Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks
Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks
复制标题
DOI：
10.1109/tmi.2019.2930068
复制
发表时间：
2020-02-01
影响因子：
10.6
通讯作者：
Salcudean, Septimiu E.
中科院分区：
文献类型：
--
作者：
Karimi, Davood;Salcudean, Septimiu E.
Hausdorff距离(HD)广泛应用于评价医学图像分割方法。然而，现有的分割方法并没有尝试直接降低HD。在本文中，我们提出了一种新的损失函数来训练基于卷积神经网络(CNN)的分割方法，目的是直接降低HD。我们提出了三种从CNN产生的分割概率图估计HD的方法。一种方法是利用分割边界的距离变换。另一种方法是基于对真实分割图和估计分割图之间的差异进行形态侵蚀。第三种方法是在分割概率图上应用不同半径的圆形/球形卷积核。基于这三种估计HD的方法，我们提出了三种可用于训练以减少HD的损失函数。我们使用这些损失函数来训练CNN，以便在超声、磁共振和计算机断层扫描图像中分割前列腺、肝脏和胰腺，并将结果与常用的损失函数进行比较。我们的结果表明，所提出的损失函数可以在不降低其他分割性能指标(如Dice相似系数)的情况下，导致HD的近似降低。提出的损失函数可用于训练医学图像分割方法，以减少较大的分割误差。
The Hausdorff Distance (HD) is widely used in evaluating medical image segmentation methods. However, the existing segmentation methods do not attempt to reduce HD directly. In this paper, we present novel loss functions for training convolutional neural network (CNN)-based segmentation methods with the goal of reducing HD directly. We propose three methods to estimate HD from the segmentation probability map produced by a CNN. One method makes use of the distance transform of the segmentation boundary. Another method is based on applying morphological erosion on the difference between the true and estimated segmentation maps. The third method works by applying circular/spherical convolution kernels of different radii on the segmentation probability maps. Based on these three methods for estimating HD, we suggest three loss functions that can be used for training to reduce HD. We use these loss functions to train CNNs for segmentation of the prostate, liver, and pancreas in ultrasound, magnetic resonance, and computed tomography images and compare the results with commonly-used loss functions. Our results show that the proposed loss functions can lead to approximately reduction in HD without degrading other segmentation performance criteria such as the Dice similarity coefficient. The proposed loss functions can be used for training medical image segmentation methods in order to reduce the large segmentation errors.