Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography

Abstract

Infrared thermography (IRT) was applied as a potentially useful tool in the detection of pregnancy in equids, especially native or wildlife. IRT measures heat emission from the body surface, which increases with the progression of pregnancy as blood flow and metabolic activity in the uterine and fetal tissues increase. Conventional IRT imaging is promising; however, with specific limitations considered, this study aimed to develop novel digital processing methods for thermal images of pregnant mares to detect pregnancy earlier with higher accuracy. In the current study, 40 mares were divided into non-pregnant and pregnant groups and imaged using IRT. Thermal images were transformed into four color models (RGB, YUV, YIQ, HSB) and 10 color components were separated. From each color component, features of image texture were obtained using Histogram Statistics and Grey-Level Run-Length Matrix algorithms. The most informative color/feature combinations were selected for further investigation, and the accuracy of pregnancy detection was calculated. The image texture features in the RGB and YIQ color models reflecting increased heterogeneity of image texture seem to be applicable as potential indicators of pregnancy. Their application in IRT-based pregnancy detection in mares allows for earlier recognition of pregnant mares with higher accuracy than the conventional IRT imaging technique.

Keywords: color model; digital image processing; mare; surface temperature; texture analysis.

Figure 1

Thermal image processing for the analysis of image texture. Image acquisition, white light (A,A’) and thermal image (B,B’); segmentation of the region of interest (ROI) (B,B’); transformation to color models (C–N’): RGB color model (C–E’), YUV color model (F–H’), YIQ color model (I–K’), and HSB color model (L–N’). Subfigures (A–N) and (A’–N’) represent non-pregnant and pregnant mares, respectively.

Figure 2

Features of (A) Histogram Statistics and (B) Gray Level Co-occurrence Matrix for each examined color component found not to be significantly different between months in the non-pregnant group. R—Red component in the RGB color model; G—Green component in the RGB color model; B—Blue component in the RGB color model; Y—Brightness component in the YUV/YIQ/HSB color models; U—U-component in the YUV color model; V—V-component in the YUV color model; I—I-component in the YIQ color model; Q—Q-component in the YIQ color model; H—Hue component in the HSB color model; S—Saturation component in the HSB color model. Skewness—skewness coefficient; Perc01, Perc10, Perc50, Perc90, Perc99—percentiles; Domn01, Domn10—dominants; Maxm01, Maxm10—maximum of moments; AngScMom—angular second moment/energy; Correlat—correlation; SumOfSqs—sum of squares; InvDefMom—inverse different moment/homogeneity; SumAverg—summation mean; SumVarnc—summation variance; SumEntrp—summation entropy; DifVarnc—differential variance; DifEntrp—differential entropy.

Figure 3

Features of (A) Histogram Statistics and (B) Gray Level Co-occurrence Matrix for each examined color component found to be significantly different between non-pregnant and pregnant groups from a given (numbered) month as compared to the end of pregnancy. R—Red component in the RGB color model; G—Green component in the RGB color model; B—Blue component in the RGB color model; Y—Brightness component in the YUV/YIQ/HSB color models; U—U-component in the YUV color model; V—V-component in the YUV color model; I—I-component in the YIQ color model; Q—Q-component in the YIQ color model; H—Hue component in the HSB color model; S—Saturation component in the HSB color model. Skewness—skewness coefficient; Perc01, Perc10, Perc50, Perc90, Perc99—percentiles; Domn01, Domn10—dominants; Maxm01, Maxm10—maximum of moments; AngScMom—angular second moment/energy; Correlat—correlation; SumOfSqs—sum of squares; InvDefMom—inverse different moment/homogeneity; SumAverg—summation mean; SumVarnc—summation variance; SumEntrp—summation entropy; DifVarnc—differential variance; DifEntrp—differential entropy.

Figure 4

Features of (A) Histogram Statistics and (B) Gray Level Co-occurrence Matrix for each examined color component found to be significantly increasing (In) or decreasing (De) with the progression of pregnancy. R—Red component in the RGB color model; G—Green component in the RGB color model; B—Blue component in the RGB color model; Y—Brightness component in the YUV/YIQ/HSB color models; U—U-component in the YUV color model; V—V-component in the YUV color model; I—I-component in the YIQ color model; Q—Q-component in the YIQ color model; H—Hue component in the HSB color model; S—Saturation component in the HSB color model. Skewness—skewness coefficient; Perc01, Perc10, Perc50, Perc90, Perc99—percentiles; Domn01, Domn10—dominants; Maxm01, Maxm10—maximum of moments; AngScMom—angular second moment/energy; Correlat—correlation; SumOfSqs—sum of squares; InvDefMom—inverse different moment/homogeneity; SumAverg—summation mean; SumVarnc—summation variance; SumEntrp—summation entropy; DifVarnc—differential variance; DifEntrp—differential entropy.