Neural Network Classification of Maternal Fetal Ultrasound Planes
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)
Want to read the original?
Access the complete publication on the publisher's website