Lactoperoxidase potential in diagnosing subclinical mastitis in cows via image processing

Abstract

This report describes how image processing harnessed to multivariate analysis techniques can be used as a bio-analytical tool for mastitis screening in cows using milk samples collected from 48 animals (32 from Jersey, 7 from Gir, and 9 from Guzerat cow breeds), totalizing a dataset of 144 sequential images was collected and analyzed. In this context, this methodology was developed based on the lactoperoxidase activity to assess mastitis using recorded images of a cuvette during a simple experiment and subsequent image treatments with an R statistics platform. The color of the sample changed from white to brown upon its exposure to reagents, which is a consequence of lactoperoxidase enzymatic reaction. Data analysis was performed to extract the channels from the RGB (Red-Green-Blue) color system, where the resulting dataset was evaluated with Principal Component Analysis (PCA), Multiple Linear Regression (MLR), and Second-Order Regression (SO). Interesting results in terms of enzymatic activity correlation (R2 = 0.96 and R2 = 0.98 by MLR and SO, respectively) and of somatic cell count (R2 = 0.97 and R2 = 0.99 by MLR and SO, respectively), important mastitis indicators, were obtained using this simple method. Additionally, potential advantages can be accessed such as quality control of the dairy chain, easier bovine mastitis prognosis, lower cost, analytical frequency, and could serve as an evaluative parameter to verify the health of the mammary gland.

Fig 1. Cuvette image of the milk sample treated.

Example of capture strategy using a common smartphone.

Fig 2. Spots of the region of interest (ROI) for image processing.

Here we denote the 2 ROIs as the blank (left) and sample (right).

Fig 3. LPO calibration curve in units mL^-1.

Calibration curve for lactoperoxidase analysis showing the absorbance vs lactoperoxidase concentration. Adjusted R² = 0.98.

Fig 4. Multivariate data analysis comparing milk treated samples and RGB channels.

Principal Component Analysis (PCA) model biplot of variables in Jersey (J), Gir (GI), and Guzerat (GU) milk samples with autoscaling.

Fig 5. Enzyme activity calibration curve.

Lactoperoxidase analysis showing the predicted activity (y-axis) vs measured activity (x-axis) and the correlation between the proposed method for quantifying lactoperoxidase and the reference method. Adjusted R² = 0.96 by multiple linear regression.

Fig 6. Multiple linear regression for CCS.

Image processing analysis of predicted (RGB) vs. measured CCS. Adjusted R² = 0.97.