How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

Incorporating distance transform maps of ground truth into segmentation CNNs has been an interesting new trend in the last year. Despite many great works leading to improvements on a variety of segmentation tasks, the comparison among these methods has not been well studied. In this paper, our first contribution is to summarize the latest developments of these methods in the 3D medical segmentation field. The second contribution is that we systematically evaluated five benchmark methods on two representative public datasets. These experiments highlight that all the five benchmark methods can bring performance gains to baseline V-Net. However, the implementation details have a noticeable impact on the performance, and not all the methods hold the benefits on different datasets. Finally, we suggest the best practices and indicate unsolved problems for incorporating distance transform maps into CNNs, which we hope would be useful for the community. The codes and trained models are publicly available at https://github.com/JunMa11/SegWithDistMap.

[1]  Yong Yin,et al.  Shape-Aware Organ Segmentation by Predicting Signed Distance Maps , 2019, AAAI.

[2]  Xin Yang,et al.  Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? , 2018, IEEE Transactions on Medical Imaging.

[3]  Jose Dolz,et al.  Boundary loss for highly unbalanced segmentation , 2018, MIDL.

[4]  Hao Chen,et al.  The Liver Tumor Segmentation Benchmark (LiTS) , 2019, Medical Image Anal..

[5]  Chi-Wing Fu,et al.  Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation , 2019, MICCAI.

[6]  Gang Li,et al.  Benchmark on Automatic Six-Month-Old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge , 2019, IEEE Transactions on Medical Imaging.

[7]  Bjoern H Menze,et al.  Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation , 2019, MLMI@MICCAI.

[8]  Klaus H. Maier-Hein,et al.  Automated Design of Deep Learning Methods for Biomedical Image Segmentation , 2019 .

[9]  Ronald M. Summers,et al.  A large annotated medical image dataset for the development and evaluation of segmentation algorithms , 2019, ArXiv.

[10]  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).

[11]  Alejandro F. Frangi,et al.  Tubular Structure Segmentation Using Spatial Fully Connected Network with Radial Distance Loss for 3D Medical Images , 2019, MICCAI.

[12]  Septimiu E. Salcudean,et al.  Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks , 2019, IEEE Transactions on Medical Imaging.

[13]  Yan Wang,et al.  Deep Distance Transform for Tubular Structure Segmentation in CT Scans , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Ziv Yaniv,et al.  A Distance Map Regularized CNN for Cardiac Cine MR Image Segmentation , 2019, Medical physics.

[15]  Marleen de Bruijne,et al.  Automated Lesion Detection by Regressing Intensity-Based Distance with a Neural Network , 2019, MICCAI.