A multi-feature fusion-based model for fetal orientation classification from intrapartum ultrasound videos.
10.12122/j.issn.1673-4254.2025.07.24
- Author:
Ziyu ZHENG
1
;
Xiaying YANG
2
;
Shengjie WU
3
;
Shijie ZHANG
2
;
Guorong LYU
2
;
Peizhong LIU
3
;
Jun WANG
4
;
Shaozheng HE
2
Author Information
1. Department of Information Construction and Management.
2. Department of Ultrasound, Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China.
3. College of Engineering, Huaqiao University, Quanzhou 362021, China.
4. Department of Obstetrics and Gynecology, Affiliated People's Hospital of Quanzhou Medical College, Quanzhou 362018, China.
- Publication Type:Journal Article
- Keywords:
attention mechanism;
deep learning;
fetal orientation;
intrapartum ultrasound
- MeSH:
Humans;
Female;
Ultrasonography, Prenatal/methods*;
Pregnancy;
Fetus/diagnostic imaging*;
Neural Networks, Computer;
Video Recording
- From:
Journal of Southern Medical University
2025;45(7):1563-1570
- CountryChina
- Language:Chinese
-
Abstract:
OBJECTIVES:To construct an intelligent analysis model for classifying fetal orientation during intrapartum ultrasound videos based on multi-feature fusion.
METHODS:The proposed model consists of the Input, Backbone Network and Classification Head modules. The Input module carries out data augmentation to improve the sample quality and generalization ability of the model. The Backbone Network was responsible for feature extraction based on Yolov8 combined with CBAM, ECA, PSA attention mechanism and AIFI feature interaction module. The Classification Head consists of a convolutional layer and a softmax function to output the final probability value of each class. The images of the key structures (the eyes, face, head, thalamus, and spine) were annotated with frames by physicians for model training to improve the classification accuracy of the anterior occipital, posterior occipital, and transverse occipital orientations.
RESULTS:The experimental results showed that the proposed model had excellent performance in the tire orientation classification task with the classification accuracy reaching 0.984, an area under the PR curve (average accuracy) of 0.993, and area under the ROC curve of 0.984, and a kappa consistency test score of 0.974. The prediction results by the deep learning model were highly consistent with the actual classification results.
CONCLUSIONS:The multi-feature fusion model proposed in this study can efficiently and accurately classify fetal orientation in intrapartum ultrasound videos.
