Cytometric fingerprinting and machine learning (CFML): A novel label-free, objective method for routine mastitis screening

Abhishek S. Dhoble, Kelly T. Ryan, Pratik Lahiri, Mu Chen, Xiaoxiao Pang, Felipe Cardoso, Kaustubh Bhalerao

Research output: Contribution to journalArticle

Abstract

Bovine mastitis costs the US dairy industry $2 billion, an average of $200 per cow annually. Mastitis is currently diagnosed based on macroscopic alteration of milk or with a somatic cells count (SCC), which are non-specific markers of infection. Cows that have milk samples with no macroscopic alteration (i.e. clots) with more than 200,000 SCC per mL are classified as experiencing subclinical mastitis. Here, we demonstrate a novel cytometric fingerprinting and machine learning (CFML) toolchain as a label-free, objective, high-throughput microbiological milk quality evaluation method for routine mastitis screening. Milk samples were collected from each quarter of the udder from paired 20 milking Holstein cows. Cytometric fingerprints were immediately obtained along with simultaneous pathological analysis. Cytometric fingerprints largely resembled SCC and unique somatic cytometric fingerprints were observed in response to bacterial pathogens distinct from algal and fungal. To demonstrate applications of machine learning in reducing human intervention in future on-farm automated mastitis screening systems, we trained multiple machine learning models on cytometric fingerprints. Tested classifiers were found to be efficient, scalable and robust in classifying specific pathogen, identifying the lactation stage and pathogen intensity with 99.27%, 100%, and 100% accuracies respectively. Our findings indicate that CFML is sensitive to milk samples from cows experiencing subclinical mastitis spanning distinct types and levels of infections. The use of CFML is hence recommended for rapid, high-throughput mastitis typing. This would assist in the use of data-driven monitoring approaches leading to proper and judicious use of antibiotics in animal agriculture.

Original languageEnglish (US)
Pages (from-to)505-513
Number of pages9
JournalComputers and Electronics in Agriculture
Volume162
DOIs
StatePublished - Jul 2019

Fingerprint

artificial intelligence
milk
mastitis
Learning systems
Labels
Screening
screening
Pathogens
somatic cell count
pathogen
cows
Throughput
pathogens
methodology
Dairies
lactation
udder quarters
Antibiotics
bovine mastitis
milk quality

Keywords

  • Dairy cattle
  • Flow cytometry
  • Machine learning
  • Mastitis
  • Milk

ASJC Scopus subject areas

  • Forestry
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

Cytometric fingerprinting and machine learning (CFML) : A novel label-free, objective method for routine mastitis screening. / Dhoble, Abhishek S.; Ryan, Kelly T.; Lahiri, Pratik; Chen, Mu; Pang, Xiaoxiao; Cardoso, Felipe; Bhalerao, Kaustubh.

In: Computers and Electronics in Agriculture, Vol. 162, 07.2019, p. 505-513.

Research output: Contribution to journalArticle

@article{b319923289a74df8a28380dbab115f48,
title = "Cytometric fingerprinting and machine learning (CFML): A novel label-free, objective method for routine mastitis screening",
abstract = "Bovine mastitis costs the US dairy industry $2 billion, an average of $200 per cow annually. Mastitis is currently diagnosed based on macroscopic alteration of milk or with a somatic cells count (SCC), which are non-specific markers of infection. Cows that have milk samples with no macroscopic alteration (i.e. clots) with more than 200,000 SCC per mL are classified as experiencing subclinical mastitis. Here, we demonstrate a novel cytometric fingerprinting and machine learning (CFML) toolchain as a label-free, objective, high-throughput microbiological milk quality evaluation method for routine mastitis screening. Milk samples were collected from each quarter of the udder from paired 20 milking Holstein cows. Cytometric fingerprints were immediately obtained along with simultaneous pathological analysis. Cytometric fingerprints largely resembled SCC and unique somatic cytometric fingerprints were observed in response to bacterial pathogens distinct from algal and fungal. To demonstrate applications of machine learning in reducing human intervention in future on-farm automated mastitis screening systems, we trained multiple machine learning models on cytometric fingerprints. Tested classifiers were found to be efficient, scalable and robust in classifying specific pathogen, identifying the lactation stage and pathogen intensity with 99.27{\%}, 100{\%}, and 100{\%} accuracies respectively. Our findings indicate that CFML is sensitive to milk samples from cows experiencing subclinical mastitis spanning distinct types and levels of infections. The use of CFML is hence recommended for rapid, high-throughput mastitis typing. This would assist in the use of data-driven monitoring approaches leading to proper and judicious use of antibiotics in animal agriculture.",
keywords = "Dairy cattle, Flow cytometry, Machine learning, Mastitis, Milk",
author = "Dhoble, {Abhishek S.} and Ryan, {Kelly T.} and Pratik Lahiri and Mu Chen and Xiaoxiao Pang and Felipe Cardoso and Kaustubh Bhalerao",
year = "2019",
month = "7",
doi = "10.1016/j.compag.2019.04.029",
language = "English (US)",
volume = "162",
pages = "505--513",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

TY - JOUR

T1 - Cytometric fingerprinting and machine learning (CFML)

T2 - A novel label-free, objective method for routine mastitis screening

AU - Dhoble, Abhishek S.

AU - Ryan, Kelly T.

AU - Lahiri, Pratik

AU - Chen, Mu

AU - Pang, Xiaoxiao

AU - Cardoso, Felipe

AU - Bhalerao, Kaustubh

PY - 2019/7

Y1 - 2019/7

N2 - Bovine mastitis costs the US dairy industry $2 billion, an average of $200 per cow annually. Mastitis is currently diagnosed based on macroscopic alteration of milk or with a somatic cells count (SCC), which are non-specific markers of infection. Cows that have milk samples with no macroscopic alteration (i.e. clots) with more than 200,000 SCC per mL are classified as experiencing subclinical mastitis. Here, we demonstrate a novel cytometric fingerprinting and machine learning (CFML) toolchain as a label-free, objective, high-throughput microbiological milk quality evaluation method for routine mastitis screening. Milk samples were collected from each quarter of the udder from paired 20 milking Holstein cows. Cytometric fingerprints were immediately obtained along with simultaneous pathological analysis. Cytometric fingerprints largely resembled SCC and unique somatic cytometric fingerprints were observed in response to bacterial pathogens distinct from algal and fungal. To demonstrate applications of machine learning in reducing human intervention in future on-farm automated mastitis screening systems, we trained multiple machine learning models on cytometric fingerprints. Tested classifiers were found to be efficient, scalable and robust in classifying specific pathogen, identifying the lactation stage and pathogen intensity with 99.27%, 100%, and 100% accuracies respectively. Our findings indicate that CFML is sensitive to milk samples from cows experiencing subclinical mastitis spanning distinct types and levels of infections. The use of CFML is hence recommended for rapid, high-throughput mastitis typing. This would assist in the use of data-driven monitoring approaches leading to proper and judicious use of antibiotics in animal agriculture.

AB - Bovine mastitis costs the US dairy industry $2 billion, an average of $200 per cow annually. Mastitis is currently diagnosed based on macroscopic alteration of milk or with a somatic cells count (SCC), which are non-specific markers of infection. Cows that have milk samples with no macroscopic alteration (i.e. clots) with more than 200,000 SCC per mL are classified as experiencing subclinical mastitis. Here, we demonstrate a novel cytometric fingerprinting and machine learning (CFML) toolchain as a label-free, objective, high-throughput microbiological milk quality evaluation method for routine mastitis screening. Milk samples were collected from each quarter of the udder from paired 20 milking Holstein cows. Cytometric fingerprints were immediately obtained along with simultaneous pathological analysis. Cytometric fingerprints largely resembled SCC and unique somatic cytometric fingerprints were observed in response to bacterial pathogens distinct from algal and fungal. To demonstrate applications of machine learning in reducing human intervention in future on-farm automated mastitis screening systems, we trained multiple machine learning models on cytometric fingerprints. Tested classifiers were found to be efficient, scalable and robust in classifying specific pathogen, identifying the lactation stage and pathogen intensity with 99.27%, 100%, and 100% accuracies respectively. Our findings indicate that CFML is sensitive to milk samples from cows experiencing subclinical mastitis spanning distinct types and levels of infections. The use of CFML is hence recommended for rapid, high-throughput mastitis typing. This would assist in the use of data-driven monitoring approaches leading to proper and judicious use of antibiotics in animal agriculture.

KW - Dairy cattle

KW - Flow cytometry

KW - Machine learning

KW - Mastitis

KW - Milk

UR - http://www.scopus.com/inward/record.url?scp=85065094672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065094672&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2019.04.029

DO - 10.1016/j.compag.2019.04.029

M3 - Article

AN - SCOPUS:85065094672

VL - 162

SP - 505

EP - 513

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

ER -