DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
Preprint
Abstract
Deep convolutional neural networks have significantly boosted the performance of fundus image segmentation when test datasets have the same distribution as the training datasets. However, in clinical practice, medical images often exhibit variations in appearance for various reasons, e.g., different scanner vendors and image quality. These distribution discrepancies could lead the deep networks to over-fit on the training datasets and lack generalization ability on the unseen test datasets. To alleviate this issue, we present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains by exploring the knowledge from multiple source domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative. Specifically, we introduce a Domain Knowledge Pool to learn and memorize the prior information extracted from multi-source domains. Then the original image features are augmented with domain-oriented aggregated features, which are induced from the knowledge pool based on the similarity between the input image and multi-source domain images. We further design a novel domain code prediction branch to infer this similarity and employ an attention-guided mechanism to dynamically combine the aggregated features with the semantic features. We comprehensively evaluate our DoFE framework on two fundus image segmentation tasks, including the optic cup and disc segmentation and vessel segmentation. Our DoFE framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.Keywords
All Related Versions
- Version 1, 2020-10-13, ArXiv
- Published version: IEEE Transactions on Medical Imaging, 39 (12), 4237.
This publication has 21 references indexed in Scilit:
- REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographsMedical Image Analysis, 2020
- Continual lifelong learning with neural networks: A reviewNeural Networks, 2019
- Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel SegmentationIEEE Transactions on Biomedical Engineering, 2018
- Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentationComputerized Medical Imaging and Graphics, 2017
- Domain Generalization for Object Recognition with Multi-task Autoencoders2015
- An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel SegmentationIEEE Transactions on Biomedical Engineering, 2012
- Optic Disk and Cup Segmentation From Monocular Color Retinal Images for Glaucoma AssessmentIEEE Transactions on Medical Imaging, 2011
- Ridge-Based Vessel Segmentation in Color Images of the RetinaIEEE Transactions on Medical Imaging, 2004
- Optic Nerve Head SegmentationIEEE Transactions on Medical Imaging, 2004
- Locating blood vessels in retinal images by piecewise threshold probing of a matched filter responseIEEE Transactions on Medical Imaging, 2000