期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 39, 期 12, 页码 4124-4136出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.3013246
关键词
Image segmentation; Standards; Task analysis; Pathology; Harmonic analysis; Computer architecture; Machine learning; Rotation-equivariance; steerable filters; deep learning; computational pathology
类别
资金
- PathLAKE Digital Pathology Consortium - Data to Early Diagnosis and Precision Medicine Strand of the government's Industrial Strategy Challenge Fund
- U.K. Medical Research Council (MRC) [MR/P015476/1]
- MRC [MR/P015476/1] Funding Source: UKRI
Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear. However, this rotational symmetry is not widely utilised as prior knowledge in modern Convolutional Neural Networks (CNNs), resulting in data hungry models that learn independent features at each orientation. Allowing CNNs to be rotation-equivariant removes the necessity to learn this set of transformations from the data and instead frees up model capacity, allowing more discriminative features to be learned. This reduction in the number of required parameters also reduces the risk of overfitting. In this paper, we propose Dense Steerable Filter CNNs (DSF-CNNs) that use group convolutions with multiple rotated copies of each filter in a densely connected framework. Each filter is defined as a linear combination of steerable basis filters, enabling exact rotation and decreasing the number of trainable parameters compared to standard filters. We also provide the first in-depth comparison of different rotation-equivariant CNNs for histology image analysis and demonstrate the advantage of encoding rotational symmetry into modern architectures. We show that DSF-CNNs achieve state-of-the-art performance, with significantly fewer parameters, when applied to three different tasks in the area of computational pathology: breast tumour classification, colon gland segmentation and multi-tissue nuclear segmentation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据