用深度学习模型增强骑自行车的阴道镜观察结果的解释
Bindhu K Rajan1, Venugopal G2, Hiron Harshan M3
1Department of Instrumentation and Control Engineering, NSS College of Engineering Palakkad, Kerala, India (Affiliated to APJ Abdul Kalam Technological University, Kerala, India. bindhukrajan09@gmail.com.
BMC veterinary research
|September 8, 2024
概括
这项研究提出了一种新的AI驱动的方法,使用深度学习和阴道镜图像来准确识别狗的雌激周期阶段. 采用XGBoost的ResNet 152模型实现了90%以上的准确性,帮助了犬种繁殖计划.
科学领域:
- 兽医医学 兽医医学 兽医医学
- 动物繁殖 动物繁殖
- 动物健康中的人工智能
背景情况:
- 准确地识别骑自行车的雌性狗的雌性是成功养犬的关键.
- 对于雌性周期分期的传统方法包括行为评估,细胞学,阴道透视和荷尔蒙检测.
- 阴道镜检查提供了一种实用且具有成本效益的方法来评估狗的繁殖期.
研究的目的:
- 开发和验证一种创新的,人工智能驱动的方法,用于精确识别犬类雌性周期阶段.
- 利用深度学习模型从阴道镜图像中提取特征.
- 为了比较先进的人工智能模型的性能与传统的机器学习算法用于雌激周期分类.
主要方法:
- 使用了210张代表四个生殖阶段的狗阴道镜图像的数据集.
- 使用Inception v3和Residual Networks (ResNet) 152模型进行了深度功能提取.
- 使用二进制灰狼优化 (BGWO) 进行了功能优化,并通过极端梯度增强 (XGBoost) 进行了分类.
- 性能与支持矢量机 (SVM),k-近邻 (KNN) 和卷积神经网络 (CNN) 相比进行了基准测试.
主要成果:
- 与XGBoost分类器相结合的ResNet 152模型实现了90.37%的平均精度.
- 对于前期,前期,前期和后期的具体准确率分别为90.91%,96.38%,88.37%和88.24%.
- 发明v3模型也表现出高性能,准确度为89.41%,相当于ResNet 152.
- 拟议的深度学习方法在准确性和其他关键指标方面明显优于传统的机器学习模型.
结论:
- 开发的AI系统提供了一种可靠和有效的工具,用于从阴道镜图像中识别狗的雌性周期阶段.
- 这项技术可以通过精确确定最佳交配时期,显著提高犬种育种计划的成功率.
- 这些发现支持将先进的人工智能技术纳入兽医诊断,以改善动物生殖健康管理.
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...


