论文信息 - On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks

On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks

Deep learning-based methods achieved impressive results for the segmentation of medical images. With the development of 3D fully convolutional networks (FCNs), it has become feasible to produce improved results for multi-organ segmentation of 3D computed tomography (CT) images. The results of multi-organ segmentation using deep learning-based methods not only depend on the choice of networks architecture, but also strongly rely on the choice of loss function. In this paper, we present a discussion on the influence of Dice-based loss functions for multi-class organ segmentation using a dataset of abdominal CT volumes. We investigated three different types of weighting the Dice loss functions based on class label frequencies (uniform, simple and square) and evaluate their influence on segmentation accuracies. Furthermore, we compared the influence of different initial learning rates. We achieved average Dice scores of 81.3%, 59.5% and 31.7% for uniform, simple and square types of weighting when the learning rate is 0.001, and 78.2%, 81.0% and 58.5% for each weighting when the learning rate is 0.01. Our experiments indicated a strong relationship between class balancing weights and initial learning rate in training.

[1] Maria Wimmer,et al. Fully Convolutional Architectures for Multiclass Segmentation in Chest Radiographs , 2017, IEEE Transactions on Medical Imaging.

[2] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3] Thomas Brox,et al. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[4] Trevor Darrell,et al. Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5] Sébastien Ourselin,et al. Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations , 2017, DLMIA/ML-CDS@MICCAI.

[6] Thomas Brox,et al. U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7] Yuichiro Hayashi,et al. Towards dense volumetric pancreas segmentation in CT using 3D fully convolutional networks , 2017, Medical Imaging.

[8] Seyed-Ahmad Ahmadi,et al. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).