Texture analysis of B-mode ultrasound images to stage hepatic lipidosis in the dairy cow: A methodological study

Colour Doppler study of blood flow in the portal vein in relation to blood flow in the milk vein, milk yield and body condition of dairy cows during dry period and lactation

In dairy cows, the liver supports the increased nutrient demands of the udder for milk production. Blood flow is key for the transport of these nutrients. This study investigated portal vein blood flow volume (PVBFVol) in relation to daily milk yield (DMY), milk vein blood flow volume (MVBFVol) and body condition parameters of high-producing dairy cows, starting from late lactation, throughout dry period, and consecutive early lactation. Seventeen repeated examinations were performed on 19 Holstein cows and 313 measurement days were finally included. Vein morphology and blood flow were examined via B-mode and spectral Doppler (triplex) ultrasonography, respectively. Body condition parameters recorded were body condition score (BCS), backfat thickness (BFT) measurement with ultrasonography, heart girth circumference (HG) and withers height (WH). Longitudinal relationship of PVBFVol with MVBFVol, DMY, BCS, BFT, HG and WH was analyzed with linear mixed models, with random intercept effects, using restricted cubic splines. A significant increase of 8.28% (p < 0.01) in PVBFVol appeared for every 1 L/min increase in MVBFVol in the univariable model. PVBFVol presented a significant negative association with BCS (p < 0.01) and BFT (p = 0.02), while interaction with production stage was significant, too. PVBFVol significantly increased by 0.38% (p = 0.04) for every 1 kg increase in DMY in the multivariable model. In conclusion, the increased PVBFVol during lactation accompanies the escalation in metabolic activity of the liver and the increased blood circulation through the udder, coping with the udder's escalating nutrient demands for milk synthesis.

Associations between the detailed milk mineral profile, milk composition, and metabolic status in Holstein cows

The causes of variation in the milk mineral profile of dairy cattle during the first phase of lactation were studied under the hypothesis that the milk mineral profile partially reflects the animals' metabolic status. Correlations between the minerals and the main milk constituents (i.e., protein, fat, and lactose percentages), and their associations with the cows' metabolic status indicators were explored. The metabolic status indicators (MET) that we used were blood energy-protein metabolites [nonesterified fatty acids, β-hydroxybutyrate (BHB), glucose, cholesterol, creatinine, and urea], and liver ultrasound measurements (predicted triacylglycerol liver content, portal vein area, portal vein diameter and liver depth). Milk and blood samples, and ultrasound measurements were taken from 295 Holstein cows belonging to 2 herds and in the first 120 d in milk (DIM). Milk mineral contents were determined by ICP-OES; these were considered the response variable and analyzed through a mixed model which included DIM, parity, milk yield, and MET as fixed effects, and the herd/date as a random effect. The MET traits were divided in tertiles. The results showed that milk protein was positively associated with body condition score (BCS) and glucose, and negatively associated with BHB blood content; milk fat was positively associated with BHB content; milk lactose was positively associated with BCS; and Ca, P, K and S were the minerals with the greatest number of associations with the cows' energy indicators, particularly BCS, predicted triacylglycerol liver content, glucose, BHB and urea. We conclude that the protein, fat, lactose, and mineral contents of milk partially reflect the metabolic adaptation of cows during lactation and within 120 DIM. Variations in the milk mineral profile were consistent with changes in the major milk constituents and the metabolic status of cows.

Artificial intelligence in veterinary diagnostic imaging: A literature review

Artificial intelligence in veterinary medicine is an emerging field. Machine learning, a subfield of artificial intelligence, allows computer programs to analyze large imaging datasets and learn to perform tasks relevant to veterinary diagnostic imaging. This review summarizes the small, yet growing body of artificial intelligence literature in veterinary imaging, provides necessary background to understand these papers, and provides author commentary on the state of the field. To date, less than 40 peer-reviewed publications have utilized machine learning to perform imaging-associated tasks across multiple anatomic regions in veterinary clinical and biomedical research. Major challenges in this field include collection and cleaning of sufficient image data, selection of high-quality ground truth labels, formation of relationships between veterinary and machine learning professionals, and closure of the gap between academic uses of artificial intelligence and currently available commercial products. Further development of artificial intelligence has the potential to help meet the growing need for radiological services through applications in workflow, quality control, and image interpretation for both general practitioners and radiologists.

Hemato-biochemical and ultrasonographic evaluation of hepatic lipidosis in dairy buffaloes

Around 60% dairy animals developed moderate to severe hepatic lipidosis at the time of parturition or during early lactation stage. Most of clinician suspect the hepatic lipidosis during above time window only. However, negative energy balance or feeding of high concentrate diet can lead to hepatic lipidosis at any phase of life. The aim of the present study was to evaluate the potential for diagnosis of hepatic lipidosis by means of hemato-biochemical parameters and ultrasonography of the liver at any stage of life. Here, ultrasonographic back fat thickness measurement was correlated with ultrasonographic features of hepatic lipidosis. A total 60 buffaloes were included under the study and sampled for hematological and biochemical parameters. Hematological parameters did not exhibit any significant difference between healthy and hepatic lipidosis-affected buffaloes. Biochemical parameters like beta hydroxy butyric acid, non esterified fatty acid, aspartate amino transferase, gamma glutamyl transferase and alkaline phosphatase revealed a significant increase, while triglyceride, cholesterol, and glucose declined significantly in hepatic lipidosis-affected buffaloes. Total protein, albumin, and total bilirubin levels did not exhibit any significant difference. Based on ultrasonographic findings, the hepatic lipidosis-affected buffaloes were further sub divided into mild, moderate, and severe groups. Portal vein diameter and depth of portal vein were also estimated in current study. Ultrasonographic examination could diagnose 53.33% hepatic lipidosis cases in buffaloes. Among it, 37.50% buffalo had mild hepatic lipidosis, 33.33% had moderate hepatic lipidosis, and 29.16% had severe hepatic lipidosis. Depth of portal vein significantly increased in hepatic lipidosis cases. However, portal vein diameter exhibited a non-significant difference in mild, moderate, and severe groups of hepatic lipidosis. Back fat thickness also revealed a non-significant difference in mild, moderate, and severe hepatic lipidosis. Above study indicate that B mode ultrasonography of the liver can be employed to differentiate various grades of hepatic lipidosis in buffaloes. Biochemical parameters like NEFA, BHBA, AST, GGT, ALP, TG, cholesterol, and glucose can be helpful to screen the hepatic lipidosis at farm level.

Associations between Milk Fatty Acid Profile and Body Condition Score, Ultrasound Hepatic Measurements and Blood Metabolites in Holstein Cows

Dairy cows have high incidences of metabolic disturbances, which often lead to disease, having a subsequent significant impact on productivity and reproductive performance. As the milk fatty acid (FA) profile represents a fingerprint of the cow’s nutritional and metabolic status, it could be a suitable indicator of metabolic status at the cow level. In this study, we obtained milk FA profile and a set of metabolic indicators (body condition score, ultrasound liver measurements, and 29 hematochemical parameters) from 297 Holstein–Friesian cows. First, we applied a multivariate factor analysis to detect latent structure among the milk FAs. We then explored the associations between these new synthetic variables and the morphometric, ultrasonographic and hematic indicators of immune and metabolic status. Significant associations were exhibited by the odd-chain FAs, which were inversely associated with β-hydroxybutyrate and ceruloplasmin, and positively associated with glucose, albumin, and γ-glutamyl transferase. Short-chain FAs were inversely related to predicted triacylglycerol liver content. Rumen biohydrogenation intermediates were associated with glucose, cholesterol, and albumin. These results offer new insights into the potential use of milk FAs as indicators of variations in energy and nutritional metabolism in early lactating dairy cows.

A Machine Learning-Based Approach for Classification of Focal Splenic Lesions Based on Their CT Features

The aim of the study was to describe the CT features of focal splenic lesions (FSLs) in dogs in order to predict lesion histotype. Dogs that underwent a CT scan and had a FSL diagnosis by cytology or histopathology were retrospectively included in the study. For the statistical analysis the cases were divided into four groups, based on the results of cytopatholoy or hystopathology, namely: nodular hyperplasia (NH), other benign lesions (OBLs), sarcoma (SA), round cell tumour (RCT). Several qualitative and quantitative CT features were described for each case. The relationship occurring between each individual CT feature and the histopathological groups was explred by means of c chi-square test for the count data and by means of Kruskal-Wallis or ANOVA for the continuous data. Furthermore, the main features of each group were described using factorial discriminant analysis, and a decision tree for lesion classification was then developed. Sarcomas were characterised by large dimensions, a cystic appearance and an overall low post contrast-enhancement. NH and OBLs were characterised by small dimensions, a solid appearance and a high post-contrast enhancement. OBLs showed higher post-contrast values than NH. Lastly, RCTs did not exhibit any distinctive CT features. The proposed decision tree had a high accuracy for the classification of SA (0.89) and a moderate accuracy for the classification of OBLs and NH (0.79), whereas it was unable to classify RCTs. The results of the factorial analysis and the proposed decision tree could help the clinician in classifying FSLs based on their CT features. A definitive FSL diagnosis can only be obtained by microscopic examination of the spleen.

Associations between ultrasound measurements and hematochemical parameters for the assessment of liver metabolic status in Holstein-Friesian cows

Metabolic disorders, including hepatic lipidosis and ketosis, severely affect animal health status and welfare with a large economic burden in dairy herds. The gold standard for diagnosing hepatic lipidosis is the liver biopsy, which is impractical and invasive for the screening at farm level. Ultrasound (US) imaging is a promising technique for identifying liver dysfunction, but standardized specifications in physiological conditions are needed. Herein, we described the features of four US measurements, namely the liver predicted triacylglycerol (pTAG) content, liver depth (LD), and portal vein area (PVA) and depth (PVD) and we investigated their associations with a set of hematochemical (HC) indicators in 342 clinically healthy Holstein Friesian dairy cows. Liver pTAG content was negatively associated with hematocrit and positively with globulin, whereas PVA was negatively associated with thiol group levels, and LD positively with ceruloplasmin. We found significant interactions between some HC parameters and parity: in particular, creatinine, thiol groups and globulin for PVA, and aspartate aminotransferase, paraoxonase and ceruloplasmin for PVD. This study offers new insights on variations in liver function occurring after calving and pave the way for the potential use of minimally invasive techniques for prompt detection of metabolic disorders in dairy herds.

Application of Ultrasound Images Texture Analysis for the Estimation of Intramuscular Fat Content in the Longissimus Thoracis Muscle of Beef Cattle after Slaughter: A Methodological Study

Simple Summary

Fat content in the muscle mass (IMF) is one of the most important characteristics influencing the aroma, tenderness, and juiciness of the meat and therefore has high importance for both commercialization purposes and consumers. However, IMF determination currently relies on visual inspection, which is a subjective and inconsistent technique. The aim of the present study is the elaboration of a procedure capable of predicting IMF% in beef carcasses using ultrasound imaging texture analysis. Ultrasound images taken on meat samples were compared to meat composition measured by chemical extraction. Determination coefficient between the two techniques was R² = 0.76, while Receiver Operating Characteristic analysis showed a sensitivity of 88% and a specificity of 90%. The results therefore suggest that the described procedure is expected to determine IMF% in muscle with good accuracy. Ultrasound imaging could be applied in routine beef grading practices. This may help to solve the issues related to subjectivity and leave to the operator only imaging acquisition. Better consistency in beef products could enhance consumers’ satisfaction and commercial standardization programs.

Abstract

Intramuscular fat (IMF) is a major trait in the evaluation of beef meat, but its determination is subjective and inconsistent and still relies on visual inspection. This research objective was a method to predict IMF% from beef meat using ultrasound (US) imaging texture analysis. US images were performed on the longissimus thoracis muscle of 27 Charolaise heifers. Cuts from the 12th to 13th ribs were scanned. The lipid content of the muscle samples was determined with the petrol ether (Randall) extraction method. A stepwise linear discriminant analysis was used to screen US texture parameters. IMF% measured by chemical extraction (IMFqa) was the dependent variable and the results of the texture analysis were the explanatory variables. The model highlighted seven parameters, as a predictive and a multiple regression equation was created. Prediction of IMF content (IMFpred) was then validated using IMFqa as ground truth. Determination coefficient between IMFqa and IMFpred was R² = 0.76, while the ROC analysis showing a sensitivity of 88% and a specificity of 90%. Bland-Altman plot upper and lower limit were +1.34 and −1.42, respectively (±1.96 SD), with a mean of −0.04. The results from the present study therefore suggest that prediction of IMF content in muscle mass by US texture analysis is possible.

A retrospective study on transabdominal ultrasound measurements of the rumen wall thickness to evaluate chronic rumen acidosis in beef cattle

BACKGROUND

Chronic and subacute rumen acidosis are economically important in the beef industry. The aim of this study was to evaluate the potential suitability of the transabdominal ultrasonographic examination of the ruminal wall to diagnose chronic rumen acidosis in beef cattle compared to direct measurement of ruminal pH, as a fast non-invasive tool to be used in field condition. Ultrasonographic examination of the rumen was conducted in 478 beef cattle before rumenocentesis (chronic rumen acidosis group = pH ≤ 5.8; healthy group = pH ≥ 5.9). Rumen wall ultrasound measurements included rumen wall thickness (RWT) and rumen mucosa and submucosa thickness (RMST).

RESULTS

The Analysis of Variance showed the high significant effect of the pH class for RWT and RMST (P < 0.001). Spearman RANK correlation analysis showed interaction between rumen pH and RWT (- 0.71; P < 0.0001) and RMST (- 0.75; P < 0.0001). A significant Spearman's correlations were found between volatile fatty acids (VFA) and RWT and RMST. The differentiation efficiency of RWT between healthy and chronic rumen acidosis groups, as a result of the receiver operator curve (ROC) analysis, was quite good with an area under the receiver operator curve (AUROC) of 0.88: P < 0.0001; 95% CI: 0.83-0.98. Using a cut-off value of > 8.2 mm. The differentiation efficiency of RMST between healthy and chronic rumen acidosis groups, as a result of ROC curve analysis, was good with an AUROC of 0.90: p < 0.0001; 95% CI: 0.85-0.94. Using a cut-off value of > 5.3 mm.

CONCLUSIONS

In this study, the thickening of RWT and RMST is correlated with the changes of ruminal pH. Transabdominal rumen ultrasound has the potential to become a powerful diagnostic tool useful to identify fattening bulls affected by chronic rumen acidosis.

Application of texture analysis of b-mode ultrasound images for the quantification and prediction of intramuscular fat in living beef cattle: A methodological study

Intramuscular fat (IMF) contributes significantly to the aroma and tenderness of the meat, therefore playing a key role in quality determination. Yet, IMF determination methods rely on visual inspection or on fat extraction from meat samples after animals' slaughter. The aim of this methodological study was the elaboration of a process capable of predicting IMF% using real-time ultrasound (RTU) images in live beef cattle. The longissimus dorsi (LD) muscle of 26 Charolaise heifers was investigated. In vivo ultrasound images were taken and texture analysis was performed. One week after the animals' slaughter, the whole twelfth rib cut was collected, and IMF% was determined by extraction with petrol ether (Randall) method. Animals were divided in 3 groups depending on their mean lipid content percentage in 100 g meat (Group 1: IMF ≤ 4.24%; Group 2: 4.25% ≤ IMF ≤ 5.75%; Group 3: IMF ≥ 5.76%). Texture parameters were selected by a stepwise linear discriminant analysis using IMF% measured by chemical extraction (IMFqa) as the dependent variable, and the results of the texture analysis as explanatory variables. 6 variables were found predictive and molded into a multiple regression equation, this equation was then validated using IMFqa as ground truth. A high linear correlation between IMFqa and IMFpred was evident (r² = 0.8504), ROC analysis perfomed on IMFpred comparing it to IMFqa showed a sensitivity of 80% and a specificity of 93.7%, while results from the Bland-Altman plot were ± 1.96 (±1.11SD).

Ultrasonographic alterations of bovine claws sole soft tissues associated with claw horn disruption lesions, body condition score and locomotion score in Holstein dairy cows

Claw Horn Disruption Lesions (CHDL) negatively affect the sole soft tissue structures located beneath the sole horn. The aim of the present study was to investigate the effect of CHDL on sole soft tissues by ultrasound means, correlating Body condition score (BCS), locomotion score and CHDL with ultrasonography evaluations of sole soft tissues in Holstein dairy cows. 100 Holstein dairy cows were enrolled in the study. BCS and locomotion score were assessed and functional trimming was performed on all animals. 84 healthy claws and 174 claws with solely one CHDL per claw were evaluated both clinically and with ultrasound, and CHDL were identified and recorded. Sole soft tissues thickness (mm) and echogenicity was determined, and ultrasonographic alterations, related to CHDL presence, where measured long their vertical (L1) and horizontal (L2) axis. Statistically significant (P < .001) differences were found in echogenicity between healthy claws and all the affected ones, with the healthy ones being mainly anechoic. Statistically significant (P < .001) differences were found for vertical (L1) and horizontal (L2) axis measures between the diverse CHDL, confirming ultrasonography as a useful tool to distinguish lesions and their extension by measuring L1 and L2. BCS had an influence both on sole soft tissues ultrasonographic appearance and on CHDL insurgency. These results confirm ultrasonography as a reliable tool for detecting an increase in sole soft tissues echogenicity, that was seen to occur with CHDL insurgency, and in determining lesion extension.

A methodological approach for deep learning to distinguish between meningiomas and gliomas on canine MR-images

Background

Distinguishing between meningeal-based and intra-axial lesions by means of magnetic resonance (MR) imaging findings may occasionally be challenging. Meningiomas and gliomas account for most of the total primary brain neoplasms in dogs, and differentiating between these two forms is mandatory in choosing the correct therapy. The aims of the present study are: 1) to determine the accuracy of a deep convolutional neural network (CNN, GoogleNet) in discriminating between meningiomas and gliomas in pre- and post-contrast T1 images and T2 images; 2) to develop an image classifier, based on the combination of CNN and MRI sequence displaying the highest accuracy, to predict whether a lesion is a meningioma or a glioma.

Results

Eighty cases with a final diagnosis of meningioma (n = 56) and glioma (n = 24) from two different institutions were included in the study. A pre-trained CNN was retrained on our data through a process called transfer learning. To evaluate CNN accuracy in the different imaging sequences, the dataset was divided into a training, a validation and a test set. The accuracy of the CNN was calculated on the test set. The combination between post-contrast T1 images and CNN was chosen in developing the image classifier (trCNN). Ten images from challenging cases were excluded from the database in order to test trCNN accuracy; the trCNN was trained on the remainder of the dataset of post-contrast T1 images, and correctly classified all the selected images. To compensate for the imbalance between meningiomas and gliomas in the dataset, the Matthews correlation coefficient (MCC) was also calculated. The trCNN showed an accuracy of 94% (MCC = 0.88) on post-contrast T1 images, 91% (MCC = 0.81) on pre-contrast T1-images and 90% (MCC = 0.8) on T2 images.

Conclusions

The developed trCNN could be a reliable tool in distinguishing between different meningiomas and gliomas from MR images.

Ultrasonographic measurement of liver, portal vein, hepatic vein and perivisceral adipose tissue in high-yielding dairy cows with fatty liver during the transition period

The aim of the present study was to evaluate the potential for diagnosis of fatty liver by means of ultrasonographic measurement of liver and perivisceral adipose tissue as an alternative to blood indicators of lipomobilization and liver biopsy in periparturient high-yielding dairy cows. Thirty cows were enrolled and divided into two groups. The evaluation of body condition score (BCS), non-esterified fatty acids (NEFA), β-hydroxybutyrate (BHB), liver and perivisceral adipose tissue ultrasonographic measurement and histological liver lipid content (GdL) was performed at 15 ± 5 d prepartum (T0), 10 ± 2 d postpartum (T1), 30 ± 2 d postpartum (T2) and 50 ± 2 d postpartum (T3). Mesenteric fat thickness (the thickness of the perivascular adipose tissue) measured on ultrasound was shown to be an independent determinant of fatty liver. The cut-off of the ultrasonographic evaluation of the liver may be useful as a first and practical approach in identifying fatty liver. In conclusion, a non-invasive and reliable diagnostic method for predicting the risk of fatty liver in high yielding dairy cows has been demonstrated.