Prof. Tamiki Komatsuzaki Profile

Prof. Tamiki Komatsuzaki

at Hokkaido Univ

SPIE Involvement:

Conference Program Committee | Author

Proceedings Article | 20 June 2024 Presentation + Paper

On-the-fly Raman microscopy guaranteeing the accuracy of discrimination

Tamiki Komatsuzaki

Proceedings Volume 13006, 1300602 (2024) https://doi.org/10.1117/12.3016553

KEYWORDS: Raman spectroscopy, Light sources and illumination, Evolutionary algorithms, Artificial intelligence, Microscopes, Tissues, Microscopy, Machine learning, Diagnostics, Tumor growth modeling

Read Abstract +

Accelerating the measurement for discrimination of samples, such as classification of cell phenotype, is crucial when faced with significant time and cost constraints. Spontaneous Raman microscopy offers label-free, rich chemical information but suffers from long acquisition time due to extremely small scattering cross-sections. One possible approach to accelerate the measurement is by measuring necessary parts with a suitable number of illumination points. However, how to design these points during measurement remains a challenge. To address this, we developed an imaging technique based on a reinforcement learning in machine learning (ML). This ML approach adaptively feeds back “optimal” illumination pattern during the measurement to detect the existence of specific characteristics of interest, allowing faster measurements while guaranteeing discrimination accuracy. Here accurate discrimination means that a user can determine an allowance error rate δ a priori to ensure that the diagnosis can be accurately accomplished with probability greater than (1 − δ) × 100%. We present our algorithm and our simulation studies using Raman images in the diagnosis of follicular thyroid carcinoma, and show that this protocol can accelerate in speedy and accurate diagnoses faster than the point scanning Raman microscopy that requires the full detailed scanning over all pixels. Given a descriptor based on Raman signals to quantify the degree of the predefined quantity to be evaluated, e.g., the degree of cancers, anomaly or defects of materials, the on-the-fly Raman image microscopy evaluates the upper and lower confidence bounds in addition to the sample average of that quantity based on finite point illuminations, and then the bandit algorithm feedbacks the desired illumination pattern to accelerate the detection of the anomaly, during the measurement to the microscope. Several updated realizations of the programmable illumination microscope using a spatial light modulator and line illumination will be presented.

Proceedings Article | 19 June 2024 Presentation

Correction for extrinsic background in Raman hyperspectral images: suppression of data leakage

Tamiki Komatsuzaki

Proceedings Volume PC13011, PC1301101 (2024) https://doi.org/10.1117/12.3016551

KEYWORDS: Raman spectroscopy, Hyperspectral imaging, Biological samples, Imaging systems, Contamination, Chemometrics, Biomedical optics, Tumor growth modeling, Thyroid, Statistical modeling

Read Abstract +

Proceedings Article | 13 March 2024 Poster

Development of information theoretic analysis to quantify information specific to Raman images

Ryoya Kondo, Yuta Mizuno, Jean-Emmanuel Clement, Kentaro Mochizuki, Katsumasa Fujita, Yoshinori Harada, Tamiki Komatsuzaki

Proceedings Volume PC12839, PC128390W (2024) https://doi.org/10.1117/12.3002493

KEYWORDS: Raman spectroscopy, Liver, Diseases and disorders, Imaging spectroscopy, Chemical analysis, Spectroscopy, Chemical species, Visualization, Tissues, Reflection

Proceedings Article | 13 March 2024 Presentation

On-the-fly slit-scanning confocal Raman microscope guaranteeing the accuracy of discrimination

Toshiki Kubo, Koji Tabata, Hiroyuki Kawagoe, James Nicholas Taylor, Jean-Emmanuel Clement, Yoshinori Harada, Atsuyoshi Nakamura, Katsumasa Fujita, Tamiki Komatsuzaki

Proceedings Volume PC12839, PC128390D (2024) https://doi.org/10.1117/12.3001684

KEYWORDS: Raman spectroscopy, Confocal microscopy, Biological samples, Microscopes, Polymethylmethacrylate, Cancer, Liver, Cancer detection, Adipose tissue, Tissues

Read Abstract +

Proceedings Article | 12 March 2024 Presentation + Paper

Fast and accurate discrimination high-speed Raman imaging combined with multi-armed bandit algorithm in reinforcement learning

Koji Tabata, Hiroyuki Kawagoe, Toshiki Kubo, James Taylor, Kentaro Mochizuki, Jean-Emmanuel Clement, Yasuaki Kumamoto, Yoshinori Harada, Atsuyoshi Nakamura, Katsumasa Fujita, Tamiki Komatsuzaki

Proceedings Volume 12853, 128530A (2024) https://doi.org/10.1117/12.3002689

KEYWORDS: Raman spectroscopy, Light sources and illumination, Machine learning, Medical research, Random forests, Microscopy, Microscopes, Engineering, Diagnostics, Decision trees

Read Abstract +

Proceedings Article | 20 September 2023 Paper

High-speed Raman spectroscopic diagnosis guaranteeing accuracy by reinforcement learning

Toshiki Kubo, Koji Tabata, Hiroyuki Kawagoe, James Taylor, Kentaro Mochizuki, Jean-Emmanuel Clement, Yasuaki Kumamoto, Yoshinori Harada, Atsuyoshi Nakamura, Katsumasa Fujita, Tamiki Komatsuzaki

Proceedings Volume 12608, 126081A (2023) https://doi.org/10.1117/12.3007934

KEYWORDS: Raman spectroscopy, Microscopy, Machine learning, Spectroscopy, Light sources and illumination, Raman scattering, Medical research, Thyroid, Microscopes, Engineering

Read Abstract +

Proceedings Article | 16 March 2023 Paper

On-the-fly Raman microscopy guaranteeing the accuracy of diagnosis by reinforcement learning

Tamiki Komatsuzaki

Proceedings Volume 12390, 1239003 (2023) https://doi.org/10.1117/12.2652139

KEYWORDS: Raman spectroscopy, Microscopes, Machine learning, Light sources and illumination, Microscopy, Thyroid, Design and modelling, Diagnostics, Cancer, Algorithm development

Read Abstract +

Proceedings Article | 30 May 2022 Presentation

On-the-fly Raman image microscopy by reinforcement machine learning

Tamiki Komatsuzaki, Koji Tabata, Hiroyuki Kawagoe, James Nicholas Taylor, Kentaro Mochizuki, Toshiki Kubo, Jean-Emmanuel Clement, Yasuaki Kumamoto, Yoshinori Harada, Atsuyoshi Nakamura, Katsumasa Fujita

Proceedings Volume PC12144, PC121440B (2022) https://doi.org/10.1117/12.2622529

KEYWORDS: Raman spectroscopy, Microscopes, Microscopy, Algorithm development, Machine learning, Error analysis, Cancer, Statistical analysis, Signal to noise ratio, Signal detection

Read Abstract +

Showing 5 of 8 publications

Conference Committee Involvement (3)

High-Throughput Biophotonics: Imaging, Spectroscopy, and Beyond X

25 January 2025 | San Francisco, California, United States

Data Science for Photonics and Biophotonics

10 April 2024 | Strasbourg, France

High-Speed Biomedical Imaging and Spectroscopy IX

27 January 2024 | San Francisco, California, United States

Keywords/Phrases

Search In:

Publication Years