Combined methods of optical spectroscopy and artificial intelligence in the assessment of experimentally induced non-alcoholic fatty liver

Romeu, Eduardo J. Arista; Rivera-Fernández, Josué D.; Roa-Tort, Karen; Valor, A.; Escobedo, Galileo; Fabila-Bustos, Diego A.; Stolik, S.; Rosa, J. de la; Guzmán, Carolina

doi:10.1016/j.cmpb.2020.105777

Cited by 3 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the ex vivo study by Evers et al [39], sensitivity and specificity of 94% were achieved when using a classification and regression tree algorithm based on five tissue parameters obtained using DRS with an extended wavelength range. The analytical model of Farrell et al [56] and Evers et al [39] showed that there is considerably less fat in liver tumors. The overall sensitivity and specificity were 95% and 92%, respectively, in the in vivo study conducted by Tanis et al [41] using the same technique.…”

Section: Discussionmentioning

confidence: 99%

“…Mathematical models, such as semi‐empirical models, the diffusion approximation to the radiative transfer equation and Monte Carlo (MC) methods have been used to derive physiological parameters that characterize the tissue. However, only a few studies have applied DRS in human liver tissue characterization [7, 8, 38–43, 54, 55], and all but two of these previous studies used the standard analytical model derived from diffusion theory proposed by Farrell et al [56]. Evers et al [39] used DRS with an extended wavelength range from 500 to 1600 nm and examined liver specimens immediately after resection from patients with colorectal liver metastases to discriminate tumors from surrounding tissues with a sensitivity and specificity both of 94% and an accuracy of 100% for each patient.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Reistad

Sturesson

2022

Journal of Biophotonics

View full text Add to dashboard Cite

The aim of this work was to evaluate the capability of diffuse reflectance spectroscopy to distinguish malignant liver tissues from surrounding tissues and to determine whether an extended wavelength range (450‐1550 nm) offers any advantages over using the conventional wavelength range. Furthermore, multivariate analysis combined with a machine learning algorithm, either linear discriminant analysis or the more advanced support vector machine, was used to discriminate between and classify freshly excised human liver specimens from 18 patients. Tumors were distinguished from surrounding liver tissues with a sensitivity of 99%, specificity of 100%, classification rate of 100% and a Matthews correlation coefficient of 100% using the extended wavelength range and a combination of principal component analysis and support vector techniques. The results indicate that this technology may be useful in clinical applications for real‐time tissue diagnostics of tumor margins where rapid classification is important.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Reistad

Sturesson

2022

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…Furthermore, hepatic steatosis might be tracked in vivo as shown by Piao et al [40], proving versatility of the method. In combination with artificial intelligence, hepatic steatosis might be diagnosed with high precision [43]. Radio-frequency ablation of human colorectal liver metastases induces necrotic tissues and their presence might be studies using DRS as well [48].…”

Section: Surazynski Et Al / a Methods To Detect Thermal Damage In Bov...mentioning

confidence: 99%

A method to detect thermal damage in bovine liver utilising diffuse reflectance spectroscopy

Surazynski,

Nieminen,

Mäkinen

et al. 2023

BSI

View full text Add to dashboard Cite

When light is illuminated using a broad spectrum and detected without physical contact between source and detector the method is often referred as diffuse reflectance spectroscopy (DRS). Combined with newest computational algorithms, DRS may reach high performance in near future in tissue characterization and pathology. In this study, we show that DRS can be used to automatically differentiate untreated fresh liver tissue from heat-induced and chemically induced tissue denaturation in bovine liver ex vivo. For this, we used a thresholding algorithm that was developed and tested using 10-fold cross validation. Our results indicate that DRS has potential to detect pathological tissue processes that result in tissue injury and ultimately tissue necrosis. The detection of necrosis is important for many medical applications, not least for tissue sampling by biopsy needle, where additional guidance to commonly used ultrasound would be welcome. Furthermore, cancer tissue is prone to necrosis as a result of tissue hypoxia and due to cancer treatments.

show abstract

Artificial Intelligence and Industry 4.0 Across the Continent: How AI and 4.0 are Addressed by Region

Cervantes

Zapata-Jaramillo

2021

Radical Solutions for Digital Transformation in Latin American Universities

View full text Add to dashboard Cite

Combined methods of optical spectroscopy and artificial intelligence in the assessment of experimentally induced non-alcoholic fatty liver

Cited by 3 publications

References 31 publications

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

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

A method to detect thermal damage in bovine liver utilising diffuse reflectance spectroscopy

Artificial Intelligence and Industry 4.0 Across the Continent: How AI and 4.0 are Addressed by Region

Contact Info

Product

Resources

About