Search

Liver tumor segmentation (LiTS) is of primary importance in diagnosis and treatment of hepatocellular carcinoma. Known automated LiTS methods could not yield satisfactory results for clinical use since they were hard to model flexible tumor shapes and locations. In clinical practice, radiologists usually estimate tumor shape and size by a Response Evaluation Criteria in Solid Tumor (RECIST) mark. Inspired by this, in this paper, we explore a deep learning (DL) based interactive LiTS method, which incorporates guidance from user-provided RECIST marks. Our method takes a three-step framework to predict liver tumor boundaries. Under this architecture, we develop a RECIST mark propagation network (RMP-Net) to estimate RECIST-like marks in off-RECIST slices. We also devise a context-guided boundary-sensitive network (CGBS-Net) to distill tumors' contextual and boundary information from corresponding RECIST(-like) marks, and then predict tumor maps. To further refine the segmentation results, we process the tumor maps using a 3D conditional random field (CRF) algorithm and a morphology hole-filling operation. Verified on two clinical contrast-enhanced abdomen computed tomography (CT) image datasets, our proposed approach can produce promising segmentation results, and outperforms the state-of-the-art interactive segmentation methods.

The liver is a very important and complex organ in our body. Efficient liver segmentation is a very important interesting and challenging task in the field of medical image processing. The abdomen ...

Medical image segmentation is one of the crucial tasks in diagnosis as well as pre-surgery. Recently, deep learning has significantly contributed to improving the efficiency of medical image extraction. The U-Net network has been a favored network model, which has been used as a platform architecture, for medical image segmentation. For the success of these studies, most of these models were primarily focused on the changing of the interconnection between the nodes in the network, and changing the structure of the convolution units. This would result in the ignorance of the output features of convolution units in the nodes. In this study, a Un-Net, an n-fold network architecture, was proposed based on the traditional U-Net. In the Un-Net model, the output features of the convolution units are taken as the skip connection. Therefore, the Un-Net network exploits the output features of the convolution units in the nodes. In this study, we investigated a U2-Net and a U3-Net for segmentation of the liver and liver tumors. Besides, dilated convolution (DC) and dense structure were also used in the nodes of our networks. The efficiency of our models was evaluated on two public datasets: LiTS and 3DIRCADb. The Dice's Similarity Coefficient (DSC) of our proposed models achieved 96.38% for liver segmentation and 73.69% for tumor segmentation on the LiTS dataset. For the 3DIRCADb dataset, the results achieved 96.45% in DSC for the liver segmentation and 73.34% for the tumor segmentation. The experimental results show that our proposed networks achieved better results than the recent networks. And it is convinced that our network would be useful for practical deployments.

Purpose The accurate segmentation of liver and liver tumors from CT images can assist radiologists in decision-making and treatment planning. The contours of liver and liver tumors are currently obtained by manual labeling, which is time-consuming and subjective. Computer-aided segmentation methods have been widely used in the segmentation of liver and liver tumors. However, due to the diversity of shape, volume, and image intensity, the segmentation is still a difficult task. In this study, we present a Spatial Feature Fusion Convolutional Network (SFF-Net) to automatically segment liver and liver tumors from CT images. Methods First, we extract side-outputs at each convolutional block in SFF-Net to make full use of multiscale features. Second, skip-connections are added in the down-sampling phase, therefore, the spatial information can be efficiently transferred to later layers. Third, we present feature fusion blocks (FFBs) to merge spatial features and high-level semantic features from early layers and later layers, respectively. Finally, a fully connected 3D conditional random fields (CRFs) is applied to refine the liver and liver tumor segmentation results. Results We test our method on the MICCAI 2017 Liver Tumor Segmentation (LiTS) challenge dataset. The Dice Global (DG) score, Dice per case (DC) score, Volume Overlap Error (VOE), Average Symmetric Surface Distance (ASSD), and tumor precision score are calculated to evaluate the liver and liver tumor segmentation accuracies. For the liver segmentation, DG is 0.955; DC is 0.937; VOE is 0.106; and ASSD is 3.678. For the tumor segmentation, DG is 0.746; DC is 0.592; VOE is 0.416; ASSD is 1.585 and the tumor precision score is 0.369. Conclusions The SFF-Net learns more spatial information by adding skip-connections and feature fusion blocks. The experiments validate that our method can accurately segment liver and liver tumors from CT images.

Automatic assessing the location and extent of liver and liver tumor is critical for radiologists, diagnosis and the clinical process. In recent years, a large number of variants of U-Net based on Multi-scale feature fusion are proposed to improve the segmentation performance for medical image segmentation. Unlike the previous works which extract the context information of medical image via applying the multi-scale feature fusion, we propose a novel network named Multi-scale Attention Net (MA-Net) by introducing self-attention mechanism into our method to adaptively integrate local features with their global dependencies. The MA-Net can capture rich contextual dependencies based on the attention mechanism. We design two blocks: Position-wise Attention Block (PAB) and Multi-scale Fusion Attention Block (MFAB). The PAB is used to model the feature interdependencies in spatial dimensions, which capture the spatial dependencies between pixels in a global view. In addition, the MFAB is to capture the channel dependencies between any feature map by multi-scale semantic feature fusion. We evaluate our method on the dataset of MICCAI 2017 LiTS Challenge. The proposed method achieves better performance than other state-of-the-art methods. The Dice values of liver and tumors segmentation are 0.960 ± 0.03 and 0.749 ± 0.08 respectively.

Hepatocellular carcinoma currently causes over 800 000 fatalities per year worldwide – and the number of cases is increasing. An early diagnosis and treatment play a crucial role in saving patients’ lives. The purpose of this study is the exploration of a robust and precise computer-aided diagnosis (CAD) method using deep learning algorithms for liver tumor localization and segmentation. The difficulty of liver tumor segmentation lies within the recognition of the contrast between healthy and malignant tissues. This study proposes an implementation of a two-phased multi-scale and multi-resolution training pipeline to perform high accuracy in medical imaging segmentation tasks. For the experiments, the Liver Tumor Segmentation challenge (LiTS) public dataset was used. It contains 131 computed tomography (CT) images, out of which 82% show liver tumors with various shapes of lesion distribution. The final results show a dice per case score of 96.3% for liver segmentation and 72.5% for tumor segmentation when compared to the top LiTS results.

The segmentation of liver tumors is crucial for diagnosis, treatment planning and treatment evaluation. Due to the setbacks that the manual segmentation brings, automatic segmentation has recently gained a lot of attention. In this work, we explore various deep learning based approaches to address automatic liver tumor segmentation. We use the data from the Liver Tumor Segmentation challenge (LiTS). In particular, the considered models here are UNet-based architectures. In addition, we investigate the influence of incorporating extra elements to the pipeline such as attention mechanisms, model ensemble, test-time inference as well as an additional model to reject false positives, over the final performance. The obtained results show that the 3D-UNet architecture, together with ensemble learning methods, performs more accurate predictions than the other examined approaches.

U-Net and a large number of variants of U-Net have been successfully used for liver and liver-tumor segmentation. In this paper, we propose a novel network called quartet attention U-Net (QAU-Net). First, QAU-Net employs quartet attention including four branches to capture inner and cross-dimensional interactions between channels and spatial locations. Secondly, QAU-Net employs long-short skip-connection to instead of the vanilla skip-connection, which avoids the duplicate process of low-resolution information and improves the feature fusion of low-resolution and high-resolution information. We evaluate the proposed method on the public LITS dataset. Experiments demonstrate that QAU-Net has better feature representation and higher liver and liver-tumor segmentation accuracy. The available code of QAU-Net we proposed is opened at https://github.com/15029257158/QAU-Net.

The liver is a common site for the development of primary (i.e., originating from the liver, e.g., hepatocellular carcinoma) or secondary (i.e., spread to the liver, e.g., colorectal cancer) tumor. Due to its complex background, heterogeneous, and diffusive shape, automatic segmentation of tumor remains a challenging task. So far, only the interactive method has been adopted to obtain the acceptable segmentation results of a liver tumor. In this paper, we design an Attention Hybrid Connection Network architecture which combines soft and hard attention mechanism and long and short skip connections. We also propose a cascade network based on the liver localization network, liver segmentation network, and tumor segmentation network to cope with this challenge. Simultaneously, the joint dice loss function is proposed to train the liver localization network to obtain the accurate 3D liver bounding box, and the focal binary cross entropy is used as a loss function to fine-tune the tumor segmentation network for detecting more potentially malignant tumor and reduce false positives. Our framework is trained using the 110 cases in the LiTS dataset and extensively evaluated by the 20 cases in the 3DIRCADb dataset and the 117 cases in the Clinical dataset, which indicates that the proposed method can achieve faster network convergence and accurate semantic segmentation and further demonstrate that the proposed method has a good clinical value.

Liver cancer is one of the most common cancers. Liver tumor segmentation is one of the most important steps in treating liver cancer. Accurate tumor segmentation on computed tomography (CT) images is a challenging task due to the variation of the tumor’s shape, size, and location. To this end, this paper proposes a liver tumor segmentation method on CT volumes using multi-scale candidate generation method (MCG), 3D fractal residual network (3D FRN), and active contour model (ACM) in a coarse-to-fine manner. First, livers are segmented using 3D U-Net and then MCG is performed on these liver regions for obtaining tumor candidates (all superpixel blocks). Second, 3D FRN is proposed to further determine tumor regions, which is considered as coarse segmentation results. Finally, the ACM is used for tumor segmentation refinement. The proposed 3D MCG-FRN + ACM is trained using the 110 cases in the LiTS dataset and evaluated on a public liver tumor dataset of the 3DIRCADb with dice per case of 0.67. The experimentations and comparisons demonstrate the performance advantage of the 3D MCG-FRN + ACM compared to other segmentation methods.

Liver tumor segmentation is the most significant and challenging task due to high variation in size, location, depth of tumor and intimate boundaries of other organs around the liver. Computed Tomography (CT) scans of the liver differ in size and other parameters, including the number of layers in each CT scan. Thus, liver CT scans from different parameters make it a challenging task. Thus, we propose an efficient liver tumor segmentation method with Mask Region-Convolutional Neural Network (Mask-RCNN) with resnet 101 as the backboneto come upwith these challenges. The proposed method based on the Mask-RCNN approach effectively identifies tumor in liver through generating proposals about the tumor region. The proposed method converts CT volumes to normalized CT image slices in preprocessing step to get a cardinal outline of liver. Then normalized CT images are feed to resnet 101 for feature extraction. Then finally, Mask-RCNN is appliedto segment tumors in the liver. Our experiment dataset comprises 130 CT scans of different patients taken from different clinical sites, and it is freely available atLiTS challenge website. The proposed method is trained on converted CT image slices. Our proposed method hasimproved the segmentation rate by providing segmentation accuracy with average dice coefficient, JC, VOE and RVD of 0.95, 0.41, 0.12, and 0.15, respectively and lesser training time due to converted CT image slices instead of training on CT volumes.

Automatic liver tumor segmentation from 3D Computed Tomography (CT) is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate liver tumor segmentation remains challenging due to the large variability of tumor sizes and inhomogeneous texture. Recent advances based on Fully Convolutional Network (FCN) in liver tumor segmentation draw on success of learning discriminative multi-level features. In this paper, we propose a Deep Attentive Refinement Network (DARN) for improved liver tumor segmentation from CT volumes by fully exploiting both low and high level features embedded in different layers of FCN. Different from existing works, we exploit attention mechanism to leverage the relation of different levels of features encoded in different layers of FCN. Specifically, we introduce a Semantic Attention Refinement (SemRef) module to selectively emphasize global semantic information in low level features with the guidance of high level ones, and a Spatial Attention Refinement (SpaRef) module to adaptively enhance spatial details in high level features with the guidance of low level ones. We evaluate our network on the public MICCAI 2017 Liver Tumor Segmentation Challenge dataset (LiTS dataset) and it achieves state-of-the-art performance. The proposed refinement modules are an effective strategy to exploit multi-level features and has great potential to generalize to other medical image segmentation tasks.

Liver cancer is a common malignant tumor and one of the main causes of cancer deaths in the world. Accurately segmenting liver tumor regions from the liver has a very important guiding role for doctors in disease diagnosis and surgical planning. Thus, the method of automated segmentation of liver tumors has important value for clinical diagnosis and treatment. This paper proposes a method that combines fully convolutional neural networks based on two-dimensional convolution and those based on three-dimensional convolution. The results show that the liver tumor segmentation effect of this method is much better than that of only using single two-dimensional convolutional neural networks or three-dimensional convolutional neural networks.

Automatic extraction of liver and tumor from CT volumes is a challenging task due to their heterogeneous and diffusive shapes. Recently, 2D and 3D deep convolutional neural networks have become popular in medical image segmentation tasks because of the utilization of large labeled datasets to learn hierarchical features. However, 3D networks have some drawbacks due to their high cost on computational resources. In this paper, we propose a 3D hybrid residual attention-aware segmentation method, named RA-UNet, to precisely extract the liver volume of interests (VOI) and segment tumors from the liver VOI. The proposed network has a basic architecture as a 3D U-Net which extracts contextual information combining low-level feature maps with high-level ones. Attention modules are stacked so that the attention-aware features change adaptively as the network goes "very deep" and this is made possible by residual learning. This is the first work that an attention residual mechanism is used to process medical volumetric images. We evaluated our framework on the public MICCAI 2017 Liver Tumor Segmentation dataset and the 3DIRCADb dataset. The results show that our architecture outperforms other state-of-the-art methods. We also extend our RA-UNet to brain tumor segmentation on the BraTS2018 and BraTS2017 datasets, and the results indicate that RA-UNet achieves good performance on a brain tumor segmentation task as well.

Automatic liver tumor detection is an important task and is more challenging in Computed Tomography (CT) due to its size, location, and irregular shape. Detection of small tumors in the liver is problematic because the liver area is mostly covered by the right rib cage. Recent work employs two-stage object detectors that are trained with bounding box annotations. In our work, we apply a simpler and faster one stage detector RetinaNet for localization of liver tumor on LiTS17, and our proposed method precisely detects one or more tumors. This model resolves the class imbalance problem between foreground and background by evaluating the focal loss. Our results on liver tumor CT images from LiTS17 dataset yields strong detection and scored mAP of 96%.

Accurate liver tumor segmentation without contrast agents (non-enhanced images) avoids the contrast-agent-associated time-consuming and high risk, which offers radiologists quick and safe assistance to diagnose and treat the liver tumor. However, without contrast agents enhancing, the tumor in liver images presents low contrast and even invisible to naked eyes. Thus the liver tumor segmentation from non-enhanced images is quite challenging. We propose a Weakly-Supervised Teacher-Student network (WSTS) to address the liver tumor segmentation in non-enhanced images by leveraging additional box-level-labeled data (labeled with a tumor bounding-box). WSTS deploys a weakly-supervised teacher-student framework (TCH-ST), namely, a Teacher Module learns to detect and segment the tumor in enhanced images during training, which facilitates a Student Module to detect and segment the tumor in non-enhanced images independently during testing. To detect the tumor accurately, the WSTS proposes a Dual-strategy DRL (DDRL), which develops two tumor detection strategies by creatively introducing a relative-entropy bias in the DRL. To accurately predict a tumor mask for the box-level-labeled enhanced image and thus improve tumor segmentation in non-enhanced images, the WSTS proposes an Uncertainty-Sifting Self-Ensembling (USSE). The USSE exploits the weakly-labeled data with self-ensembling and evaluates the prediction reliability with a newly-designed Multi-scale Uncertainty-estimation. WSTS is validated with a 2D MRI dataset, where the experiment achieves 83.11% of Dice and 85.12% of Recall in 50 patient testing data after training by 200 patient data (half amount data is box-level-labeled). Such a great result illustrates the competence of WSTS to segment the liver tumor from non-enhanced images. Thus, WSTS has excellent potential to assist radiologists by liver tumor segmentation without contrast-agents.

Accurate segmentation of liver tumors is an important guarantee for the success of liver cancer surgery, where convolutional network has been a type of popular method. However, the performance of the traditional convolutional network is limited by the network depth. To improve the accuracy of liver tumor segmentation, we propose a cascaded deep fully convolutional network (DFCN) which uses ResNet as the basis network followed by side output layer in the upsampling stage to fuse multi-scale image features. For better localizing the liver tumors, the segmentation result is further refined by a fully connected conditional random field. Experimental results show that the proposed method achieves higher segmentation accuracy than several state-of-the-art methods.

Liver tumor segmentation from computed tomography images is an essential task for the automated diagnosis and treatment of liver cancer. However, such task is di cult due to the variability of morphologies, di use boundaries, heterogeneous densities, and sizes of the lesions. In this work we develop a new system designed for the segmentation of tumors from images acquired by computed tomography, the proposed system uses a network based on convolutional neural networks (CNN). The results are compared with a segmentation carried out by medical experts.

The main cause of death related to cancer worldwide is from hepatic cancer. Detection of hepatic cancer early using computed tomography (CT) could prevent millions of patients&rsquo, death every year. However, reading hundreds or even tens of those CT scans is an enormous burden for radiologists. Therefore, there is an immediate need is to read, detect, and evaluate CT scans automatically, quickly, and accurately. However, liver segmentation and extraction from the CT scans is a bottleneck for any system, and is still a challenging problem. In this work, a deep learning-based technique that was proposed for semantic pixel-wise classification of road scenes is adopted and modified to fit liver CT segmentation and classification. The architecture of the deep convolutional encoder&ndash, decoder is named SegNet, and consists of a hierarchical correspondence of encode&ndash, decoder layers. The proposed architecture was tested on a standard dataset for liver CT scans and achieved tumor accuracy of up to 99.9% in the training phase.

Background Malignant liver tumor is one of the main causes of human death. In order to help physician better diagnose and make personalized treatment schemes, in clinical practice, it is often necessary to segment and visualize the liver tumor from abdominal computed tomography images. Due to the large number of slices in computed tomography sequence, developing an automatic and reliable segmentation method is very favored by physicians. However, because of the noise existed in the scan sequence and the similar pixel intensity of liver tumors with their surrounding tissues, besides, the size, position and shape of tumors also vary from one patient to another, automatic liver tumor segmentation is still a difficult task. Results We perform the proposed algorithm to the Liver Tumor Segmentation Challenge dataset and evaluate the segmentation results. Experimental results reveal that the proposed method achieved an average Dice score of 68.4% for tumor segmentation by using the designed network, and ASD, MSD, VOE and RVD improved from 27.8 to 21, 147 to 124, 0.52 to 0.46 and 0.69 to 0.73, respectively after performing adversarial training strategy, which proved the effectiveness of the proposed method. Conclusions The testing results show that the proposed method achieves improved performance, which corroborated the adversarial training based strategy can achieve more accurate and robustness results on liver tumor segmentation task.

Channel attention, a channel-wise method often used in computer vision tasks, including liver tumor segmentation tasks, is able to model the channel relationship to augment the representation ability of feature maps. Channel attention could adaptively generate channel-wise responses using global pooling, which aggregates spatial information roughly. Actually, global pooling may introduce the loss of fine information, which is vital for segmentation tasks. Hence, we rethink the problem and propose the channel attention with adaptive global pooling(short for CAAGP), which preserves spatial and fine-grained information for liver tumor segmentation tasks when channel attention is generated. The model consists of three main parts, including improved self-attention, adaptive global pooling and responses generation modules. Self-attention achieves excellent performance in the computing of the spatial attention, while introducing serious calculation and memory burdens. In order to remedy these burdens, we improve self-attention and consider aggregating spatial information from x and y directions respectively. Extensive experiments have been conducted to verify the effectiveness of our proposed method. Our CAAGP outperforms other attention mechanisms significantly in liver tumor segmentation, especially for tumors with small size.

Segmenting liver tumors from computed tomography (CT) images plays a very important role in computer-aided diagnosis, surgical planning, and treatment monitoring. However, accurate and robust segmentation of the tumors remains a challenging issue, due to low contrast and vague boundaries between the tumors and surrounding tissues as well as the wide variations of the tumors in intensity, shape, and location across patients. In this paper, we developed an effective method for liver tumor segmentation with adaptive region growing and graph cuts. First, initial segmentation results for liver tumors and the regions of interest (ROIs) that contain the tumors are extracted by adaptive region growing with a manual selected seed specified for each tumor region. Then, the ROIs are enhanced by Gaussian fitting based nonlinear mapping according to the intensity distributions of the initially segmented tumor regions. Finally, the enhanced information combined with gradient information is integrated into graph cuts to extract the tumors from the ROIs effectively and accurately. The method is non-sensitive to noise and does not involve a pre-segmentation of liver or a complicated and tedious procedure of training. Results on 3Dircadb dataset demonstrate that the method achieves much better comprehensive performance on liver tumor segmentation compared with many art-of-state methods and has a huge advantage in segmenting the tumors with low contrast, small size, and weak boundaries.

Smart multimedia-based medical analytics and decision-making systems are of prime importance in the healthcare sector. Liver cancer is commonly stated to be the sixth most widely diagnosed cancer and requires an early diagnosis to help with treatment planning. Liver tumors have similar intensity levels and contrast as compared to neighboring tissues. Similarly, irregular tumor shapes are another major issue that depends on the cancer stage and tumor type. Generally, liver tumor segmentation comprises two steps: the first one involves liver identification, and the second stage involves tumor segmentation. This research work performed tumor segmentation directly from a CT scan, which tends to be more difficult and important. We propose an efficient algorithm that employs multi-scale parallel convolution blocks (MPCs) and Res blocks based on residual learning. The fundamental idea of utilizing multi-scale parallel convolutions of varying filter sizes in MPCs is to extract multi-scale features for different tumor sizes. Moreover, the utilization of residual connections and residual blocks helps to extract rich features with a reduced number of parameters. Moreover, the proposed work requires no post-processing techniques to refine the segmentation. The proposed work was evaluated using the 3DIRCADb dataset and achieved a Dice score of 77.15% and 93% accuracy.

Liver and hepatic tumor segmentation is a crucial yet challenging step during the screening and diagnosis of liver illnesses. Currently, accurate 3D segmentation deep learning models are large, while the smaller 2D ones are generally less accurate due to their small receptive fields. To reduce model sizes and increase segmentation accuracy, we propose 2.5D Perpendicular-UNet to fuse the segmentation results of three perpendicular 2.5D Res-UNets in the task of liver and hepatic tumor segmentation. Data augmentation, loss functions, and post-processing steps are customizable with our model. With a larger receptive field in three dimensions, our model outperforms 2D UNet models in accuracy, achieving 0.962 and 0.735 Dice scores for liver and tumor segmentation on the liver tumor segmentation dataset. Being smaller than 3D models, our 2.5D P-UNet trains using less data and GPU memory. This enables it to be deployed on low-configuration hardware, expanding its potential use.

Automated segmentation of liver tumors in contrast-enhanced abdominal computed tomography (CT) scans is essential in assisting medical professionals to evaluate tumor development and make fast therapeutic schedule. Although deep convolutional neural networks (DCNNs) have contributed many breakthroughs in image segmentation, this task remains challenging, since 2D DCNNs are incapable of exploring the inter-slice information and 3D DCNNs are too complex to be trained with the available small dataset. In this paper, we propose the light-weight hybrid convolutional network (LW-HCN) to segment the liver and its tumors in CT volumes. Instead of combining a 2D and a 3D networks for coarse-to-fine segmentation, LW-HCN has a encoder-decoder structure, in which 2D convolutions used at the bottom of the encoder decreases the complexity and 3D convolutions used in other layers explore both spatial and temporal information. To further reduce the complexity, we design the depthwise and spatiotemporal separate (DSTS) factorization for 3D convolutions, which not only reduces parameters dramatically but also improves the performance. We evaluated the proposed LW-HCN model against several recent methods on the LiTS and 3D-IRCADb datasets and achieved, respectively, the Dice per case of 73.0% and 94.1% for tumor segmentation, setting a new state of the art.

In this work, a liver tumor segmentation approach is proposed using triplanar views, consisting of axial, sagittal and coronal planes. These three planes are integrated as the input streams for the Convolutional Neural Network (ConvNet). The main objective of including the input patches from triplanar views is to enrich the ConvNet with more context information to aid in the classification of liver tumor. The input patches are extracted from liver Computed Tomography (CT) dataset using center pixel of interests from the triplanar views. These patches are fed into the proposed Triplanar ConvNet. Pilot experiments were conducted to evaluate the efficiency of using triplanar views in comparisons with single-view from axial plane. The preliminary results achieved in this study revealed that triplanar approach yield better results than using patches only from single-view.

Using deep learning for Medical Images Diagnosis automatically is a new trend in recent years. Concretely, the fundamental step in these studies is the automatic segmentation system for human organ, that has the benefit of accuracy in the diagnosis process for medical images (CT images). Traditionally, if there is no module of automatic segmentation system, this process has to be performed by the experience of specialized physicians. More importantly, this process takes much time of physicians, while the automatic segmentation system can alternative efficiently. However, the accuracy and responsiveness are the challenges for a segmentation system with a small organ or small tissue, i.e., a liver tumor, because of the lack of data for deep learning. This paper highlights some augmentation and preprocessing techniques from a small dataset of medical images. We propose a method to improve the module of automatic segmentation, in particular, liver tumor segmentation. For the augmented dataset from 3D Image Reconstruction for Comparison of Algorithm Database (3D-IRCADb), we achieve the dice score of 94.58% for liver segmentation and 45.87% for liver tumor. Furthermore, with a real dataset from a patient, the dice score of our system is over 78% for liver segmentation.

Accurate segmentation of liver and tumors from abdominal computer tomography (CT) scans is critical for computer-assisted diagnosis and therapy. In this paper, we proposed a graph cuts based segmentation approach for fast automatic liver segmentation and semi-automatic liver tumor segmentation from CT images. Only one seed point for each tumor was selected manually. Liver/tumor volumes of interest (VOI) were extracted automatically and supervoxels were employed to reduce the computational cost. Intensity and spatial information were incorporated into the graph cuts algorithm. Experimental results demonstrate that the proposed method can detect the liver and tumor accurately with significant reduction of processing time.

As the largest glandular organ in the human body, liver has a large number of blood vessels and is connected with many important organs, such as spleen, pancreas and gallbladder, etc. The segmentation of liver and its lesions on medical images can help doctors accurately diagnose liver tumor and assess the probability of subsequent deterioration of the patient. Generally speaking, it is not only subjective but also wastes time if doctors rely on experience to manually analyze liver CT images. Therefore, it has been extensively studied in recent years. The segmentation of liver lesions is a kind of challenging task due to the low contrast ratio between the liver, lesions and nearby organs. To this end, we proposed to use the DeepLabV3+ semantic segmentation model based on the tensorflow architecture to segment the CT image of liver and locate the lesion positions. It combined deep convolutional neural networks (DCNNs) and probabilistic graphical model (DenseCRFs) and has been proven to have very good performance in a variety of computer vision tasks.

International audience; Toward an efficient clinical management of hepatocellular carcinoma (HCC), we propose a classification framework dedicated to tumor necrosis rate estimation from dynamic contrast-enhanced CT scans. Based on machine learning, it requires weak interaction efforts to segment healthy, active and necrotic liver tissues. Our contributions are two-fold. First, we apply random forest (RF) on supervoxels using multi-phase supervoxel-based features that discriminate tissues based on their dynamic in response to contrast agent injection. Second, we extend this technique in a hierarchical multi-scale fashion to deal with multiple spatial extents and appearance heterogeneity. It translates in an adaptive data sampling scheme combining RF and hierarchical multi-scale tree resulting from recursive supervoxel decomposition. By concatenating multi-phase features across the hierarchical multi-scale tree to describe leaf supervoxels, we enable RF to automatically infer the most informative scales without defining any explicit rules on how to combine them. Assessment on clinical data confirms the benefits of multi-phase information embedded in a multi-scale supervoxel representation for HCC tumor segmentation. Dedicated but not limited only to HCC management, both contributions reach further steps toward more accurate multi-label tissue classification.

International audience; To reduce the manual labor time and provide the accuracy of liver tumor segmentation in the treatment planning of radiofrequency ablation (RFA), a novel method for liver tumor image segmentation by nonlocal active contours is proposed in this paper. A multi Gabor feature map of the liver tumor image is computed to describe the homogeneity of patches in a nonlocal way, and the nonlocal comparisons between pairs of patches are used to calculate the active contour energy. The whole energy function is minimized via a level set method to give the final segmentation. The experimental results indicate that the proposed method leads to good liver tumor segmentation with a good robustness to initialization condition. Experiment results show the proposed method can provide segmentation close to manual results, with the mean overlap error (OE) less than 23.86%

International audience; Pre-operative locoregional treatments (PLT) delay the tumor progression by necrosis for patients with hepato-cellular carcinoma (HCC). Toward an efficient evaluation of PLT response, we address the estimation of liver tumor necrosis (TN) from CT scans. The TN rate could shortly supplant standard criteria (RECIST, mRECIST, EASL or WHO) since it has recently shown higher correlation to survival rates. To overcome the inter-expert variability induced by visual qualitative assessment, we propose a semi-automatic method that requires weak interaction efforts to segment parenchyma, tumoral active and necrotic tissues. By combining SLIC supervoxels and random decision forest, it involves discriminative multi-phase cluster-wise features extracted from registered dynamic contrast-enhanced CT scans. Quantitative assessment on expert groundtruth annotations confirms the benefits of exploiting multi-phase information from semantic regions to accurately segment HCC liver tumors.

The delineation of tumor boundaries is an essential task for the diagnosis and follow-up of liver cancer. However accurate segmentation remains challenging due to tissue inhomogeneity and high variability in tumor appearance. In this paper, we propose a semi-automatic liver tumor segmentation method that combines a deformable model with a machine learning mechanism. More precisely, segmentation is performed by an MRF-based omni-directional deformable surface model that uses image information together with a two-class (tumor, non-tumor) voxel classification map. The classification map is produced by a kernel SVM classifier trained on texture features, as well as intensity mean and variance. The segmentation method is validated on a metastatic tumor dataset consisting of 27 tumors across a set of abdominal CT images, using leave-one-out validation. Compared to pure voxel and gradient approaches, our method achieves better performance in terms of mean distance and Dice scores on the group of 27 liver tumors and can deal with highly pathological cases.

In computed tomography of liver tumors there is often heterogeneous density, weak boundaries, and the liver tumors are surrounded by other abdominal structures with similar densities. These pose limitations to accurate the hepatic tumor segmentation. We propose a level set model incorporating likelihood energy with the edge energy. The minimization of the likelihood energy approximates the density distribution of the target and the multimodal density distribution of the background that can have multiple regions. In the edge energy formulation, our edge detector preserves the ramp associated with the edges for weak boundaries. We compared our approach to the Chan-Vese and the geodesic level set models and the manual segmentation performed by clinical experts. The Chan-Vese model was not successful in segmenting hepatic tumors and our model outperformed the geodesic level set model. Our results on 18 clinical datasets showed that our algorithm had a Jaccard distance error of 14.4 ± 5.3%, relative volume difference of -8.1 ± 2.1%, average surface distance of 2.4 ± 0.8 mm, RMS surface distance of 2.9 ± 0.7 mm, and the maximum surface distance of 7.2 ± 3.1 mm.

Robust and efficient liver and tumor segmentation segmentation tools from CT images are important for clinical decision-making in liver treatment planning and response evaluation. In this work, we report recent advances in an ongoing project Liver Workbench which aims to provide a suite of tools for the segmentation segmentation, quantification and modeling of various objects in CT images such as the liver, its vessels and tumors. Firstly, a liver segmentation segmentation approach is described. It registers a liver mesh model model to actual image features by adopting noise-insensitive flipping-free mesh deformations. Next, a propagation learning approach is incorporated into a semi-automatic classification method for robust segmentation segmentation of liver tumors based on liver ROI obtained. Finally, an unbiased probabilistic liver atlas construction technique is adopted to embody the shape and intensity variation to constrain liver segmentation segmentation. We also report preliminary experimental results.

Low contrast between tumor and healthy liver tissue is one of the significant and challenging features among others in the automated tumor delineation process. In this paper we propose kernel based clustering algorithms that incorporate Tsallis entropy to resolve long range interactions between tumor and healthy tissue intensities. This paper reports the algorithm and its encouraging results of evaluation with MICCAI liver Tumor Segmentation Challenge 08 (LTS08) dataset. Work in progress involves incorporating additional features and expert knowledge into clustering algorithm to improve the accuracy.

The key challenge in tumor segmentation is to determine their exact location and volume. Difficulties arise because of low intensity boundaries, varying shapes and sizes. Furthermore, tumors can be located everywhere in the liver. Interactive segmentation methods seem to be the most appropriate in terms of reliability and robustness. In this work, we use a graph-cut based method to interactively segment tumors. However, complexity of the underlying graphs is enormous for clinical 3D datasets. We propose a method to identify automatically a region of interest using a coarse resolution image, which is then used to construct a reduced graph for final segmentation in the original image in full resolution. We compared our results to ground truth segmentations done by experts. Our results suggest that accuracy is comparable to other approaches. The average overlap was 80%, the average surface distance 0.73 mm and the average maximum surface distance 5.31 mm.rl

Manual delineations by experts are often used as reference standards for validating segmentation algorithms, although it is well known that they always show some degree of variability. Our goal is to estimate the effects of using a limited number of expert segmentations. Given ten manual delineations of 13 liver tumors, we analyzed the volume error made by randomly selecting subsets of the ten segmentations compared to the complete set. We found that when using just one segmentation the expected error was 17% with a maximum of 35%. This means that it is questionable whether a comparison with a single reference allows a reliable validation. When three segmentations are chosen, the error is halved, so this might be a reasonable compromise between accuracy and viability of evaluation studies.

Liver and liver tumor segmentations are very important for a contemporary planning system of liver surgery. However, both liver and liver tumor segmentations are a grand challenge in clinics. In this paper, we proposed an integrated paradigm with fuzzy c-means (FCM) and level set method for computerized liver tumor segmentation. An innovation in this paper is to interface the initial segmentations from FCM and the fine delineation with level set method by morphological operations. The results in real medical images confirm the effectiveness of such integrated paradigm for liver tumor segmentation.