Deep LOGISMOS: Deep learning graph-based 3D segmentation of pancreatic tumors on CT scans

  title={Deep LOGISMOS: Deep learning graph-based 3D segmentation of pancreatic tumors on CT scans},
  author={Zhihui Guo and Ling Zhang and Le Lu and Mohammadhadi Bagheri and Ronald M. Summers and Milan Sonka and Jianhua Yao},
  journal={2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)},
  • Zhihui GuoLing Zhang Jianhua Yao
  • Published 25 January 2018
  • Computer Science
  • 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
This paper reports Deep LOGISMOS approach to 3D tumor segmentation by incorporating boundary information derived from deep contextual learning to LOGISMOS — layered optimal graph image segmentation of multiple objects and surfaces. Accurate and reliable tumor segmentation is essential to tumor growth analysis and treatment selection. A fully convolutional network (FCN), UNet, is first trained using three adjacent 2D patches centered at the tumor, providing contextual UNet segmentation and… 

Figures and Tables from this paper

Auto-segmentation of pancreatic tumor in multi-parametric MRI using deep convolutional neural networks.

  • Ying LiangD. Schott X. Li
  • Medicine, Physics
    Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
  • 2020

Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet

A Probabilistic-map-guided bi-directional recurrent UNet (PBR-UNet) architecture, which fuses intra-slice information and inter-slice probabilistic maps into a local 3D hybrid regularization scheme, which is followed by a bi- directional recurrent optimization scheme.

BoxNet: Deep Learning Based Biomedical Image Segmentation Using Boxes Only Annotation

This paper develops a method to combine graph search and DL to generate fine object masks from box annotation, in which DL uses box annotation to compute a rough segmentation for GS and then GS is applied to locate the optimal object boundaries.

DCE-MRI Breast Lesions Segmentation with a 3TP U-Net Deep Convolutional Neural Network

This work proposes "3TP U-Net", an U-Shaped Deep Convolutional Neural Network that exploits the well-known Three Time Points approach for the lesion segmentation task, and shows that it is able to outperform not only the classical (non-deep) approaches but also some very recent deep proposal.

U-Net Based Architecture for an Improved Multiresolution Segmentation in Medical Images

mrU-Net illustrated a faster training rate and slightly more accurate image segmentation compared to U-Net, and added more convolution layers to extract features directly from the down-sampled images to boost its higher capability in extracting image-derived features.

Quantitative analysis of metastatic breast cancer in mice using deep learning on cryo-image data

Assessing the size and distribution of metastases proves the usefulness and robustness of cryo-imaging and the software for evaluating new cancer imaging and therapeutics technologies.

Automatic Pancreas Segmentation Using Double Adversarial Networks with Pyramidal Pooling Module

An automatic segmentation model using double adversarial networks with a pyramidal pooling module to collect multi-level features and retain substantial information for segmentation in order to improve the network segmentation performance.

DLU-Net for Pancreatic Cancer Segmentation

An extension of the convolutional network U-Net is proposed, which is called DLU-Net, for accurately cutting out the irregular shape of Pancreas and improving the segmentation accuracy for pancreatic cancer, that can more accurately segment the edge of cancer.

A Novel Bayesian Model Incorporating Deep Neural Network and Statistical Shape Model for Pancreas Segmentation

This work proposes a novel Bayesian model incorporating the segmentation results from both deep neural network and statistical shape model for segmentation and reports 85.32 % of the mean DSC that outperforms the state-of-the-art and approximately 12 % improvement from the predicted segment ofDeep neural network.



Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation

This paper proposes a new DL framework for 3D image segmentation, based on a fully convolutional network (FCN) and a recurrent neural network (RNN), which are responsible for exploiting the intra-slice and inter-slice contexts, respectively.

Combining fully convolutional networks and graph-based approach for automated segmentation of cervical cell nuclei

A novel approach for segmentation of cervical nuclei that combines fully convolutional networks (FCN) and graph-based approach (FCNG), which is trained to learn the nucleus high-level features to generate a nucleus label mask and a nucleus probabilistic map.

Machine learning in a graph framework for subcortical segmentation

A 3D graph-based machine learning method, called LOGISMOS-RF, to segment the caudate and the putamen from brain MRI scans in a robust and accurate way, which is statistically significantly more accurate than the three other methods.

LOGISMOS—Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces: Cartilage Segmentation in the Knee Joint

The reported LOGISMOS framework provides robust and accurate segmentation of the knee joint bone and cartilage surfaces of the femur, tibia, and patella, and the developed framework can be applied to a broad range of multiobject multisurface segmentation problems.

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation

This work proposes a deep convolution encoder-decoder structure with fusion layers to incorporate different modalities of MRI data and exploits convolutional LSTM to model a sequence of 2D slices, and jointly learn the multi-modalities and convLSTM in an end-to-end manner.

Personalized Pancreatic Tumor Growth Prediction via Group Learning

A deep convolutional neural network approach is developed to model the voxel-wise spatio-temporal tumor progression and achieves a Dice coefficient of 86.8%, outperforming the DSC and RVD obtained by a previous state-of-the-art model-based method.

An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision

The goal of this paper is to provide an experimental comparison of the efficiency of min-cut/max flow algorithms for applications in vision, comparing the running times of several standard algorithms, as well as a new algorithm that is recently developed.

Caffe: Convolutional Architecture for Fast Feature Embedding

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.