In Frontiers in reproductive health
Medical ultrasound imaging plays an important role in computer-aided diagnosis systems. In many cases, it is the preferred method of doctors for diagnosing diseases. Combined with computer vision technology, segmentation of ovarian ultrasound images can help doctors accurately judge diseases, reduce doctors' workload, and improve doctors' work efficiency. However, accurate segmentation of an ovarian ultrasound image is a challenging task. On the one hand, there is a lot of speckle noise in ultrasound images; on the other hand, the edges of objects are blurred in ultrasound images. In order to segment the target accurately, we propose an ovarian follicles segmentation network combined with edge information. By adding an edge detection branch at the end of the network and taking the edge detection results as one of the losses of the network, we can accurately segment the ovarian follicles in an ultrasound image, making the segmentation results finer on the edge. Experiments show that the proposed network improves the segmentation accuracy of ovarian follicles, and that it has advantages over current algorithms.
Chen Zhong, Zhang Changheng, Li Zhou, Yang Jinkun, Deng He
2022
computer-aided diagnosis, deep learning, deep neural network, medical image segmentation, ovarian follicle segmentation
