Skip to main content
SpringerLink
Log in

Deep learning based identification of pituitary adenoma on surgical endoscopic images: a pilot study

  • Research
  • Published:
Neurosurgical Review Aims and scope Submit manuscript

Abstract

Accurate tumor identification during surgical excision is necessary for neurosurgeons to determine the extent of resection without damaging the surrounding tissues. No conventional technologies have achieved reliable performance for pituitary adenomas. This study proposes a deep learning approach using intraoperative endoscopic images to discriminate pituitary adenomas from non-tumorous tissue inside the sella turcica. Static images were extracted from 50 intraoperative videos of patients with pituitary adenomas. All patients underwent endoscopic transsphenoidal surgery with a 4 K ultrahigh-definition endoscope. The tumor and non-tumorous tissue within the sella turcica were delineated on static images. Using intraoperative images, we developed and validated deep learning models to identify tumorous tissue. Model performance was evaluated using a fivefold per-patient methodology. As a proof-of-concept, the model’s predictions were pathologically cross-referenced with a medical professional’s diagnosis using the intraoperative images of a prospectively enrolled patient. In total, 605 static images were obtained. Among the cropped 117,223 patches, 58,088 were labeled as tumors, while the remaining 59,135 were labeled as non-tumorous tissues. The evaluation of the image dataset revealed that the wide-ResNet model had the highest accuracy of 0.768, with an F1 score of 0.766. A preliminary evaluation on one patient indicated alignment between the ground truth set by neurosurgeons, the model’s predictions, and histopathological findings. Our deep learning algorithm has a positive tumor discrimination performance in intraoperative 4-K endoscopic images in patients with pituitary adenomas.

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

Data availability

The datasets generated during the current study and model codes are available from the corresponding author upon reasonable request.

References

  1. Melmed S, Casanueva FF, Hoffman AR et al (2011) Diagnosis and treatment of hyperprolactinemia: an Endocrine Society clinical practice guideline. J Clin Endocrinol Metab 96:273–288. https://doi.org/10.1210/jc.2010-1692

    Article  PubMed  CAS  Google Scholar 

  2. Aghi MK, Chen CC, Fleseriu M et al (2016) Congress of Neurological Surgeons Systematic Review and evidence-based guidelines on the management of patients with nonfunctioning pituitary adenomas: executive summary. Neurosurgery 79:521–523. https://doi.org/10.1227/NEU.0000000000001386

    Article  PubMed  Google Scholar 

  3. Honegger J, Grimm F (2018) The experience with transsphenoidal surgery and its importance to outcomes. Pituitary 21:545–555. https://doi.org/10.1007/s11102-018-0904-4

    Article  PubMed  Google Scholar 

  4. Behbahaninia M, Martirosyan NL, Georges J et al (2013) Intraoperative fluorescent imaging of intracranial tumors: a review. Clin Neurol Neurosurg 115:517–528. https://doi.org/10.1016/J.CLINEURO.2013.02.019

    Article  PubMed  Google Scholar 

  5. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp 248–255. https://doi.org/10.1109/CVPR.2009.5206848

  6. Lui TKL, Guo CG, Leung WK (2020) Accuracy of artificial intelligence on histology prediction and detection of colorectal polyps: a systematic review and meta-analysis. Gastrointest Endosc 92:11-22.e6. https://doi.org/10.1016/J.GIE.2020.02.033

    Article  PubMed  Google Scholar 

  7. Nagata Y, Takeuchi K, Yamamoto T et al (2019) Peel-off resection of the pituitary gland for functional pituitary adenomas: pathological significance and impact on pituitary function. Pituitary 22:507–513. https://doi.org/10.1007/s11102-019-00980-w

    Article  PubMed  Google Scholar 

  8. Nagata Y, Takeuchi K, Yamamoto T et al (2019) Removal of the medial wall of the cavernous sinus for functional pituitary adenomas: a technical report and pathologic significance. World Neurosurg 126:53–58. https://doi.org/10.1016/J.WNEU.2019.02.134

    Article  PubMed  Google Scholar 

  9. Ishikawa T, Takeuchi K, Nagata Y et al (2018) Three types of dural suturing for closure of CSF leak after endoscopic transsphenoidal surgery. J Neurosurg 131:1625–1631. https://doi.org/10.3171/2018.4.JNS18366

    Article  Google Scholar 

  10. Giustina A, Chanson P, Bronstein MD et al (2010) A consensus on criteria for cure of acromegaly. J Clin Endocrinol Metab 95:3141–3148. https://doi.org/10.1210/jc.2009-2670

    Article  PubMed  CAS  Google Scholar 

  11. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. 2006 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90

  12. Zagoruyko S, Komodakis N (2016) Wide residual networks. Proceedings of the British Machine Vision Conference, p. 87.1–87.12. https://doi.org/10.5244/C.30.87

  13. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261–2269. https://doi.org/10.1109/CVPR.2017.243

  14. Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26:297–302. https://doi.org/10.2307/1932409

    Article  Google Scholar 

  15. Sørensen T (1948) A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on Danish commons. Munksgaard, Copenhagen

    Google Scholar 

  16. Rolston JD, Han SJ, Aghi MK (2016) Nationwide shift from microscopic to endoscopic transsphenoidal pituitary surgery. Pituitary 19:248–250. https://doi.org/10.1007/s11102-015-0685-y

    Article  PubMed  PubMed Central  Google Scholar 

  17. Nagata Y, Takeuchi K, Yamamoto T, Mizuno A, Wakabayashi T (2020) Fully endoscopic transcylinder trans-magendie foraminal approach for fourth ventricular cavernoma: a technical case report. World Neurosurg 142:104–107. https://doi.org/10.1016/j.wneu.2020.06.171

    Article  PubMed  Google Scholar 

  18. Nagata Y, Watanabe T, Nagatani T, Takeuchi K, Chu J, Wakabayashi T (2017) The multiscope technique for microvascular decompression. World Neurosurg 103:310–314. https://doi.org/10.1016/j.wneu.2017.04.059

    Article  PubMed  Google Scholar 

  19. Marcus HJ, Hughes-Hallett A, Cundy TP et al (2014) Comparative effectiveness of 3-dimensional vs 2-dimensional and high-definition vs standard-definition neuroendoscopy: a preclinical randomized crossover study. Neurosurgery 74:375–380. https://doi.org/10.1227/NEU.0000000000000249

    Article  PubMed  Google Scholar 

  20. Uozumi Y, Taniguchi M, Nakai T, Kimura H, Umehara T, Kohmura E (2020) Comparative evaluation of 3-dimensional high definition and 2-dimensional 4-K ultra-high definition endoscopy systems in endonasal skull base surgery. Oper Neurosurg (Hagerstown) 19:281–287. https://doi.org/10.1093/ons/opz426

    Article  PubMed  Google Scholar 

  21. Cho SS, Lee JYK (2019) Intraoperative fluorescent visualization of pituitary adenomas. Neurosurg Clin N Am 30:401–412. https://doi.org/10.1016/j.nec.2019.05.002

    Article  PubMed  Google Scholar 

  22. Akutsu N, Taniguchi M, Kohmura E (2016) Visualization of the normal pituitary gland during the endoscopic endonasal removal of pituitary adenoma by narrow band imaging. Acta Neurochir (Wien) 158:1977–1981. https://doi.org/10.1007/s00701-016-2901-6

    Article  PubMed  Google Scholar 

  23. Chang SW, Donoho DA, Zada G (2019) Use of optical fluorescence agents during surgery for pituitary adenomas: current state of the field. J Neurooncol 141:585–593. https://doi.org/10.1007/s11060-018-03062-2

    Article  PubMed  Google Scholar 

  24. Micko A, Rapoport BI, Youngerman BE et al (2020) Limited utility of 5-ALA optical fluorescence in endoscopic endonasal skull base surgery: a multicenter retrospective study. J Neurosurg 1–7. https://doi.org/10.3171/2020.5.JNS201171

  25. Marbacher S, Klinger E, Schwzer L et al (2014) Use of fluorescence to guide resection or biopsy of primary brain tumors and brain metastases. Neurosurg Focus 36:E10. https://doi.org/10.3171/2013.12.FOCUS13464

    Article  PubMed  Google Scholar 

  26. Vergeer RA, Theunissen REP, van Elk T et al (2022) Fluorescence-guided detection of pituitary neuroendocrine tumor (PitNET) tissue during endoscopic transsphenoidal surgery available agents, their potential, and technical aspects. Rev Endocr Metab Disord 23:647–657. https://doi.org/10.1007/s11154-022-09718-9

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  27. Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90. https://doi.org/10.1145/3065386

    Article  Google Scholar 

  28. Spadaccini M, Iannone A, Maselli R et al (2021) Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis. Lancet Gastroenterol Hepatol 6:793–802. https://doi.org/10.1016/S2468-1253(21)00215-6

    Article  PubMed  Google Scholar 

  29. Sharma P, Hassan C (2022) Artificial intelligence and deep learning for upper gastrointestinal neoplasia. Gastroenterology 162:1056–1066. https://doi.org/10.1053/J.GASTRO.2021.11.040

    Article  PubMed  Google Scholar 

  30. Repici A, Badalamenti M, Maselli R et al (2020) Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology 159:512-520.e7. https://doi.org/10.1053/J.GASTRO.2020.04.062

    Article  PubMed  Google Scholar 

  31. Su JR, Li Z, Shao XJ et al (2020) Impact of a real-time automatic quality control system on colorectal polyp and adenoma detection: a prospective randomized controlled study (with videos). Gastrointest Endosc 91:415-424.e4. https://doi.org/10.1016/J.GIE.2019.08.026

    Article  PubMed  Google Scholar 

  32. Wang P, Liu X, Berzin TM et al (2020) Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised study. Lancet Gastroenterol Hepatol 5:343–351. https://doi.org/10.1016/S2468-1253(19)30411-X

    Article  PubMed  Google Scholar 

  33. Staartjes VE, Volokitin A, Regli L, Konukoglu E, Serra C (2021) Machine vision for real-time intraoperative anatomic guidance: a proof-of-concept study in endoscopic pituitary surgery. Oper Neurosurg (Hagerstown) 21:242–247. https://doi.org/10.1093/ons/opab187

    Article  PubMed  Google Scholar 

  34. Rigante M, La Rocca G, Lauretti L et al (2017) Preliminary experience with 4K ultra-high definition endoscope: analysis of pros and cons in skull base surgery. Acta Otorhinolaryngol Ital 37:237–241. https://doi.org/10.14639/0392-100X-1684

  35. Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6:60. https://doi.org/10.1186/s40537-019-0197-0

    Article  Google Scholar 

  36. Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pretraining help deep learning? J Mach Learn Res 11:625–660

    Google Scholar 

  37. Lee EJ, Ahn JY, Noh T, Kim SH, Kim TS, Kim SH (2009) Tumor tissue identification in the pseudocapsule of pituitary adenoma: should the pseudocapsule be removed for total resection of pituitary adenoma? Neurosurgery 64:ons62–70. https://doi.org/10.1227/01.NEU.0000330406.73157.49

  38. Zhang X, Wang YG, Tan J et al (2022) Comparison of outcomes between intracapsular resection and pseudocapsule-based extracapsular resection for pituitary adenoma: a systematic review and meta-analysis. BMC Neurol 22:52. https://doi.org/10.1186/s12883-022-02574-9

    Article  PubMed  PubMed Central  Google Scholar 

  39. Qu X, Yang J, Sun JD et al (2011) Transsphenoidal pseudocapsule-based extracapsular resection for pituitary adenomas. Acta Neurochir (Wien) 153:799–806. https://doi.org/10.1007/s00701-011-0961-1

    Article  PubMed  Google Scholar 

  40. Bergman JJGHM, de Groof AJ, Pech O et al (2019) An interactive web-based educational tool improves detection and delineation of Barrett’s esophagus–related neoplasia. Gastroenterology 156:1299-1308.e3. https://doi.org/10.1053/j.gastro.2018.12.021

    Article  PubMed  Google Scholar 

  41. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66. https://doi.org/10.1109/TSMC.1979.4310076

    Article  Google Scholar 

Download references

Acknowledgements

We would like to thank Editage (www.editage.com) for their editing support on this manuscript.

Funding

This research was funded by the Industry-University Collaborative Project for Human Resource Development to Accelerate AI R&D in the Health and Medical Fields (MEXT).

Author information

Authors and Affiliations

  1. Department of Neurosurgery, Nagoya University Graduate School of Medicine, 65 Tsurumai-cho, Showa-ku, Nagoya, 466-8550, Japan

    Yutaro Fuse, Kazuhito Takeuchi, Yuichi Nagata & Ryuta Saito

  2. Academia-Industry Collaboration Platform for Cultivating Medical AI Leaders (AI-MAILs), Nagoya University Graduate School of Medicine, Nagoya, Japan

    Yutaro Fuse

  3. RIKEN Center for Advanced Intelligence Project, Tokyo, Japan

    Noriaki Hashimoto & Ichiro Takeuchi

  4. Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan

    Yusuke Takagi

  5. Department of Neurosurgery, Japanese Red Cross Aichi Medical Center Nagoya Daini Hospital, Nagoya, Japan

    Tetsuya Nagatani

  6. Department of Mechanical Systems Engineering, Graduate School of Engineering, Nagoya University, Nagoya, Japan

    Ichiro Takeuchi

Authors
  1. Yutaro Fuse
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kazuhito Takeuchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Noriaki Hashimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuichi Nagata
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yusuke Takagi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Tetsuya Nagatani
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ichiro Takeuchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Ryuta Saito
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conception and design: Y.F., K.T., and Y.N.; development of methodology: Y.F., K.T., N.H., Y.N., and I.T.; acquisition of data: Y.F. and Y.N.; image annotation: Y.N., K.T., and T.N.; data analysis and deep learning: Y.F., N.H., Y.T., and I.T.; interpretation of data: Y.F., K.T., N.H., Y.N., and I.T.; writing of the initial manuscript: Y.F. and Y.N.; manuscript revision: K.T., N.H., T.N., and I.T.; supervision: I.T. and R.S.; approval of the final manuscript: all authors.

Corresponding author

Correspondence to Kazuhito Takeuchi.

Ethics declarations

Ethics approval

This single-center observational study (2021-0050-2) was approved by our institutional review board. This research was conducted in accordance with the Declaration of Helsinki, as revised in 2013.

Consent to participate

Written informed consent was obtained from all prospectively analyzed patients. Informed consent was obtained from other patients through an opt-out approach on our institution’s website.

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 518 KB)

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

Fuse, Y., Takeuchi, K., Hashimoto, N. et al. Deep learning based identification of pituitary adenoma on surgical endoscopic images: a pilot study. Neurosurg Rev 46, 291 (2023). https://doi.org/10.1007/s10143-023-02196-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10143-023-02196-w

Keywords

Search

Navigation