**5. Conclusions**

Our results clearly demonstrate that a fibre-optic TEF probe accompanied with ML algorithms such as k-Nearest Neighbours or AdaBoost is highly promising for real-time in situ di fferentiation between cancerous and healthy tissues by detection the information about the tissue type that is encoded in the fluorescence spectrum. This detection can be supplemented and enhanced by parallel collection and classification of blood perfusion rhythmic data, especially the one that denote cardiac oscillations. Clearly, the data collection procedure as well as the design of the proposed fibre-optic probe have to be improved. Once it is done, we are convinced that the proposed fibre probe together with the elaborated ML techniques constitutes a highly promising device for a prompt and precise in situ decision-making and would allow to choose the optimal surgical tactics during the tumour resection.

As a next step, we will elaborate a procedure for the collection of data with much higher quality as well as improve the design of the fibre-optic probe by, for instance, dropping the 365 nm excitation channel and introducing a non-contact proximity sensor.

**Author Contributions:** Original draft preparation, data curation and processing, data acquisition software, E.Z.; data processing, draft preparation, M.Z.; measurements, methodology, data curation, E.P.; measurements, K.K.; data acquisition setup, methodology, V.D.; experiments at the Orel Regional Clinical Hospital, conceptualisation, A.M.; conceptualisation, S.S.; initiated and supervised the work, project administration, E.U.R.; funding acquisition, supervision, project administration, A.D.; all authors edited the manuscript. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research received no external funding.

**Acknowledgments:** This study was supported by the Russian Science Foundation under project No. 18-15-00201 (development of experimental setup and data acquisition). Special thanks are extended to the patients of the Orel Regional Clinical Hospital who kindly agreed to take part in the studies in the framework of their planned minimally invasive surgical intervention. M.Z. would like to acknowledge the funding received within the H2020-MSCA-IF-2017 scheme (grant No. 792421). E.Z. acknowledges the support of the Academy of Finland (grant No. 318281). V.D. acknowledges the funding received within the H2020-MSCA-IF-2018 scheme (grant No. 839888).

**Conflicts of Interest:** The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.
