Medical Applications of Laser Molecular Imaging and Machine Learning最新文献

Supplemental Materials 补充材料

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.sup

Y. Kistenev, A. Borisov, D. Vrazhnov

引用次数: 0

Back Matter 回到问题

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.bm

Y. Kistenev, A. Borisov, D. Vrazhnov

引用次数: 0

Laser-based Molecular Data-Acquisition Technologies 基于激光的分子数据采集技术

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.CH2

Y. Kistenev, A. Borisov, D. Vrazhnov

{"title":"Laser-based Molecular Data-Acquisition Technologies","authors":"Y. Kistenev, A. Borisov, D. Vrazhnov","doi":"10.1117/3.2599935.CH2","DOIUrl":"https://doi.org/10.1117/3.2599935.CH2","url":null,"abstract":"A “gold standard” for the verification of many diseases is histopathology analysis of a biopsy sample. A biopsy is the extraction of cells or tissues for examination. The latter’s disadvantages are that it is time consuming and invasive. In cancer detection, there is a high risk of metastasis due to the cancer cells possible dissimilation through blood or lymph vessels from the region of surgery. The term “optical biopsy” has entered into common usage in the field of biomedical optics. This term has internal inconsistency because “biopsy” refers specifically to tissue removal, whereas the implication of “optical” is that tissue is not removed. Regardless, “optical biopsy” is commonly understood as optical measurements, often a kind of spectroscopy, to noninvasively (or minimally invasively) perform in vivo and real-time diagnosis. Depending on an analyzed diagnostic agent, the optical biopsy is often divided into breath biopsy, liquid biopsy, and tissue biopsy. Optical biopsy can be used as a diagnostic tool or to reveal specific (patho-) physiological mechanisms. The latter is connected with the chemical-based identification of particular compounds. But an individual molecular compound hardly serves as a biomarker of a specific disease due to low specificity. Reliable diagnostics is possible through the control of a group (profile) of molecular biomarkers. Probabilistic discrimination of biomarker profiles can be conducted by a pattern-recognition approach, which forms the basis for assessing acceptable diagnostic accuracy. The chemical analytical-based identification of individual molecular biomarkers is not strictly necessary in a clinical setting; also, note that the biochemical origin of most molecular biomarkers is unknown.","PeriodicalId":285501,"journal":{"name":"Medical Applications of Laser Molecular Imaging and Machine Learning","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127022053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fundamental Concepts Related to Laser Molecular Imaging 有关激光分子成像的基本概念

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.ch1

Y. Kistenev, A. Borisov, D. Vrazhnov

引用次数: 0

Medical Applications 医学应用

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.ch5

Y. Kistenev, A. Borisov, D. Vrazhnov

引用次数: 0

Clusterization and Predictive Model Construction 聚类与预测模型构建

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.CH4

Y. Kistenev, A. Borisov, D. Vrazhnov

引用次数: 0

Informative Feature Extraction 信息特征提取

Medical Applications of Laser Molecular Imaging and Machine Learning Pub Date : 2021-07-26 DOI: 10.1117/3.2599935.CH3

Y. Kistenev, A. Borisov, D. Vrazhnov

{"title":"Informative Feature Extraction","authors":"Y. Kistenev, A. Borisov, D. Vrazhnov","doi":"10.1117/3.2599935.CH3","DOIUrl":"https://doi.org/10.1117/3.2599935.CH3","url":null,"abstract":"Laser molecular imaging produces high-dimension data with the structure dependent on the optical modality, laser type, detection method, kind of sample, etc. Generally, data’s high dimension corresponds to a situation where the number of initial parameters exceeds by orders of magnitude the number of hidden independent variables, e.g., when the number of measured absorption coefficients of a complex gas mixture exceeds by an order or more the quantity of pure components in the mixture. The high-dimension data are hard to use for predictive data model construction due to the “curse of dimensionality” problem formulated by R. Bellman. Essentially, when the feature vector’s dimension increases, the volume of data needed for classifier training grows exponentially. This is because the difference between two random vectors tends to zero as their dimension increases according to the central limit theorem. One of the main goals of feature extraction is to overcome this problem. The universal approach for this is in decreasing the data dimension. Concrete ways depend on the data origin. In particular, 2D-3D images can be decomposed into small geometrical parts with similar properties named textures. The texture approach allows one to find a compact description of the initial image. Molecular spectra can be considered as a degenerate case of molecular imaging data in a case of a homogeneous medium when we can study only one “point” to describe the whole sample. Feature vector dimension reduction includes feature selection and feature extraction. The difference between them is only in the ways used to get the result. This chapter describes these methods in details sufficient for practical applications. The Python codes for the most useful analytical methods described in the chapter are presented in the Supplemental Materials.","PeriodicalId":285501,"journal":{"name":"Medical Applications of Laser Molecular Imaging and Machine Learning","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130270432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0