论文标题
深入监督手指骨骼细分的主动学习
Deeply Supervised Active Learning for Finger Bones Segmentation
论文作者
论文摘要
细分是医学图像分析的先决条件但又具有挑战性的任务。在本文中，我们介绍了一种新型的有监督的活跃学习方法，以进行手指骨骼细分。提出的架构以迭代和增量学习方式进行了微调。在每个步骤中，深度监督机制都指导隐藏层的学习过程，并选择要标记的样本。广泛的实验表明，与完整注释相比，使用标记的样品较少的样品可实现竞争性分割结果。
Segmentation is a prerequisite yet challenging task for medical image analysis. In this paper, we introduce a novel deeply supervised active learning approach for finger bones segmentation. The proposed architecture is fine-tuned in an iterative and incremental learning manner. In each step, the deep supervision mechanism guides the learning process of hidden layers and selects samples to be labeled. Extensive experiments demonstrated that our method achieves competitive segmentation results using less labeled samples as compared with full annotation.
