Abstract
Breast-conserving surgery is a recommended treatment for early-stage breast cancer. Recurrence and post-operative complications are potential risks when margins are not entirely removed during surgery or when timing constraints in the OR limit extensive analysis of resected tissue. Raman spectroscopy (RS), a non-destructive optical technique, enables the acquisition of molecular signatures of tissue samples allowing confirmation of different diseases, including cancer. Typically, the measured spectra must be processed and used to train conventional machine learning classifiers for cancer/normal discrimination. However, there is a lack of real-time spatially-resolved information that allows confirmation of cancer at a specific site during surgery. In this paper, we propose a tissue characterization pipeline based on convolutional neural networks (CNN), using 4 \(\times \) 1D convolutional layers for automated feature extraction and a fully-connected layer as an alternative to classifying the complete RS spectra (without previous feature selection). Using 169 samples collected from 20 patients, we evaluated the performance of the proposed model, achieving an accuracy and sensitivity of 0.93(0.01) and 0.94(0.02), respectively, improving over traditional SVM-based models. Results demonstrate the potential of CNN models for classification in the OR and highlight the value of efficient signal processing to enhance their use for in-situ cancer detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cordero, E., Latka, I., Matthäus, C., Schie, I., et al.: In-vivo Raman spectroscopy: from basics to applications. J. Biomed. Opt. 23(07), 1 (2018). https://doi.org/10.1117/1.jbo.23.7.071210
Cui, S., Zhang, S., Yue, S.: Raman spectroscopy and imaging for cancer diagnosis. J. Healthcare Eng. 2018 (2018). https://doi.org/10.1155/2018/8619342
Dallaire, F., et al.: Quantitative spectral quality assessment technique validated using intraoperative in vivo Raman spectroscopy measurements. J. Biomed. Opt. 25(04), 1 (2020). https://doi.org/10.1117/1.jbo.25.4.040501
David, S., et al.: In situ Raman spectroscopy and machine learning unveil biomolecular alterations in invasive breast cancer. J. Biomed. Opt. 29(03), 1–33 (2023)
Desroches, J., Jermyn, M., Mok, K., Lemieux-Leduc, C., et al.: Characterization of a Raman spectroscopy probe system for intraoperative brain tissue classification. Biomed. Opt. Express 6(7), 2380 (2015). https://doi.org/10.1364/boe.6.002380
Desroches, J., et al.: Development and first in-human use of a Raman spectroscopy guidance system integrated with a brain biopsy needle. J. Biophotonics 12(3), 1–7 (2019). https://doi.org/10.1002/jbio.201800396
Elumalai, S., Managó, S., De Luca, A.C.: Raman microscopy: progress in research on cancer cell sensing. Sensors (Switzerland) 20(19), 1–19 (2020). https://doi.org/10.3390/s20195525
Gao, P., Han, B., Du, Y., Zhao, G., et al.: The clinical application of Raman spectroscopy for breast cancer detection. J. Spectrosc. 2017(1) (2017). https://doi.org/10.1155/2017/5383948
Giaquinto, A.N., Sung, H., Miller, K.D., Kramer, J.L., et al.: Breast cancer statistics, 2022. CA Cancer J. Clin. 72(6), 524–541 (2022)
Grajales, D., et al.: Image-guided Raman spectroscopy navigation system to improve transperineal prostate cancer detection. Part 2: in-vivo tumor-targeting using a classification model combining spectral and MRI-radiomics features. J. Biomed. Opt. 27(09), 1–16 (2022). https://doi.org/10.1117/1.jbo.27.9.095004
Haka, A.S., Shafer-Peltier, K.E., Fitzmaurice, M., Crowe, J., et al.: Diagnosing breast cancer by using Raman spectroscopy. Proc. Natl. Acad. Sci. USA 102(35), 12371–12376 (2005). https://doi.org/10.1073/pnas.0501390102
Jacobs, L.: Positive margins: the challenge continues for breast surgeons. Ann. Surg. Oncol. 15(5), 1271–1272 (2008). https://doi.org/10.1245/s10434-007-9766-0
Kazemzadeh, M., Hisey, C.L., Martinez-calderon, M., Chamley, L.W., et al.: Deep learning as an improved method of preprocessing biomedical raman spectroscopy data, pp. 1–9 (2022). https://doi.org/10.36227/techrxiv.19435718.v1
Lazaro-Pacheco, D., Shaaban, A.M., Rehman, S., Rehman, I.: Raman spectroscopy of breast cancer. Appl. Spectrosc. Rev. 55(6), 439–475 (2020). https://doi.org/10.1080/05704928.2019.1601105
Lemoine, É., Dallaire, F., Yadav, R., Agarwal, R., et al.: Feature engineering applied to intraoperative in vivo Raman spectroscopy sheds light on molecular processes in brain cancer: a. In: The Royal Society of Chemistry, pp. 6517–6532 (2019). https://doi.org/10.1039/c9an01144g
Lopes, R.M., Silveira, L., Silva, M.A.R., Leite, K.R.M., et al.: Diagnostic model based on Raman spectra of normal, hyperplasia and prostate adenocarcinoma tissues in vitro. Spectroscopy 25(2), 89–102 (2011). https://doi.org/10.3233/SPE-2011-0494
Ma, D., Shang, L., Tang, J., Bao, Y., et al.: Classifying breast cancer tissue by Raman spectroscopy with one-dimensional convolutional neural network. Spectrochimica Acta - Part A: Molec. Biomolec. Spectrosc. 256, 119732 (2021). https://doi.org/10.1016/j.saa.2021.119732
Pardo, A., Streeter, S.S., Maloney, B.W., et al.: Modeling and synthesis of breast cancer optical property signatures with generative models. IEEE Trans. Med. Imaging 40(6), 1687–1701 (2021). https://doi.org/10.1109/TMI.2021.3064464
Paszke, A., Gross, S., Massa, F., Lerer, A., et al.: PyTorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)
Petersen, D., Naveed, P., Ragheb, A., Niedieker, D., et al.: Raman fiber-optical method for colon cancer detection: cross-validation and outlier identification approach. Spectrochimica Acta - Part A 181, 270–275 (2017). https://doi.org/10.1016/j.saa.2017.03.054
Plante, A., Dallaire, F., Grosset, A.A., Nguyen, T., Birlea, M., et al.: Dimensional reduction based on peak fitting of Raman micro spectroscopy data improves detection of prostate cancer in tissue specimens. J. Biomed. Opt. 26(11), 116501 (2021). https://doi.org/10.1117/1.jbo.26.11.116501
Santilli, A.M., Jamzad, A., Janssen, N.N., et al.: Perioperative margin detection in basal cell carcinoma using a deep learning framework. Int. J. Comput. Assist. Radiol. Surg. 15(5), 887–896 (2020). https://doi.org/10.1007/s11548-020-02152-9
Sheehy, G., Picot, F., Dallaire, F., Ember, K., Nguyen, T., Leblond, F.: Open-sourced Raman spectroscopy data processing package implementing a novel baseline removal algorithm validated from multiple datasets acquired in human tissue and biofluids. J. Biomed. Opt. 28(February), 1–20 (2023). https://doi.org/10.1117/1.JBO.28.2.025002
St John, E.R., Balog, J., McKenzie, J.S., Rossi, M., et al.: Rapid evaporative ionisation mass spectrometry of electrosurgical vapours for the identification of breast pathology: Towards an intelligent knife for breast cancer surgery. Breast Cancer Res. 19(1), 1–14 (2017). https://doi.org/10.1186/s13058-017-0845-2
Stomp-Agenant, M., van Dijk, T., R. Onur, A., Grimbergen, M., et al.: In vivo Raman spectroscopy for bladder cancer detection using a superficial Raman probe compared to a nonsuperficial Raman probe. J. Biophotonics 15(6), 1–9 (2022). https://doi.org/10.1002/jbio.202100354
Van Rossum, G., Drake, F.: Python 3 Reference Manual. CreateSpace, Scotts Valley (2009)
Zhang, L., Li, C., Peng, D., Yi, X., et al.: Raman spectroscopy and machine learning for the classification of breast cancers. Spectrochimica Acta - Part A: Molec. Biomolec. Spectrosc. 264, 120300 (2022). https://doi.org/10.1016/j.saa.2021.120300
Zhou, M., Hu, Y., Wang, R., Guo, T., et al.: An end-to-end deep learning approach for Raman spectroscopy classification. J. Chemom. 37, 1–16 (2022). https://doi.org/10.1002/cem.3464
Acknowledgements
This research was undertaken thanks, in part, to funding from the Canada First Research Excellence Fund through the TransMedTech Institute.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosures
Frédéric Leblond is co-founder of ODS Medical (now Reveal Surgical) formed in 2015 to commercialize a Raman spectroscopy system for neurosurgical and prostate surgery applications. He has ownership and patents in the company.
Appendix
Appendix
Figure 4 shows the results of the hyperparameter optimization. Except for the learning rate, where a value of 0.001 presented better performance than the alternatives, variations in the other parameters did not significantly affect the classification performance. Thus, for the proposed model (described in Sect. 3.3), we selected those that presented a subtle advantage; in the case of the number of epochs, the range of training time for 30 epochs was 91–102 s, while for 60 epochs, the range was 173–199 s, so the former was chosen.
AUC (mean value in red) for the 1D-CNN model during the hyperparameter optimization, testing different epochs, learning rates, number of layers, and features. Selected values are shown with an arrow. (Color figure online)
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Grajales, D. et al. (2023). Towards Real-Time Confirmation of Breast Cancer in the OR Using CNN-Based Raman Spectroscopy Classification. In: Ali, S., van der Sommen, F., van Eijnatten, M., Papież, B.W., Jin, Y., Kolenbrander, I. (eds) Cancer Prevention Through Early Detection. CaPTion 2023. Lecture Notes in Computer Science, vol 14295. Springer, Cham. https://doi.org/10.1007/978-3-031-45350-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-45350-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45349-6
Online ISBN: 978-3-031-45350-2
eBook Packages: Computer ScienceComputer Science (R0)
