Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation

By Zengqiang Yan, Xin Yang, Kwang-Ting Cheng. IEEE Transactions on Biomedical Engineering, 2018

385 citations recorded by the source corpus.

Objective: Deep learning based methods for retinal vessel segmentation are usually trained based on pixel-wise losses, which treat all vessel pixels with equal importance in pixel-to-pixel matching between a predicted probability map and the corresponding manually annotated segmentation. However, due to the highly imbalanced pixel ratio between thick and thin vessels in fundus images, a pixel-wise loss would limit deep learning models to learn features for accurate segmentation of thin vessels, which is an important task for clinical diagnosis of eye-related diseases. Methods: In this paper, we propose a new segment-level loss which emphasizes more on the thickness consistency of thin vessels in the training process. By jointly adopting both the segment-level and the pixel-wise losses, the importance between thick and thin vessels in the loss calculation would be more balanced. As a result, more effective features can be learned for vessel segmentation without increasing the overall model complexity. Results: Experimental results on public data sets demonstrate that the model trained by the joint losses outperforms the current state-of-the-art methods in both separate-training and cross-training evaluations. Conclusion: Compared to the pixel-wise loss, utilizing the proposed joint-loss framework is able to learn more distinguishable features for vessel segmentation. In addition, the segment-level loss can bring consistent performance improvement for both deep and shallow network architectures. Significance: The findings from this study of using joint losses can be applied to other deep learning models for performance improvement without significantly changing the network architectures.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/a3c99c3ddd80c6b420217262e96e66bedc0f4d63

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Gary G. Yen
2. Yuta Nakashima
3. Yao Zhou
4. Zhang Yi
5. Liangzhi Li
6. Bing Xue
7. Mengjie Zhang
8. Yanan Sun

In Ophthalmology

1. Gary G. Yen
2. Yao Zhou
3. Zhang Yi

In Radiology, Nuclear Medicine and Imaging

1. Gary G. Yen
2. Yao Zhou
3. Zhang Yi

Citations in the corpus

• Evolutionary Compression of Deep Neural Networks for Biomedical Image Segmentation (2020, methodology): “The area under curve (AUC) of the receiving operator characteristics (ROC) curve is computed as a performance metric as well, which is threshold independent and can approximately measure the overall performance [34], [61].”
• IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks (2019, background): “The emergence of UNet [1] leads to a new era of image segmentation in the medical domain, and has revolutionized most image segmentation tasks in relevant domain [15, 16, 17, 18, 19].”
• SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation (2020, neutral): “[17] 2018 0.”