Wavelength weightings in machine learning for ovine joint tissue differentiation using diffuse reflectance spectroscopy (DRS)

Abstract

Objective: To investigate the DRS of ovine joint tissue to determine the optimal optical wavelengths for tissue differentiation and relate these wavelengths to the biomolecular composition of tissues. In this study, we combine machine learning with DRS for tissue classification and then look further at the weighting matrix of the classifier to further understand the key differentiating features. Methods: Supervised machine learning was used to analyse DRS data. After normalising the data, dimension reduction was achieved through multiclass Fisher’s linear discriminant analysis (Multiclass FLDA) and classified with linear discriminant analysis (LDA). The classifier was first run with all the tissue types and the wavelength range 190 nm – 1081 nm. We analysed the weighting matrix of the classifier and then ran the classifier again, the first time using the ten highest weighted wavelengths and the second using only the single highest. Our method was applied to a dataset containing ovine joint tissue including cartilage, cortical and subchondral bone, fat, ligament, meniscus, and muscle. Results: It achieved a classification accuracy of 100% using the wavelength 190 nm – 1081 nm (2048 attributes) with an accuracy of 90% being present for 10 attributes with the exception of those with comparable compositions such as ligament and meniscus. An accuracy greater than 70% was achieved using a single wavelength, with the same exceptions. Conclusion: Multiclass FLDA combined with LDA is a viable technique for tissue identification from DRS data. The majority of differentiating features existed within the wavelength ranges 370-470 and 800-1010 nm. Focusing on key spectral regions means that a spectrometer with a narrower range can potentially be used, with less computational power needed for subsequent analysis.

Multimodal feedback systems for smart laser osteotomy: Depth control and tissue differentiation

“…The tissues were classified using support vector machines (SVM). Other machine learning approaches were diffuse reflectance spectroscopy with linear discriminant analysis, [16][17][18] Raman spectroscopy and nearest-mean classifiers, 19 and OCT and convolutional neural networks. 20,21 The utilization of short-pulse (ns-ps-fs) laser ablation systems offers the advantage of generating a localized plasma at the ablation site.…”

Frameworks of wavelength selection in diffuse reflectance spectroscopy for tissue differentiation in orthopedic surgery

“…There has been considerable research into wavelength selection in spectroscopy [22][23][24][25] as well as generic FS algorithms, [26][27][28][29] for which novel approaches have been proposed to process spectral data. For example, a previous study by Gunaratne et al 30 used multiclass Fisher's linear discriminant analysis (LDA) to both select features and classify tissue types in ovine joint tissue specimens for orthopedic applications, achieving 100% accuracy with full DRS data of 2048 wavelengths from 190 to 1081 nm, 90% with the selected 10 wavelengths, and 70% with the selected single wavelength. Fanjul-Vélez et al 18 examined the use of spectral characteristics extraction and principal component analysis (PCA) as a dimensionality reduction technique on DRS measurements from ex vivo porcine specimens, demonstrating specificity and sensitivity values of >98%.…”

“…There has been considerable research into wavelength selection in spectroscopy 22 – 25 as well as generic FS algorithms, 26 – 29 for which novel approaches have been proposed to process spectral data. For example, a previous study by Gunaratne et al 30 . used multiclass Fisher’s linear discriminant analysis (LDA) to both select features and classify tissue types in ovine joint tissue specimens for orthopedic applications, achieving 100% accuracy with full DRS data of 2048 wavelengths from 190 to 1081 nm, 90% with the selected 10 wavelengths, and 70% with the selected single wavelength.…”

Distinguishing tumor from healthy tissue in human liver ex vivo using machine learning and multivariate analysis of diffuse reflectance spectra

“…Machine learning and empirical models, such as multivariate statistical algorithms, have also been used to distinguish between human tumors and surrounding tumor‐free tissues [10–12, 14, 21, 22, 32, 33, 37, 57–61]. The advantage is that no prior knowledge of the absorption and scattering properties of the tissue is required.…”