Novel neural network classification of maternal fetal ultrasound planes through optimized feature selection
2024

Neural Network Classification of Maternal Fetal Ultrasound Planes

Sample size: 12400 publication 10 minutes Evidence: high

Author Information

Author(s): Rathika S., Mahendran K., Sudarsan H., Ananth S. Vijay

Primary Institution: Prince Shri Venkateshwara Padmavathy Engineering College, Chennai, India

Hypothesis

Can a Deep Learning-based automated categorization method improve the detection efficiency and diagnosis accuracy of maternal fetal ultrasound planes?

Conclusion

The proposed approach provides a solid foundation for automating the classification of fetal ultrasound planes, enhancing prenatal diagnosis and care.

Supporting Evidence

  • The proposed model achieved an accuracy of 98.07%, surpassing existing models.
  • Feature selection using PSOGWO improved classification performance significantly.
  • The study demonstrated that the Fast-RBFNN model outperformed conventional deep learning models.
  • Pre-processing steps were crucial for achieving optimal model performance.

Takeaway

This study created a smart computer program that helps doctors quickly and accurately identify different parts of a baby in ultrasound pictures.

Methodology

The study used a hybrid optimization technique for feature selection and a Radial Basis Function Neural Network for classification of maternal fetal ultrasound images.

Potential Biases

The dataset may have biases that complicate deep learning model training.

Limitations

The study used data from the same dataset for both training and testing, which may affect the model's generalizability.

Participant Demographics

The dataset consists of maternal-fetal ultrasound images collected from publicly available sources.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/s12880-024-01453-8

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication