A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network
Mastitis is one of the most predominant diseases with a negative impact on ranch products worldwide. It reduces milk production, damages milk quality, increases treatment costs, and even leads to the premature elimination of animals. In addition, failure to take effective measures in time will lead...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/14/5/707 |
| _version_ | 1797264930346369024 |
|---|---|
| author | Xinxin Zhang Yuan Li Yiping Zhang Zhiqiu Yao Wenna Zou Pei Nie Liguo Yang |
| author_facet | Xinxin Zhang Yuan Li Yiping Zhang Zhiqiu Yao Wenna Zou Pei Nie Liguo Yang |
| author_sort | Xinxin Zhang |
| collection | DOAJ |
| description | Mastitis is one of the most predominant diseases with a negative impact on ranch products worldwide. It reduces milk production, damages milk quality, increases treatment costs, and even leads to the premature elimination of animals. In addition, failure to take effective measures in time will lead to widespread disease. The key to reducing the losses caused by mastitis lies in the early detection of the disease. The application of deep learning with powerful feature extraction capability in the medical field is receiving increasing attention. The main purpose of this study was to establish a deep learning network for buffalo quarter-level mastitis detection based on 3054 ultrasound images of udders from 271 buffaloes. Two data sets were generated with thresholds of somatic cell count (SCC) set as 2 × 10<sup>5</sup> cells/mL and 4 × 10<sup>5</sup> cells/mL, respectively. The udders with SCCs less than the threshold value were defined as healthy udders, and otherwise as mastitis-stricken udders. A total of 3054 udder ultrasound images were randomly divided into a training set (70%), a validation set (15%), and a test set (15%). We used the EfficientNet_b3 model with powerful learning capabilities in combination with the convolutional block attention module (CBAM) to train the mastitis detection model. To solve the problem of sample category imbalance, the PolyLoss module was used as the loss function. The training set and validation set were used to develop the mastitis detection model, and the test set was used to evaluate the network’s performance. The results showed that, when the SCC threshold was 2 × 10<sup>5</sup> cells/mL, our established network exhibited an accuracy of 70.02%, a specificity of 77.93%, a sensitivity of 63.11%, and an area under the receiver operating characteristics curve (AUC) of 0.77 on the test set. The classification effect of the model was better when the SCC threshold was 4 × 10<sup>5</sup> cells/mL than when the SCC threshold was 2 × 10<sup>5</sup> cells/mL. Therefore, when SCC ≥ 4 × 10<sup>5</sup> cells/mL was defined as mastitis, our established deep neural network was determined as the most suitable model for farm on-site mastitis detection, and this network model exhibited an accuracy of 75.93%, a specificity of 80.23%, a sensitivity of 70.35%, and AUC 0.83 on the test set. This study established a 1/4 level mastitis detection model which provides a theoretical basis for mastitis detection in buffaloes mostly raised by small farmers lacking mastitis diagnostic conditions in developing countries. |
| first_indexed | 2024-04-25T00:36:43Z |
| format | Article |
| id | doaj.art-a0da81779c7d4b478a592ee16cbea6d9 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-04-25T00:36:43Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-a0da81779c7d4b478a592ee16cbea6d92024-03-12T16:37:59ZengMDPI AGAnimals2076-26152024-02-0114570710.3390/ani14050707A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning NetworkXinxin Zhang0Yuan Li1Yiping Zhang2Zhiqiu Yao3Wenna Zou4Pei Nie5Liguo Yang6National Center for International Research on Animal Genetics, Breeding and Reproduction (NCIRAGBR), Ministry of Science and Technology of the People’s Republic of China, Huazhong Agricultural University, Wuhan 430070, ChinaNational Center for International Research on Animal Genetics, Breeding and Reproduction (NCIRAGBR), Ministry of Science and Technology of the People’s Republic of China, Huazhong Agricultural University, Wuhan 430070, ChinaNational Center for International Research on Animal Genetics, Breeding and Reproduction (NCIRAGBR), Ministry of Science and Technology of the People’s Republic of China, Huazhong Agricultural University, Wuhan 430070, ChinaNational Center for International Research on Animal Genetics, Breeding and Reproduction (NCIRAGBR), Ministry of Science and Technology of the People’s Republic of China, Huazhong Agricultural University, Wuhan 430070, ChinaNational Center for International Research on Animal Genetics, Breeding and Reproduction (NCIRAGBR), Ministry of Science and Technology of the People’s Republic of China, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of Veterinary Medicine, Hunan Agricultural University, Changsha 410128, ChinaNational Center for International Research on Animal Genetics, Breeding and Reproduction (NCIRAGBR), Ministry of Science and Technology of the People’s Republic of China, Huazhong Agricultural University, Wuhan 430070, ChinaMastitis is one of the most predominant diseases with a negative impact on ranch products worldwide. It reduces milk production, damages milk quality, increases treatment costs, and even leads to the premature elimination of animals. In addition, failure to take effective measures in time will lead to widespread disease. The key to reducing the losses caused by mastitis lies in the early detection of the disease. The application of deep learning with powerful feature extraction capability in the medical field is receiving increasing attention. The main purpose of this study was to establish a deep learning network for buffalo quarter-level mastitis detection based on 3054 ultrasound images of udders from 271 buffaloes. Two data sets were generated with thresholds of somatic cell count (SCC) set as 2 × 10<sup>5</sup> cells/mL and 4 × 10<sup>5</sup> cells/mL, respectively. The udders with SCCs less than the threshold value were defined as healthy udders, and otherwise as mastitis-stricken udders. A total of 3054 udder ultrasound images were randomly divided into a training set (70%), a validation set (15%), and a test set (15%). We used the EfficientNet_b3 model with powerful learning capabilities in combination with the convolutional block attention module (CBAM) to train the mastitis detection model. To solve the problem of sample category imbalance, the PolyLoss module was used as the loss function. The training set and validation set were used to develop the mastitis detection model, and the test set was used to evaluate the network’s performance. The results showed that, when the SCC threshold was 2 × 10<sup>5</sup> cells/mL, our established network exhibited an accuracy of 70.02%, a specificity of 77.93%, a sensitivity of 63.11%, and an area under the receiver operating characteristics curve (AUC) of 0.77 on the test set. The classification effect of the model was better when the SCC threshold was 4 × 10<sup>5</sup> cells/mL than when the SCC threshold was 2 × 10<sup>5</sup> cells/mL. Therefore, when SCC ≥ 4 × 10<sup>5</sup> cells/mL was defined as mastitis, our established deep neural network was determined as the most suitable model for farm on-site mastitis detection, and this network model exhibited an accuracy of 75.93%, a specificity of 80.23%, a sensitivity of 70.35%, and AUC 0.83 on the test set. This study established a 1/4 level mastitis detection model which provides a theoretical basis for mastitis detection in buffaloes mostly raised by small farmers lacking mastitis diagnostic conditions in developing countries.https://www.mdpi.com/2076-2615/14/5/707PolyLossconvolutional block attention modulesomatic cell countquartermastitis |
| spellingShingle | Xinxin Zhang Yuan Li Yiping Zhang Zhiqiu Yao Wenna Zou Pei Nie Liguo Yang A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network Animals PolyLoss convolutional block attention module somatic cell count quarter mastitis |
| title | A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network |
| title_full | A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network |
| title_fullStr | A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network |
| title_full_unstemmed | A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network |
| title_short | A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network |
| title_sort | new method to detect buffalo mastitis using udder ultrasonography based on deep learning network |
| topic | PolyLoss convolutional block attention module somatic cell count quarter mastitis |
| url | https://www.mdpi.com/2076-2615/14/5/707 |
| work_keys_str_mv | AT xinxinzhang anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT yuanli anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT yipingzhang anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT zhiqiuyao anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT wennazou anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT peinie anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT liguoyang anewmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT xinxinzhang newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT yuanli newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT yipingzhang newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT zhiqiuyao newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT wennazou newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT peinie newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork AT liguoyang newmethodtodetectbuffalomastitisusingudderultrasonographybasedondeeplearningnetwork |