidence of congenital stapes footplate fixation since 1970: a population-based study. Otol Neurotol. 2020;41(4):489–93.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Akazawa Y, Ganaha A, Higa T, Kondo S, Oyakawa Y, Hirakawa H, et al. Measurement of stapes footplate thickness in otosclerosis by ultra-high-resolution computed tomography. Acta Otolaryngol. 2020;140(11):899–903.

    Article  PubMed  Google Scholar 

  10. Dinc AE, Kumbul YC. Clinical landmarks in chronic otitis media with tympanosclerosis: clinical history may have predictive value in the diagnosis of ossicular chain mobility. J Laryngol Otol. 2019;133(11):992–4.

    Article  PubMed  CAS  Google Scholar 

  11. Boleas-Aguirre MS, Ruiz de Erenchun-Lasa I, Bulnes-Plano MD. Audiological results after total ossicular reconstruction for stapes fixation. Eur Arch Otorhinolaryngol. 2015;272(11):3123–30.

    Article  PubMed  Google Scholar 

  12. Wycherly BJ, Berkowitz F, Noone AM, Kim HJ. Computed tomography and otosclerosis: a practical method to correlate the sites affected to hearing loss. Ann Otol Rhinol Laryngol. 2010;119(12):789–94.

    Article  PubMed  Google Scholar 

  13. Vincent R, Oates J, Sperling NM. Stapedotomy for tympanosclerotic stapes fixation: is it safe and efficient? a review of 68 cases. Otol Neurotol. 2002;23(6):866–72.

    Article  PubMed  Google Scholar 

  14. Acar GO, Kivekas I, Hanna BM, Huang L, Gopen Q, Poe DS. Comparison of stapedotomy minus prosthesis, circumferential stapes mobilization, and small fenestra stapedotomy for stapes fixation. Otol Neurotol. 2014;35(4):e123–9.

    Article  PubMed  Google Scholar 

  15. Dalchow CV, Dunne AA, Sesterhenn A, Teymoortash A, Werner JA. Malleostapedotomy: the marburg experience. Adv Otorhinolaryngol. 2007;65:215–21.

    PubMed  CAS  Google Scholar 

  16. Nassiri AM, Benson JC, Doerfer KW, Perkins EL, Sweeney AD, Patel NS, et al. Absent pyramidal eminence and stapedial tendon associated with congenital stapes footplate fixation: intraoperative and radiographic findings. Am J Otolaryngol. 2021;42(6): 103144.

    Article  PubMed  Google Scholar 

  17. Brown LA, Mocan BO, Redleaf MI. Diagnostic protocol for detecting otosclerosis on high-resolution temporal bone CT. Ann Otol Rhinol Laryngol. 2019;128(11):1054–60.

    Article  PubMed  Google Scholar 

  18. Priya SR, Singh PP, Upreti L, Vaid L. High resolution computed tomography in stapedial otosclerosis. Indian J Otolaryngol Head Neck Surg. 2013;65(Suppl 3):505–11.

    Article  PubMed  CAS  Google Scholar 

  19. Tringali S, Pouget JF, Bertholon P, Dubreuil C, Martin C. Value of temporal bone density measurements in otosclerosis patients with normal-appearing computed tomographic scan. Ann Otol Rhinol Laryngol. 2007;116(3):195–8.

    Article  PubMed  Google Scholar 

  20. Bi WL, Hosny A, Schabath MB, Giger ML, Birkbak NJ, Mehrtash A, et al. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin. 2019;69(2):127–57.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Geras KJ, Mann RM, Moy L. Artificial intelligence for mammography and digital breast tomosynthesis: current concepts and future perspectives. Radiology. 2019;293(2):246–59.

    Article  PubMed  Google Scholar 

  22. Choi YS, Bae S, Chang JH, Kang SG, Kim SH, Kim J, et al. Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics. Neuro Oncol. 2021;23(2):304–13.

    Article  PubMed  CAS  Google Scholar 

  23. Rudie JD, Rauschecker AM, Bryan RN, Davatzikos C, Mohan S. Emerging applications of artificial intelligence in neuro-oncology. Radiology. 2019;290(3):607–18.

    Article  PubMed  Google Scholar 

  24. Castellano G, Bonilha L, Li LM, Cendes F. Texture analysis of medical images. Clin Radiol. 2004;59(12):1061–9.

    Article  PubMed  CAS  Google Scholar 

  25. van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. Radiomics in medical imaging-“how-to” guide and critical reflection. Insights Imaging. 2020;11(1):91.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Arbelaez Ossa L, Starke G, Lorenzini G, Vogt JE, Shaw DM, Elger BS. Re-focusing explainability in medicine. Digit Health. 2022;8:20552076221074490.

    PubMed  PubMed Central  Google Scholar 

  27. Lekadir K, Osuala R, Gallin C, Lazrak N, Kushibar K, Tsakou G, et al. FUTURE-AI: Guiding principles and consensus recommendations for trustworthy artificial intelligence in medical imaging. arXiv preprint arXiv:210909658. 2021.

  28. Tang R, Yin H, Wang Z, Zhang Z, Zhao L, Zhang P, et al. Stapes visualization by ultra-high resolution CT in cadaveric heads: a preliminary study. Eur J Radiol. 2021;141: 109786.

    Article  PubMed  Google Scholar 

  29. Heutink F, Klabbers TM, Huinck WJ, Lucev F, van der Woude WJ, Mylanus EAM, et al. Ultra-high-resolution CT to detect intracochlear new bone formation after cochlear implantation. Radiology. 2022;302(3):605–12.

    Article  PubMed  Google Scholar 

  30. Fujiwara M, Watanabe Y, Kashiwagi N, Ohta Y, Sato T, Nishigaki M, et al. Improved visualization of the chorda tympani nerve using ultra-high-resolution computed tomography. Acta Radiol Open. 2021;10(11):20584601211061444.

    PubMed  PubMed Central  Google Scholar 

  31. Yamashita K, Hiwatashi A, Togao O, Kikuchi K, Matsumoto N, Momosaka D, et al. Ultrahigh-resolution CT scan of the temporal bone. Eur Arch Otorhinolaryngol. 2018;275(11):2797–803.

    Article  PubMed  Google Scholar 

  32. Heutink F, Koch V, Verbist B, van der Woude WJ, Mylanus E, Huinck W, et al. Multi-scale deep learning framework for cochlea localization, segmentation and analysis on clinical ultra-high-resolution CT images. Comput Methods Programs Biomed. 2020;191: 105387.

    Article  PubMed  Google Scholar 

  33. Depeursinge A, Chin AS, Leung AN, Terrone D, Bristow M, Rosen G, et al. Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution computed tomography. Invest Radiol. 2015;50(4):261–7.

    Article  PubMed  PubMed Central  Google Scholar 

  34. Fujima N, Andreu-Arasa VC, Onoue K, Weber PC, Hubbell RD, Setty BN, et al. Utility of deep learning for the diagnosis of otosclerosis on temporal bone CT. Eur Radiol. 2021;31(7):5206–11.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This study has received funding by National Natural Science Foundation of China (61931013, 82171886), Beijing Natural Science Foundation (7222301), Capital’s Funds for Health Improvement and Research (No. 2022-1-1111), Beijing Scholar 2015 (No. [2015] 160), and Beijing Key Clinical Discipline Funding (No. 2021-135).

Funding

National Natural Science Foundation of China, 61931013, Zhenchang Wang, 82171886, Pengfei Zhao, Beijing Natural Science Foundation, 7222301, Pengfei Zhao, Capital’s Funds for Health Improvement and Research, 2022-1-1111, Zhenchang Wang, Beijing Scholar 2015, [2015] 160, Zhenchang Wang, Beijing Key Clinical Discipline Funding, 2021-135, Zhenchang Wang.

Author information

Author notes

  1. Ruowei Tang and Jia Li have contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong’an Road, Xicheng District, Beijing, 100050, People’s Republic of China

    Ruowei Tang, Jia Li, Pengfei Zhao, Zhengyu Zhang, Hongxia Yin, Heyu Ding, Ning Xu, Zhenghan Yang & Zhenchang Wang

Authors
  1. Ruowei Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jia Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pengfei Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhengyu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hongxia Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Heyu Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ning Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Zhenghan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Zhenchang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: RT, JL, PZ, HD; methodology: RT, JL, PZ, ZW; formal analysis and investigation: RT, JL, ZZ, HY, NX; writing—original draft preparation: RT, JL; writing—review and editing: RT, JL, PZ, ZZ, HY, HD, NX, ZY, ZW; funding acquisition: ZW; resources: PZ, ZY, ZW; supervision: PZ, ZY, ZW.

Corresponding authors

Correspondence to Pengfei Zhao or Zhenchang Wang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Consent to participate

Informed consent was waived from all individual participants included in the study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Ruowei Tang and Jia Li are co-first authors.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 1162 KB)

Supplementary file2 (CSV 175 KB)

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tang, R., Li, J., Zhao, P. et al. Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT. Jpn J Radiol 42, 69–77 (2024). https://doi.org/10.1007/s11604-023-01475-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11604-023-01475-2

Keywords

Search

Navigation