Grade diagnosis of human glioma using Fourier transform infrared microscopy and artificial neural network

Identification of hepatocellular carcinoma and paracancerous tissue based on the peak area in FTIR microspectroscopy

“…According to a report 48 by Verdonck et al, the peak at 3070 cm À1 corresponds to the Fermi-enhanced overtone of the amide II bands (at 1550 cm À1 ), and the corresponding area in HCC is about 3.24 times that of the adjacent tissues. Moreover, the absorption at 1654 cm À1 and 1548 cm À1 is mainly ascribed to the C]O bond stretching vibrations of amide I and amide II with the C-N bond and C-N-H bond exural vibrations, 26,28 and the proportions in HCC foci are also 1.46 and 1.33 times higher than those of the adjacent tissues, respectively. These phenomena indicate that the level of protein in the foci increased signicantly.…”

“…[10][11][12] It depends on the quantum energy of the infrared radiation, the absorption of which induces a transition between the vibrational states of the molecule. 13 FTIR spectroscopy has been widely applied in various research studies including plants, 14,15 animals, [16][17][18] microorganisms, 19,20 food [21][22][23] and human diseases, [24][25][26] for various types of samples including serum, 27,28 urine, 29,30 cell lines, 31 and tissue sections. 32,33 Although a wide range of biological studies have been covered by FTIR spectroscopy, most of the analyses are based on the full spectrum, peak frequency shi 34 and intensity of the bands, 35,36 the relative ratios [37][38][39] of the vibrating groups and so on, 40 while in this study, we found that the similarity of the full spectrum between the HCC foci and the paracancerous tissue makes it difficult to identify the groups by some machine learning techniques, and hence, the peak areas of the spectra were calculated and selected as the features to perform the classication models of k-nearest neighbor (KNN), random forest (RF) and support vector machine (SVM).…”

Applications of Artificial Intelligence Based on Medical Imaging in Glioma: Current State and Future Challenges

“…Furthermore, the combination of IS with a microscope enables the spatial distribution of proteins, lipids, nucleic acids, and other compounds in tissue samples to be examined. Peng et al (133) used Fourier transform infrared microscopy to study 9360 spectra from the tissue of 77 glioma patients. This study employed artificial neural networks to categorize gliomas (HGG and LGG) with higher than 98% accuracy, specificity, and sensitivity.…”

“…Peng et al. ( 133 ) used Fourier transform infrared microscopy to study 9360 spectra from the tissue of 77 glioma patients. This study employed artificial neural networks to categorize gliomas (HGG and LGG) with higher than 98% accuracy, specificity, and sensitivity.…”

Grade classification of human glioma using a convolutional neural network based on mid‐infrared spectroscopy mapping

“…Here, we emphasize that each unstained slice used for IR interrogation came from a different block. The detailed process is illustrated in Figure S1 in the supplemental document [29]. According to the histopathological diagnosis results, 21 slices were diagnosed with low-grade gliomas (WHO II), including 6 oligodendrogliomas and 15 diffuse astrocytomas, with 14 males and 7 females aged from 10 to 63 years old and with an average age of 38.3 years old.…”