Automatic Liver Segmentation Using an Adversarial Image-to-Image Network

Yang, Dong; Xu, Daguang; Zhou, S. Kevin; Georgescu, Bogdan; Chen, Mingqing; Grbić, Saša; Metaxas, Dimitris N.; Comanicìu, Dorin

doi:10.1007/978-3-319-66179-7_58

Cited by 173 publications

(127 citation statements)

References 12 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…It is known that the process of liver segmentation has many difficulties (challenges) [46] and of the difficulties that faced us in this study, including what is related to medical images in general, they contain artifacts and the weakness of the border in some cases so we used the first phase in various steps to reduce the noise and clarification of the boundary to the extent that can be relied upon somewhat in the segmentation process.…”

Section: Resultsmentioning

confidence: 99%

Automatic Liver Segmentation from Abdominal MRI Images using Active Contours

Mohamed

Seada

Hamdy

et al. 2017

IJCA

View full text Add to dashboard Cite

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 system for the automatic segmentation of the liver from Magnetic Resonance Images (MRI). The system works without the need for setting manual seed points or setting a region of interest. Instead, the proposed system automatically detects and segments the liver through relying on its anatomical features for detection and using active contour for segmentation. The proposed segmentation system begins with localizing the liver or a part of it from a given MRI image using biggest components analysis. The extracted liver part is later used as a mask for full liver segmentation using active contour. The proposed system is fully automatic, works on different cases of MRI images (different sizes, healthy and abnormal liver). The detection and segmentation of the liver succeeded in 95% of the test cases acquired from different MRI imaging modalities.

show abstract

Section: Resultsmentioning

confidence: 99%

Automatic Liver Segmentation from Abdominal MRI Images using Active Contours

Mohamed

Seada

Hamdy

et al. 2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Especially for biomedical image segmentation they have been shown to be very successful in terms of accuracy and robustness, e.g. [13], [14], [15], [16], [17]. By now there are many competing architectures that yield fast performance and high accuracy.…”

Section: Machine Learningmentioning

confidence: 99%

Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

Eule

Haering

Grosshans

et al. 2018

Preprint

View full text Add to dashboard Cite

A central problem in biomedical imaging is the automated segmentation of images for further quantitative analysis. Recently, fully convolutional neural networks, such as the U-Net, were applied successfully in a variety of segmentation tasks. A downside of this approach is the requirement for a large amount of well-prepared training samples, consisting of image -ground truth mask pairs. Since training data must be created by hand for each experiment, this task can be very costly and time-consuming. Here, we present a segmentation method based on cycle consistent generative adversarial networks, which can be trained even in absence of prepared image -mask pairs. We show that it successfully performs image segmentation tasks on samples with substantial defects and even generalizes well to different tissue types.

show abstract

“…However, segmentation error often occur near the organ surface largely due to low image quality, vague organ boundaries, and large organ shape variation. Although several attempts [1,9] have been reported in the literature, it is still challenging for deep learning models to produce segmented results with smooth and realistic shapes as it would require strong global reasoning ability to model relations between all image voxels.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Adversarial Shape Learning for Abdomen Organ Deep Segmentation

Cai

Xia

Yang

et al. 2019

Machine Learning in Medical Imaging

Self Cite

View full text Add to dashboard Cite

Automatic segmentation of abdomen organs using medical imaging has many potential applications in clinical workflows. Recently, the state-of-the-art performance for organ segmentation has been achieved by deep learning models, i.e., convolutional neural network (CNN). However, it is challenging to train the conventional CNN-based segmentation models that aware of the shape and topology of organs. In this work, we tackle this problem by introducing a novel end-to-end shape learning architecture -organ point-network. It takes deep learning features as inputs and generates organ shape representations as points that located on organ surface. We later present a novel adversarial shape learning objective function to optimize the point-network to capture shape information better. We train the point-network together with a CNN-based segmentation model in a multi-task fashion so that the shared network parameters can benefit from both shape learning and segmentation tasks. We demonstrate our method with three challenging abdomen organs including liver, spleen, and pancreas. The point-network generates surface points with fine-grained details and it is found critical for improving organ segmentation. Consequently, the deep segmentation model is improved by the introduced shape learning as significantly better Dice scores are observed for spleen and pancreas segmentation.

show abstract

Automatic Liver Segmentation Using an Adversarial Image-to-Image Network

Cited by 173 publications

References 12 publications

Automatic Liver Segmentation from Abdominal MRI Images using Active Contours

Automatic Liver Segmentation from Abdominal MRI Images using Active Contours

Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

End-to-End Adversarial Shape Learning for Abdomen Organ Deep Segmentation

Contact Info

Product

Resources

About