Detector location selection based on VIP analysis in near-infrared detection of dural hematoma

Abstract

Detection of dural hematoma based on multi-channel near-infrared differential absorbance has the advantages of rapid and non-invasive detection. The location and number of detectors around the light source are critical for reducing the pathological characteristics of the prediction model on dural hematoma degree. Therefore, rational selection of detector numbers and their distances from the light source is very important. In this paper, a detector position screening method based on Variable Importance in the Projection (VIP) analysis is proposed. A preliminary modeling based on Partial Least Squares method (PLS) for the prediction of dural position was established using light absorbance information from 30 detectors located 2.0-5.0 cm from the light source with a 0.1 cm interval. The mean relative error (MRE) of the dural position prediction model was 4.08%. After VIP analysis, the number of detectors was reduced from 30 to 4 and the MRE of the dural position prediction was reduced from 4.08% to 2.06% after the reduction in detector numbers. The prediction model after VIP detector screening still showed good prediction of the epidural position. This study provided a new approach and important reference on the selection of detector location in near-infrared dural hematoma detection.

Effects and prediction of nonpoint source pollution on the structure of aquatic food webs

“…Variable importance in the project (VIP) is an indicator obtained during the calculation of PLSR, which can be used to measure the importance of the independent variable to the dependent variable. The VIP of the independent variable is greater than 1, indicating that the independent variable plays a more important role; when the VIP value is between 0.5 and 1, the explanatory effect of the independent variable is not obvious, whereas when VIP is less than 0.5, the independent variable has little explanatory role for the dependent variable (Afanador, Tran, & Buydens, 2013; Hu et al, 2018; Sun et al, 2018). The calculation method is as follows: Among them, p is the number of independent variables, m is the number of components extracted from the original variables by the partial least squares method, T h represents the h th component and R ( Y , T h ) represents the explanatory power of component T h to the dependent variable Y , which is equal to the square of the correlation coefficient between the two; w hj is the j th component of the axis w h , and w h is the eigenvector of the .…”

“…The VIP of the independent variable is greater than 1, indicating that the independent variable plays a more important role; when the VIP value is between 0.5 and 1, the explanatory effect of the independent variable is not obvious, whereas when VIP is less than 0.5, the independent variable has little explanatory role for the dependent variable (Afanador, Tran, & Buydens, 2013;Hu et al, 2018;Sun et al, 2018).…”

Extrapolation study for determining the time since injury in a rat subcutaneous hematoma model utilizing ATR-FTIR spectroscopy

“…[16][17][18] Furthermore, infrared spectroscopy is frequently utilised to detect skin lesions and associated illnesses, [19][20][21] whereas near-infrared spectroscopy has proven effective in identifying intracranial hematomas. [22][23][24] Currently, the utilization of FTIR in forensics is mostly focused on distinguishing and identifying body uids, species and postmortem interval prediction, cause of death, and biochemical changes in postmortem tissues. 25 The kinds of molecules and reactions vary in the process of wound healing, and these differences are captured by the spectrum to provide specic characteristic spectral peaks that can be used to identify and quantify the high specicity of infrared absorption spectra for molecules.…”

Open craniocerebral hematoma imaging based on near-infrared spectroscopy

“…Compared with NIRS traditional imaging methods have higher accuracy, but they are only suitable for use in hospitals because of their high cost, large volume and use of radioactive elements. Therefore NIRS, being non-invasive, portable and of low cost, is more suitable use at a first aid scene [2]. In the 'optical window' band of 650-950 nm, biological tissues exhibit high absorption and low scattering of near-infrared light, meaning that near-infrared light has good penetration to biological tissues situated a few centimeters under the skin, and because of the high hemoglobin concentration in an acute hematoma, compared with endovascular blood, any blood outside the blood vessels absorbs more near-infrared light.…”