School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, China.
Department of Pathology, Changhai Hospital, The Navy Military Medical University, Shanghai, China.
Comput Biol Med. 2022 Dec;151(Pt A):106228. doi: 10.1016/j.compbiomed.2022.106228. Epub 2022 Oct 20.
The morphology of tissues in pathological images has been used routinely by pathologists to assess the degree of malignancy of pancreatic ductal adenocarcinoma (PDAC). Automatic and accurate segmentation of tumor cells and their surrounding tissues is often a crucial step to obtain reliable morphological statistics. Nonetheless, it is still a challenge due to the great variation of appearance and morphology. In this paper, a selected multi-scale attention network (SMANet) is proposed to segment tumor cells, blood vessels, nerves, islets and ducts in pancreatic pathological images. The selected multi-scale attention module is proposed to enhance effective information, supplement useful information and suppress redundant information at different scales from the encoder and decoder. It includes selection unit (SU) module and multi-scale attention (MA) module. The selection unit module can effectively filter features. The multi-scale attention module enhances effective information through spatial attention and channel attention, and combines different level features to supplement useful information. This helps learn the information of different receptive fields to improve the segmentation of tumor cells, blood vessels and nerves. An original-feature fusion unit is also proposed to supplement the original image information to reduce the under-segmentation of small tissues such as islets and ducts. The proposed method outperforms state-of-the-arts deep learning algorithms on our PDAC pathological images and achieves competitive results on the GlaS challenge dataset. The mDice and mIoU have reached 0.769 and 0.665 in our PDAC dataset.
组织病理学图像的形态学已被病理学家常规用于评估胰腺导管腺癌 (PDAC) 的恶性程度。自动且准确地分割肿瘤细胞及其周围组织通常是获取可靠形态学统计数据的关键步骤。尽管如此，由于外观和形态的巨大变化，这仍然是一个挑战。本文提出了一种选择的多尺度注意网络 (SMANet)，用于分割胰腺病理图像中的肿瘤细胞、血管、神经、胰岛和导管。所提出的选择多尺度注意模块用于从编码器和解码器的不同尺度增强有效信息、补充有用信息和抑制冗余信息。它包括选择单元 (SU) 模块和多尺度注意 (MA) 模块。选择单元模块可以有效地过滤特征。多尺度注意模块通过空间注意和通道注意增强有效信息，并结合不同层次的特征来补充有用信息。这有助于学习不同感受野的信息，从而提高肿瘤细胞、血管和神经的分割效果。还提出了一种原始特征融合单元，用于补充原始图像信息，以减少胰岛和导管等小组织的欠分割。与最先进的深度学习算法相比，该方法在我们的 PDAC 病理图像上表现出色，并在 GlAS 挑战数据集上取得了有竞争力的结果。我们的 PDAC 数据集的 mDice 和 mIoU 分别达到了 0.769 和 0.665。
