Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:3193-3196. doi: 10.1109/EMBC46164.2021.9630108.
Automatic breast ultrasound image (BUS) segmentation is still a challenging task due to poor image quality and inherent speckle noise. In this paper, we propose a novel multi-scale fuzzy generative adversarial network (MSF-GAN) for breast ultrasound image segmentation. The proposed MSF-GAN consists of two networks: a generative network to generate segmentation maps for input BUS images, and a discriminative network that employs a multi-scale fuzzy (MSF) entropy module for discrimination. The major contribution of this paper is applying fuzzy logic and fuzzy entropy in the discriminative network which can distinguish the uncertainty of segmentation maps and groundtruth maps and forces the generative network to achieve better segmentation performance. We evaluate the performance of MSF-GAN on three BUS datasets and compare it with six state-of-the-art deep neural network-based methods in terms of five metrics. MSF-GAN achieves the highest mean IoU of 78.75%, 73.30%, and 71.12% on three datasets, respectively.
自动乳腺超声图像 (BUS) 分割仍然是一项具有挑战性的任务，因为图像质量较差且存在固有的斑点噪声。在本文中，我们提出了一种新颖的多尺度模糊生成对抗网络 (MSF-GAN) 用于乳腺超声图像分割。所提出的 MSF-GAN 由两个网络组成：一个生成网络，用于为输入 BUS 图像生成分割图，以及一个判别网络，它采用多尺度模糊 (MSF) 熵模块进行判别。本文的主要贡献是在判别网络中应用模糊逻辑和模糊熵，可以区分分割图和真实图的不确定性，并迫使生成网络实现更好的分割性能。我们在三个 BUS 数据集上评估了 MSF-GAN 的性能，并在五个指标上与六种最先进的基于深度神经网络的方法进行了比较。MSF-GAN 在三个数据集上分别实现了最高的平均 IoU 为 78.75%、73.30%和 71.12%。
