Fast Segmentation of Convex Cyst-like Structures in Gelatin Soft Tissue Phantoms under Ultrasound Imaging with Artifacts and Limited Training Samples

• Autorzy: Drozd Dalia , Ciszkiewicz Adam

Identyfikatory

DOI

10.12913/22998624/188390

• Języki publikacji: EN

Abstrakty

EN

Ultrasound imaging is common for surgical training and development of medical robotics systems. Recent advancements in surgical training often utilize soft-tissue phantoms based on gelatin, with additional objects inserted to represent different, typically fluid-based pathologies. Segmenting these objects from the images is an important step in the development of training and robotic systems. The current study proposes a simple and fast algorithm for segmenting convex cyst-like structures from phantoms under very low training sample scenarios. The algorithm is based on a custom two-step thresholding procedure with additional post-processing with two trainable parameters. Two large phantoms with convex cysts are created and used to train the algorithm and evaluate its performance. The train/test procedure are repeated 60 times with different dataset splits and prove the viability of the solution with only 4 training images. The DICE coefficients were on average at 0.92, while in the best cases exceeded 0.95, all with fast performance in single-thread operation. The algorithm might be useful for development of surgical training systems and medical robotic systems in general.

Słowa kluczowe

EN

thresholding; medical imaging; computer vision; ultrasound imaging; algorithm

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2024
• Tom: Vol. 18, no 4
• Strony: 89--96
• Opis fizyczny: Bibliogr. 29 poz., fig., tab.

Twórcy

autor

Drozd Dalia

• Faculty of Mechanical Engineering, Cracow University of Technology, ul. Warszawska 24, 31-155 Cracow, Poland

autor

Ciszkiewicz Adam

• Faculty of Mechanical Engineering, Cracow University of Technology, ul. Warszawska 24, 31-155 Cracow, Poland

• https://orcid.org/0000-0002-7816-5193

Bibliografia

• 1. Kuhl C.K., Schrading S., Leutner C.C., Morakkabati-Spitz N., Wardelmann E., Fimmers R., Kuhn W., and Schild H. Mammography, breast ultrasound, and magnetic resonance imaging for surveillance of women at high familial risk for breast cancer. J. Clin. Oncol. Wolters Kluwer 2005, 23(33): 8469–76, https://doi.org/10.1200/JCO.2004.00.4960.
• 2. Schoots I.G., Roobol M.J., Nieboer D., Bangma C. H., Steyerberg E.V., Hunink M.G.M. Magnetic resonance imaging–targeted biopsy may enhance the diagnostic accuracy of significant prostate cancer detection compared to standard transrectal ultrasound-guided biopsy: a systematic review and metaanalysis. Eur. Urol. 2015, 68(3): 438–50, https://doi.org/https://doi.org/10.1016/j.eururo.2014.11.037.
• 3. Li J.W., Karmakar M.K., Li X., Fanzca W.H.K., Kee W.D.N. Gelatin-agar lumbosacral spine phantom. J. Ultrasound Med. John Wiley & Sons, Ltd 2011, 30(2): 263–72, https://doi.org/https://doi.org/10.7863/jum.2011.30.2.263.
• 4. Richardson C., Bernard S., and Dinh V.A. A costeffective, gelatin-based phantom model for learning ultrasound-guided fine-needle aspiration procedures of the head and neck. J. Ultrasound Med. John Wiley & Sons, Ltd 2015, 34(8): 1479–84, https://doi.org/https://doi.org/10.7863/ultra.34.8.1479.
• 5. Selame L.A., Risler Z., Zakaria S.J., Hughes L.P., Lewiss R.E., Kehm K., Goodsell K.,
• 6. Kalwani R., Mirsch D., Kluger S.B., Au A. A comparison of homemade vascular access ultrasound phantom models for peripheral intravenous catheter insertion. J. Vasc. Access SAGE Publications Ltd STM 2020, 22(6): 891–97, https://doi.org/10.1177/1129729820961941.
• 7. Zhao X., Ersoy E., Ng D.L. Comparison of low-cost phantoms for ultrasound-guided fine-needle aspiration biopsy training. J. Am. Soc. Cytopathol. 2023, 12(4): 275–83, https://doi.org/https://doi.org/10.1016/j.jasc.2023.03.005.
• 8. Liang K., Light E.D., Rogers A.J., von Allmen D., Smith S.W. 3-D Ultrasound guidance of autonomous surgical robotics: Feasibility studies. Proc. - IEEE Ultrason. Symp. 2009, 582–85, https://doi.org/10.1109/ULTSYM.2009.5441429.
• 9. Liang K., Rogers A.J., Light E.D., von Allmen D., Smith S.W. Three-dimensional ultrasound guidance of autonomous robotic breast biopsy: feasibility study. Ultrasound Med. Biol. 2010, 36(1): 173–77, https://doi.org/10.1016/j.ultrasmedbio.2009.08.014.
• 10. Liang K., Rogers A.J., Light E.D., von Allmen D., Smith S.W. Simulation of autonomous robotic multiple-core biopsy by 3D ultrasound guidance. Ultrason. Imaging NIH Public Access 2010, 32(2): 118–27.
• 11. Giannotti E., Jethwa K., Closs S., Sun R., Bhatti H., Jameset J., Clarke C. Promoting simulation-based training in radiology: a homemade phantom for the practice of ultrasound-guided procedures. Br. J. Radiol. 2022, 95(1137): 20220354, https://doi.org/10.1259/bjr.20220354.
• 12. Feng Y., Qiu S., Chen Y., Ma S. Viscoelastic Characterization of soft tissue-mimicking gelatin phantoms using indentation and magnetic resonance elastography. JoVE MyJoVE Corp 2022, (183): e63770, https://doi.org/doi:10.3791/63770.
• 13. Antoniou A. and Damianou C. MR relaxation properties of tissue-mimicking phantoms. Ultrasonics 2022, 119: 106600, https://doi.org/https://doi.org/10.1016/j.ultras.2021.106600.
• 14. Jonasson H., Anderson C.D., and Saager R.B. Water and hemoglobin modulated gelatin-based phantoms to spectrally mimic inflamed tissue in the validation of biomedical techniques and the modeling of microdialysis data. J. Biomed. Opt. 2022, 27(7): 74712, https://doi.org/10.1117/1.JBO.27.7.074712.
• 15. Anugrah M.A., Suryani S., Ilyas S., Mutmainna I., Fahri A.N., Jusmawang, Tahir D. Composite gelatin/Rhizophora SPP particleboards/PVA for soft tissue phantom applications. Radiat. Phys. Chem. 2020, 173: 108878, https://doi.org/https://doi.org/10.1016/j.radphyschem.2020.108878.
• 16. Houten E.E.W. Van, Viviers D., McGarry M.D.J., vR., Perriñez P.R., Perreard I.I., Weaver J. B., Paulsen K.D. Subzone based magnetic resonance elastography using a Rayleigh damped material model. Med. Phys. John Wiley & Sons, Ltd 2011, 38(4): 1993–2004, https://doi.org/https://doi.org/10.1118/1.3557469.
• 17. Huang Q., Luo Y., Zhang Q. Breast ultrasound image segmentation: a survey. Int. J. Comput. Assist. Radiol. Surg. 2017, 12(3): 493–507, https://doi.org/10.1007/s11548-016-1513-1.
• 18. Huang J., Triedman J.K., Vasilyev N.V, Suematsu Y., Cleveland R.O., Dupont P.E. Imaging artifacts of medical instruments in ultrasound-guided interventions. J. Ultrasound Med. John Wiley & Sons, Ltd 2007, 26(10): 1303–22, https://doi.org/https://doi.org/10.7863/jum.2007.26.10.1303.
• 19. Ramme A.J., Guss M.S., Vira S., Vigdorchik J.M., Newe A., Raithel E., Chang G. Evaluation of automated volumetric cartilage quantification for hip preservation surgery. J. Arthroplasty 2015, https://doi.org/10.1016/j.arth.2015.08.009.
• 20. Davignon F., Deprez J.-F., Basset O. A parametric imaging approach for the segmentation of ultrasound data. Ultrasonics 2005, 43(10): 789–801, https://doi.org/https://doi.org/10.1016/j.ultras.2005.06.001.
• 21. Noh Y.-G., Ryu W.-S., Schellingerhout D., Park J., Chung J., Jeong S.-W., Gwak D.-S., Kim B.J., Kim J.-T., Hong K.-S., Lee K.B,, Park T.H., Park S.-S., Park J.-M., Kang K., Cho Y.-J., Park H.-K., Lee B.-C., Yu K.-H, Oh M.S., Lee S.J., Kim J.G., Cha J.-K., Kim D.-H., Lee J., Park M.S., Kim D., Bang O.Y., Kim E.Y., Sohn C.-H, Kim H., Bae H.-J., Kimet D.-E. Deep learning algorithms for automatic segmentation of acute cerebral infarcts on diffusion-weighted images: Effects of training data sample size, transfer learning, and data features. medRxiv 2023, 2023.07.02.23292150, https://doi.org/10.1101/2023.07.02.23292150
• 22. Maxwell A., Li R., Yang B., Weng H., Ou A., Hong H., Zhou Z., Gong P., Zhang 23. C. Deep learning architectures for multi-label classification of intelligent health risk prediction. BMC Bioinformatics 2017, 18(14): 523, https://doi.org/10.1186/s12859-017-1898-z.
• 24. Capelin M., Martinez G.A.S., Xing Y., Siquerila A. Analysis of wire rolling processes using convolutional neural networks. Adv. Sci. Technol. Res. J. 2024, 18(2): 103–14, https://doi.org/10.12913/22998624/183699.
• 25. Plaksyvyi A., Skublewska-Paszkowska M., and Powroznik P. A comparative analysis of image segmentation using classical and deep learning approach. Adv. Sci. Technol. Res. J. 2023, 17(6): 127–39, https://doi.org/10.12913/22998624/172771.
• 26. Ciszkiewicz A., Milewski G., Lorkowski J. Baker’s Cyst Classification Using Random Forests. In: Proceedings of the Federated Conference on Computer Science and Information Systems 2018, https://doi.org/10.15439/2018F89.
• 27. Walt S. van der, Schönberger J.L., Nunez-Iglesias J., Boulogne F., Warner J.D., Yager N., Gouillart E., Yu T. scikit-image: image processing in Python. Peer J 2014, 2: e453, https://doi.org/10.7717/peerj.453.
• 28. Dice L.R. Measures of the amount of ecologic association between species. Ecology John Wiley & Sons, Ltd 1945, 26(3): 297–302, https://doi.org/https://doi.org/10.2307/1932409.
• 29. Ciszkiewicz A., Lorkowski J., Milewski G. Differential evolution and cost-maps for needle path planning in Baker’s cyst aspiration. Acta Bioeng. Biomech. 2022, 24(4): 39–47, https://doi.org/10.37190/ABB-02157-2022-02.

Uwagi

1) Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024). 2) Błąd w bibliografii: poz. 5 i 6. stanowią jedno źródło.