Li Xinyao, Yao Yuan, Ni Dong, Chen Siping, Li Shengli, Lei Baiying, Wang Tianfu
Department of Biomedical Engineering, School of Medicine, Shenzhen University, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Shenzhen, China.
Department of Ultrasound, Affiliated Shenzhen Maternal and Child Healthcare, Hospital of Nanfang Medical University, Shenzhen, China.
Biomed Mater Eng. 2014;24(6):2821-9. doi: 10.3233/BME-141100.
Currently, placental maturity staging is mainly based on subjective observation of the physician. To address this issue, a new method is proposed for automatic staging of placental maturity based on B-mode ultrasound images. Due to small variations in the placental images, dense descriptor is utilized in place of the sparse descriptor to boost performance. Dense sampled DAISY descriptor is investigated for the demonstrated scale and translation invariant properties. Moreover, the extracted dense features are encoded by vector locally aggregated descriptor (VLAD) for performance boosting. The experimental results demonstrate an accuracy of 0.874, a sensitivity of 0.996 and a specificity of 0.874 for placental maturity staging. The experimental results also show that the dense features outperform the sparse features.
目前，胎盘成熟度分级主要基于医生的主观观察。为了解决这个问题，提出了一种基于B超图像的胎盘成熟度自动分级新方法。由于胎盘图像变化较小，因此使用密集描述符代替稀疏描述符来提高性能。研究了密集采样的DAISY描述符的尺度和平移不变性。此外，提取的密集特征通过向量局部聚集描述符（VLAD）进行编码以提高性能。实验结果表明，胎盘成熟度分级的准确率为0.874，灵敏度为0.996，特异性为0.874。实验结果还表明，密集特征优于稀疏特征。
