Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386448466> ?p ?o ?g. }
- W4386448466 abstract "ABSTRACT Raman spectroscopy has been widely used for label-free biomolecular analysis of cell and tissue for pathological diagnosis in vitro and in vivo . AI technology facilitates disease diagnosis based on Raman spectroscopy including machine learning (PCA and SVM), manifold learning (UMAP) and deep learning (ResNet and AlexNet). However, it is not clear how to optimize the appropriate AI classification model for different types of Raman spectral data. Here, We selected five representative Raman spectral datasets, including endometrial carcinoma, hepatoma extracellular vesicles, bacteria, melanoma cell, diabetic skin, with different characteristics regarding sample size, spectral data size, Raman shift range, tissue sites, Kullback-Leibler (KL) divergence, and key Raman shifts, explore the performance of different AI models (e.g. PCA-SVM, SVM, UMAP-SVM, ResNet or AlexNet). Tissue sites mean that spectral collection sites from sample, KL divergence means the divergence between spectra of different types. We found that for dataset of large spectral data size, Resnet performed better than PCA-SVM and UMAP, for dataset of small spectral data size, PCA-SVM or UMAP performed better. We also optimized the network parameters (e.g. principal components, activation function, and loss function) of AI model based on data characteristics. Using AI classification models, the mean area under receiver operating characteristic curves (AUC) for representative datasets reached 0.966, with mean sensitivity of 89.6%, mean specificity of 95.4%, mean accuracy of 93.4%, and mean time expense of 5 seconds. By using data characteristic assisted AI classification model, the accuracy improve from 85.1% to 94.6% for endometrial carcinoma grading, from 77.l% to 90.7% for hepatoma extracellular vesicles detection, from 89.3% to 99.7% for melanoma cell detection, from 88.1% to 97.9% for bacterial identification, from 53.7% to 85.5% for diabetic skin screening. Furthermore, according to the saliency maps, we found classification-associated biomolecules (e.g. nucleic acid, tyrosine, tryptophan, cholesteryl ester, fatty acid, and collagen), which contribute to the pathological diagnosis classification. Data characteristic assisted AI classification model was demonstrated to improve the robustness and accuracy of Raman spectroscopy in pathological classification. Collectively, this study opens up new opportunities for accurate and rapid Raman optical biopsy." @default.
- W4386448466 created "2023-09-06" @default.
- W4386448466 creator A5020769112 @default.
- W4386448466 creator A5022256556 @default.
- W4386448466 creator A5024316929 @default.
- W4386448466 creator A5024338716 @default.
- W4386448466 creator A5029072614 @default.
- W4386448466 creator A5036964506 @default.
- W4386448466 creator A5040899817 @default.
- W4386448466 creator A5048379858 @default.
- W4386448466 creator A5052812929 @default.
- W4386448466 creator A5056337166 @default.
- W4386448466 creator A5058278009 @default.
- W4386448466 creator A5059845740 @default.
- W4386448466 creator A5067010958 @default.
- W4386448466 creator A5067974430 @default.
- W4386448466 creator A5082230753 @default.
- W4386448466 creator A5083857025 @default.
- W4386448466 creator A5091003078 @default.
- W4386448466 date "2023-09-05" @default.
- W4386448466 modified "2023-09-26" @default.
- W4386448466 title "Applications of Data Characteristic AI-assisted Raman Spectroscopy in Pathological Classification" @default.
- W4386448466 cites W2017044153 @default.
- W4386448466 cites W2048719990 @default.
- W4386448466 cites W2086247612 @default.
- W4386448466 cites W2097358067 @default.
- W4386448466 cites W2124216274 @default.
- W4386448466 cites W2137871970 @default.
- W4386448466 cites W2324855040 @default.
- W4386448466 cites W2324914261 @default.
- W4386448466 cites W2335004929 @default.
- W4386448466 cites W2752532133 @default.
- W4386448466 cites W2755029307 @default.
- W4386448466 cites W2755197094 @default.
- W4386448466 cites W2889326414 @default.
- W4386448466 cites W2904840918 @default.
- W4386448466 cites W2911514609 @default.
- W4386448466 cites W2914001277 @default.
- W4386448466 cites W2953468357 @default.
- W4386448466 cites W2965546913 @default.
- W4386448466 cites W2982482221 @default.
- W4386448466 cites W2997610855 @default.
- W4386448466 cites W2999277653 @default.
- W4386448466 cites W3001433962 @default.
- W4386448466 cites W3015428699 @default.
- W4386448466 cites W3036229468 @default.
- W4386448466 cites W3093633048 @default.
- W4386448466 cites W3158186962 @default.
- W4386448466 cites W3172733547 @default.
- W4386448466 cites W3184113492 @default.
- W4386448466 cites W3187096419 @default.
- W4386448466 cites W3217181462 @default.
- W4386448466 cites W4200209221 @default.
- W4386448466 cites W4288593343 @default.
- W4386448466 cites W4290839712 @default.
- W4386448466 cites W4292869272 @default.
- W4386448466 doi "https://doi.org/10.1101/2023.09.05.23295054" @default.
- W4386448466 hasPublicationYear "2023" @default.
- W4386448466 type Work @default.
- W4386448466 citedByCount "0" @default.
- W4386448466 crossrefType "posted-content" @default.
- W4386448466 hasAuthorship W4386448466A5020769112 @default.
- W4386448466 hasAuthorship W4386448466A5022256556 @default.
- W4386448466 hasAuthorship W4386448466A5024316929 @default.
- W4386448466 hasAuthorship W4386448466A5024338716 @default.
- W4386448466 hasAuthorship W4386448466A5029072614 @default.
- W4386448466 hasAuthorship W4386448466A5036964506 @default.
- W4386448466 hasAuthorship W4386448466A5040899817 @default.
- W4386448466 hasAuthorship W4386448466A5048379858 @default.
- W4386448466 hasAuthorship W4386448466A5052812929 @default.
- W4386448466 hasAuthorship W4386448466A5056337166 @default.
- W4386448466 hasAuthorship W4386448466A5058278009 @default.
- W4386448466 hasAuthorship W4386448466A5059845740 @default.
- W4386448466 hasAuthorship W4386448466A5067010958 @default.
- W4386448466 hasAuthorship W4386448466A5067974430 @default.
- W4386448466 hasAuthorship W4386448466A5082230753 @default.
- W4386448466 hasAuthorship W4386448466A5083857025 @default.
- W4386448466 hasAuthorship W4386448466A5091003078 @default.
- W4386448466 hasBestOaLocation W43864484661 @default.
- W4386448466 hasConcept C119857082 @default.
- W4386448466 hasConcept C120665830 @default.
- W4386448466 hasConcept C121332964 @default.
- W4386448466 hasConcept C12267149 @default.
- W4386448466 hasConcept C153180895 @default.
- W4386448466 hasConcept C154945302 @default.
- W4386448466 hasConcept C27438332 @default.
- W4386448466 hasConcept C40003534 @default.
- W4386448466 hasConcept C41008148 @default.
- W4386448466 hasConcept C58471807 @default.
- W4386448466 hasConceptScore W4386448466C119857082 @default.
- W4386448466 hasConceptScore W4386448466C120665830 @default.
- W4386448466 hasConceptScore W4386448466C121332964 @default.
- W4386448466 hasConceptScore W4386448466C12267149 @default.
- W4386448466 hasConceptScore W4386448466C153180895 @default.
- W4386448466 hasConceptScore W4386448466C154945302 @default.
- W4386448466 hasConceptScore W4386448466C27438332 @default.
- W4386448466 hasConceptScore W4386448466C40003534 @default.
- W4386448466 hasConceptScore W4386448466C41008148 @default.
- W4386448466 hasConceptScore W4386448466C58471807 @default.
- W4386448466 hasLocation W43864484661 @default.