Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields

By P. Christ, Mohamed Ezzeldin A. Elshaer, Florian Ettlinger, S. Tatavarty, Marc Bickel, Patrick Bilic, Markus Rempfler, M. Armbruster, Felix O. Hofmann, M. D’Anastasi and 3 more. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2016

679 citations recorded by the source corpus.

Automatic segmentation of the liver and its lesion 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 abdomen images using cascaded fully convolutional neural networks (CFCNs) and dense 3D conditional random fields (CRFs). 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 from the predicted liver ROIs of step 1. We refine the segmentations of the CFCN using a dense 3D CRF that accounts for both spatial coherence and appearance. CFCN models were trained in a 2-fold cross-validation on the abdominal CT dataset 3DIRCAD comprising 15 hepatic tumor volumes. Our results show that CFCN-based semantic liver and lesion segmentation achieves Dice scores over \(94\,\%\) for liver with computation times below 100 s per volume. We experimentally demonstrate the robustness of the proposed method as a decision support system with a high accuracy and speed for usage in daily clinical routine.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/59d5a686c82c9c73ee5f6ef42b8be0c245dc84b1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

A survey on deep learning in medical image analysis (2017, methodology): “…graphical models like MRFs ( Shakeri t al., 2016; Song et al., 2015 ) and Conditional Random Fields (CRFs) Alansary et al., 2016; Cai et al., 2016a; Christ et al., 2016; Dou et al., 016b; Fu et al., 2016a; Gao et al., 2016c ) to refine the…”
Deep Learning-based Image Segmentation on Multimodal Medical Imaging (2019, methodology): “Further, for the task of automatic tumor segmentation, CNNs have been applied to segmentation of tumors in brain [5], [12], [13], liver [14], breast [15], lung [16], [17],”
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes (2018, methodology): “such as UNet architecture [15], the multi-channel FCN [16], and the FCN based on VGG-16 [17].”
An application of cascaded 3D fully convolutional networks for medical image segmentation (2018, background): “, 2016b) and/or performing slice-wise processing in 2D (Christ et al., 2016; Zhou et al., 2016a).”
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (2020, background): “, liver and liver tumor segmentation [101], [102], brain tumor segmentation [103]), which could be an effective way to refine segmentation results.”
Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks (2019, neutral): “For liver segmentation in CT, the reported values of HD vary greatly between 24 mm and 119 mm [53].”
Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges (2019, background): “Christ et al. [15] believed that by cascading the FCNs, the accuracy of liver lesion segmentation could be improved.”
A Review of Deep-Learning-Based Medical Image Segmentation Methods (2021, neutral): “[42] proposed superimposing a series of FCNs.”
Automatic Brain Tumor Segmentation Using Cascaded Anisotropic Convolutional Neural Networks (2017, background): “There are several benefits of using a cascaded framework for segmentation of hierarchical structures [7].”
PSNet: prostate segmentation on MRI based on a convolutional neural network (2018, methodology): “In this work, we use a weighted cross entropy loss function.(29) The loss function is formulated as follows:”