Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples
This work addresses the problem of efficient and accurate 3D medical image segmentation for clinical applications, representing an incremental advance with specific performance gains.
The authors tackled the challenge of applying deep neural networks to 3D medical image segmentation by proposing a novel 3D coarse-to-fine framework, which achieved state-of-the-art results with an average improvement of over 2% and up to 7% in Dice-Sorensen Coefficient on datasets like NIH pancreas.
Although deep neural networks have been a dominant method for many 2D vision tasks, it is still challenging to apply them to 3D tasks, such as medical image segmentation, due to the limited amount of annotated 3D data and limited computational resources. In this chapter, by rethinking the strategy to apply 3D Convolutional Neural Networks to segment medical images, we propose a novel 3D-based coarse-to-fine framework to efficiently tackle these challenges. The proposed 3D-based framework outperforms their 2D counterparts by a large margin since it can leverage the rich spatial information along all three axes. We further analyze the threat of adversarial attacks on the proposed framework and show how to defense against the attack. We conduct experiments on three datasets, the NIH pancreas dataset, the JHMI pancreas dataset and the JHMI pathological cyst dataset, where the first two and the last one contain healthy and pathological pancreases respectively, and achieve the current state-of-the-art in terms of Dice-Sorensen Coefficient (DSC) on all of them. Especially, on the NIH pancreas segmentation dataset, we outperform the previous best by an average of over $2\%$, and the worst case is improved by $7\%$ to reach almost $70\%$, which indicates the reliability of our framework in clinical applications.