Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks

Abstract

Automatic segmentation of the liver and hepatic lesions is an important step towards deriving quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This paper presents a method to automatically segment liver and lesions in CT and MRI abdomen images using cascaded fully convolutional neural networks (CFCNs) enabling the segmentation of a large-scale medical trial or quantitative image analysis. We train and cascade two FCNs for a combined segmentation of the liver and its lesions. In the first step, we train a FCN to segment the liver as ROI input for a second FCN. The second FCN solely segments lesions within the predicted liver ROIs of step 1. CFCN models were trained on an abdominal CT dataset comprising 100 hepatic tumor volumes. Validations on further datasets show that CFCN-based semantic liver and lesion segmentation achieves Dice scores over 94% for liver with computation times below 100s per volume. We further experimentally demonstrate the robustness of the proposed method on an 38 MRI liver tumor volumes and the public 3DIRCAD dataset.

arXiv commentUnder Review

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation
• Metastatic liver tumour segmentation from discriminant Grassmannian manifolds

Cited by in corpus (24)

• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation
• Adapting Mask-RCNN for Automatic Nucleus Segmentation
• Automatic Liver Lesion Detection using Cascaded Deep Residual Networks
• PA-ResSeg: A Phase Attention Residual Network for Liver Tumor Segmentation from Multi-phase CT Images
• Gastric histopathology image segmentation using a hierarchical conditional random field
• Early Detection of Retinopathy of Prematurity stage using Deep Learning approach
• Detection-aided liver lesion segmentation using deep learning
• Liver Segmentation from Multimodal Images using HED-Mask R-CNN
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• Hybrid Cascaded Neural Network for Liver Lesion Segmentation
• Deep Supervision for Pancreatic Cyst Segmentation in Abdominal CT Scans
• Interactive Deep Refinement Network for Medical Image Segmentation
• Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function
• Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey
• Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning
• ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
• Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
• A Time Series Graph Cut Image Segmentation Scheme for Liver Tumors
• Spinal Metastases Segmentation in MR Imaging using Deep Convolutional Neural Networks
• Fully Convolutional Network for Melanoma Diagnostics
• Automated Human Claustrum Segmentation using Deep Learning Technologies
• 3D Organ Shape Reconstruction from Topogram Images
• Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans