Deep learning based detection and classification of fetal lip in ultrasound images
Author:
Li Yapeng1, Cai Peiya2, Huang Yubing3, Yu Weifeng4, Liu Zhonghua4, Liu Peizhong15
Affiliation:
1. School of Medicine , Huaqiao University , Quanzhou , China 2. Department of Gynecology and Obstetrics , The Second Affiliated Hospital of Fujian Medical University , Quanzhou , China 3. Department of Ultrasound , The Second Affiliated Hospital of Fujian Medical University , Quanzhou , China 4. Department of Ultrasound , Quanzhou First Hospital Affiliated to Fujian Medical University , Quanzhou , China 5. College of Engineering , Huaqiao University , Quanzhou , China
Abstract
Abstract
Objectives
Fetal cleft lip is a common congenital defect. Considering the delicacy and difficulty of observing fetal lips, we have utilized deep learning technology to develop a new model aimed at quickly and accurately assessing the development of fetal lips during prenatal examinations. This model can detect ultrasound images of the fetal lips and classify them, aiming to provide a more objective prediction for the development of fetal lips.
Methods
This study included 632 pregnant women in their mid-pregnancy stage, who underwent ultrasound examinations of the fetal lips, collecting both normal and abnormal fetal lip ultrasound images. To improve the accuracy of the detection and classification of fetal lips, we proposed and validated the Yolov5-ECA model.
Results
The experimental results show that, compared with the currently popular 10 models, our model achieved the best results in the detection and classification of fetal lips. In terms of the detection of fetal lips, the mean average precision (mAP) at 0.5 and mAP at 0.5:0.95 were 0.920 and 0.630, respectively. In the classification of fetal lip ultrasound images, the accuracy reached 0.925.
Conclusions
The deep learning algorithm has accuracy consistent with manual evaluation in the detection and classification process of fetal lips. This automated recognition technology can provide a powerful tool for inexperienced young doctors, helping them to accurately conduct examinations and diagnoses of fetal lips.
Funder
Quanzhou Scientific and Technological Planning Projects National Natural Science Foundation of Fujian scientific Research Funds of Huaqiao University
Publisher
Walter de Gruyter GmbH
Reference47 articles.
1. Mossey, PA, Little, J, Munger, RG, Dixon, MJ, Shaw, WC. Cleft lip and palate. Lancet 2009;374:1773–85. https://doi.org/10.1016/s0140-6736(09)60695-4. 2. Lee, W, Kirk, J, Shaheen, K, Romero, R, Hodges, A, Comstock, C. Fetal cleft lip and palate detection by three-dimensional ultrasonography. Ultrasound Obstet Gynecol: Off J Int Soc Ultrasound Obstet Gynecol 2000;16:314–20. https://doi.org/10.1046/j.1469-0705.2000.00181.x. 3. Berge, S, Plath, H, Van de Vondel, P, Appel, T, Niederhagen, B, Von Lindern, J, et al.. Fetal cleft lip and palate: sonographic diagnosis, chromosomal abnormalities, associated anomalies and postnatal outcome in 70 fetuses. Ultrasound Obstet Gynecol: Off J Int Soc Ultrasound Obstet Gynecol 2001;18:422–31. https://doi.org/10.1046/j.0960-7692.2001.00575.x. 4. Shaw, GM, Vollset, SE, Carmichael, SL, Yang, W, Finnell, RH, Blom, H, et al.. Nested case-control study of one-carbon metabolites in mid-pregnancy and risks of cleft lip with and without cleft palate. Pediatr Res 2009;66:501–6. https://doi.org/10.1203/pdr.0b013e3181b9b544. 5. Liu, H, Yan, F, Sun, H, Li, G, Ai, F, Dong, X. Ultrasonography of fetal cleft lip and palate in first-trimester. Clin Exp Obstet Gynecol 2017;44:408–12. https://doi.org/10.12891/ceog3406.2017.
|
|