Objective-Dependent Uncertainty Driven Retinal Vessel Segmentation
This work addresses the challenge of accurate tiny vessel segmentation in medical imaging, which is critical for diagnosing neovascular diseases, but it is incremental as it builds on existing deep learning approaches with specific enhancements.
The paper tackles the problem of segmenting tiny vessels in retinal fundus images by proposing a deep CNN that separates overall vessel segmentation and tiny vessel segmentation into two objectives, using objective-dependent uncertainty to learn both simultaneously. The result is an 8.3% average improvement in sensitivity for tiny vessels and better AUC compared to state-of-the-art methods on three public datasets.
From diagnosing neovascular diseases to detecting white matter lesions, accurate tiny vessel segmentation in fundus images is critical. Promising results for accurate vessel segmentation have been known. However, their effectiveness in segmenting tiny vessels is still limited. In this paper, we study retinal vessel segmentation by incorporating tiny vessel segmentation into our framework for the overall accurate vessel segmentation. To achieve this, we propose a new deep convolutional neural network (CNN) which divides vessel segmentation into two separate objectives. Specifically, we consider the overall accurate vessel segmentation and tiny vessel segmentation as two individual objectives. Then, by exploiting the objective-dependent (homoscedastic) uncertainty, we enable the network to learn both objectives simultaneously. Further, to improve the individual objectives, we propose: (a) a vessel weight map based auxiliary loss for enhancing tiny vessel connectivity (i.e., improving tiny vessel segmentation), and (b) an enhanced encoder-decoder architecture for improved localization (i.e., for accurate vessel segmentation). Using 3 public retinal vessel segmentation datasets (CHASE_DB1, DRIVE, and STARE), we verify the superiority of our proposed framework in segmenting tiny vessels (8.3% average improvement in sensitivity) while achieving better area under the receiver operating characteristic curve (AUC) compared to state-of-the-art methods.