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

• 成果类型: Article
• 署名作者: Tabata, Koji; Kawagoe, Hiroyuki; Taylor, J. Nicholas; Mochizuki, Kentaro; Kubo, Toshiki; Clement, Jean-Emmanuel; Kumamoto, Yasuaki; Harada, Yoshinori; Nakamura, Atsuyoshi; Fujita, Katsumasa; Komatsuzaki, Tamiki
• 署名单位: Hokkaido University; Hokkaido University; University of Osaka; Kyoto Prefectural University of Medicine; University of Osaka; Hokkaido University; National Institute of Advanced Industrial Science & Technology (AIST); Hokkaido University; University of Osaka
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-14696
• DOI: 10.1073/pnas.2304866121
• 发表日期: 2024-03-19
• 关键词: deep neural-networks; high-sensitivity; go; game; algorithm; shogi; chess

摘要

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 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 points during measurement remains a challenge. To address this, we developed imaging technique based on a reinforcement learning in machine learning (ML). This ML approach adaptively feeds back optimal illumination pattern during measurement to detect the existence of specific characteristics of interest, allowing faster measurements while guaranteeing discrimination accuracy. Using a set of Raman images of human follicular thyroid and follicular thyroid carcinoma cells, we showed that our technique requires 3,333 to 31,683 times smaller number of illuminations for discriminating the phenotypes than raster scanning. To quantitatively evaluate the number of illuminations depending on the requisite discrimination accuracy, prepared a set of polymer bead mixture samples to model anomalous and normal tissues. We then applied a home-built programmable-illumination microscope equipped our algorithm, and confirmed that the system can discriminate the sample conditions with 104 to 4,350 times smaller number of illuminations compared to standard illumination Raman microscopy. The proposed algorithm can be applied to other of microscopy that can control measurement condition on the fly, offering an approach for the acceleration of accurate measurements in various applications including medical diagnosis.