Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function
Published in
arXiv.org(2019)External Links:
TL
TL;DR
This work proposes a method as a part of the LiTS (Liver Tumor Segmentation Challenge) competition for ISBI 17 and MICCAI 17 comparing methods for automatics egmentation of liver lesions in CT scans and achieves very good shape extractions with high detection sensitivity, with competitive scores at time of publication.
Abstract
At present, lesion segmentation is still performed manually (or semi-automatically) by medical experts. To facilitate this process, we contribute a fully-automatic lesion segmentation pipeline. This work proposes a method as a part of the LiTS (Liver Tumor Segmentation Challenge) competition for ISBI 17 and MICCAI 17 comparing methods for automatics egmentation of liver lesions in CT scans. By utilizing cascaded, densely connected 2D U-Nets and a Tversky-coefficient based loss function, our framework achieves very good shape extractions with high detection sensitivity, with competitive scores at time of publication. In addition, adjusting hyperparameters in our Tversky-loss allows to tune the network towards higher sensitivity or robustness.
References16 items
1
Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks
2
Neural Network-Based Automatic Liver Tumor Segmentation With Random Forest-Based Candidate Filtering
3
Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
4
MR‐based synthetic CT generation using a deep convolutional neural network method
5