A Hessian-based filter for vascular segmentation of noisy hepatic CT scans

Vascular liver segmentation: a narrative review on methods and new insights brought by artificial intelligence

Liver vessel segmentation from routinely performed medical imaging is a useful tool for diagnosis, treatment planning and delivery, and prognosis evaluation for many diseases, particularly liver cancer. A precise representation of liver anatomy is crucial to define the extent of the disease and, when suitable, the consequent resective or ablative procedure, in order to guarantee a radical treatment without sacrificing an excessive volume of healthy liver. Once mainly performed manually, with notable cost in terms of time and human energies, vessel segmentation is currently realized through the application of artificial intelligence (AI), which has gained increased interest and development of the field. Many different AI-driven models adopted for this aim have been described and can be grouped into different categories: thresholding methods, edge- and region-based methods, model-based methods, and machine learning models. The latter includes neural network and deep learning models that now represent the principal algorithms exploited for vessel segmentation. The present narrative review describes how liver vessel segmentation can be realized through AI models, with a summary of model results in terms of accuracy, and an overview on the future progress of this topic.

Pulmonary vessel volume in idiopathic pulmonary fibrosis compared with healthy controls aged > 50 years

Idiopathic pulmonary fibrosis (IPF) is characterised by progressive fibrosing interstitial pneumonia with an associated irreversible decline in lung function and quality of life. IPF prevalence increases with age, appearing most frequently in patients aged > 50 years. Pulmonary vessel-like volume (PVV) has been found to be an independent predictor of mortality in IPF and other interstitial lung diseases, however its estimation can be impacted by artefacts associated with image segmentation methods and can be confounded by adjacent fibrosis. This study compares PVV in IPF patients (N = 21) with PVV from a healthy cohort aged > 50 years (N = 59). The analysis includes a connected graph-based approach that aims to minimise artefacts contributing to calculation of PVV. We show that despite a relatively low extent of fibrosis in the IPF cohort (20% of the lung volume), PVV is 2-3 times higher than in controls. This suggests that a standardised method to calculate PVV that accounts for tree connectivity could provide a promising tool to provide early diagnostic or prognostic information in IPF patients and other interstitial lung disease.

Robust Deep 3D Blood Vessel Segmentation Using Structural Priors

Deep learning has enabled significant improvements in the accuracy of 3D blood vessel segmentation. Open challenges remain in scenarios where labeled 3D segmentation maps for training are severely limited, as is often the case in practice, and in ensuring robustness to noise. Inspired by the observation that 3D vessel structures project onto 2D image slices with informative and unique edge profiles, we propose a novel deep 3D vessel segmentation network guided by edge profiles. Our network architecture comprises a shared encoder and two decoders that learn segmentation maps and edge profiles jointly. 3D context is mined in both the segmentation and edge prediction branches by employing bidirectional convolutional long-short term memory (BCLSTM) modules. 3D features from the two branches are concatenated to facilitate learning of the segmentation map. As a key contribution, we introduce new regularization terms that: a) capture the local homogeneity of 3D blood vessel volumes in the presence of biomarkers; and b) ensure performance robustness to domain-specific noise by suppressing false positive responses. Experiments on benchmark datasets with ground truth labels reveal that the proposed approach outperforms state-of-the-art techniques on standard measures such as DICE overlap and mean Intersection-over-Union. The performance gains of our method are even more pronounced when training is limited. Furthermore, the computational cost of our network inference is among the lowest compared with state-of-the-art.

GCA-Net: global context attention network for intestinal wall vascular segmentation

PURPOSE

Precise segmentation of intestinal wall vessels is vital to colonic perforation prevention. However, there are interferences such as gastric juice in the vessel image of the intestinal wall, especially vessels and the mucosal folds are difficult to distinguish, which easily lead to mis-segmentation. In addition, the insufficient feature extraction of intricate vessel structures may leave out information of tiny vessels that result in rupture. To overcome these challenges, an effective network is proposed for segmentation of intestinal wall vessels.

METHODS

A global context attention network (GCA-Net) that employs a multi-scale fusion attention (MFA) module is proposed to adaptively integrate local and global context information to improve the distinguishability of mucosal folds and vessels, more importantly, the ability to capture tiny vessels. Also, a parallel decoder is used to introduce a contour loss function to solve the blurry and noisy blood vessel boundaries.

RESULTS

Extensive experimental results demonstrate the superiority of the GCA-Net, with accuracy of 94.84%, specificity of 97.89%, F1-score of 73.80%, AUC of 96.30%, and MeanIOU of 76.46% in fivefold cross-validation, exceeding the comparison methods. In addition, the public dataset DRIVE is used to verify the potential of GCA-Net in retinal vessel image segmentation.

CONCLUSION

A novel network for segmentation of intestinal wall vessels is developed, which can suppress interferences in intestinal wall vessel images, improve the discernibility of blood vessels and mucosal folds, enhance vessel boundaries, and capture tiny vessels. Comprehensive experiments prove that the proposed GCA-Net can accurately segment the intestinal wall vessels.

Attention-Guided Deep Neural Network With Multi-Scale Feature Fusion for Liver Vessel Segmentation

Liver vessel segmentation is fast becoming a key instrument in the diagnosis and surgical planning of liver diseases. In clinical practice, liver vessels are normally manual annotated by clinicians on each slice of CT images, which is extremely laborious. Several deep learning methods exist for liver vessel segmentation, however, promoting the performance of segmentation remains a major challenge due to the large variations and complex structure of liver vessels. Previous methods mainly using existing UNet architecture, but not all features of the encoder are useful for segmentation and some even cause interferences. To overcome this problem, we propose a novel deep neural network for liver vessel segmentation, called LVSNet, which employs special designs to obtain the accurate structure of the liver vessel. Specifically, we design Attention-Guided Concatenation (AGC) module to adaptively select the useful context features from low-level features guided by high-level features. The proposed AGC module focuses on capturing rich complemented information to obtain more details. In addition, we introduce an innovative multi-scale fusion block by constructing hierarchical residual-like connections within one single residual block, which is of great importance for effectively linking the local blood vessel fragments together. Furthermore, we construct a new dataset containing 40 thin thickness cases (0.625 mm) which consist of CT volumes and annotated vessels. To evaluate the effectiveness of the method with minor vessels, we also propose an automatic stratification method to split major and minor liver vessels. Extensive experimental results demonstrate that the proposed LVSNet outperforms previous methods on liver vessel segmentation datasets. Additionally, we conduct a series of ablation studies that comprehensively support the superiority of the underlying concepts.

Liver vessel segmentation based on inter-scale V-Net

Segmentation and visualization of liver vessel is a key task in preoperative planning and computer-aided diagnosis of liver diseases. Due to the irregular structure of liver vessel, accurate liver vessel segmentation is difficult. This paper proposes a method of liver vessel segmentation based on an improved V-Net network. Firstly, a dilated convolution is introduced into the network to make the network can still enlarge the receptive field without reducing down-sampling and save detailed spatial information. Secondly, a 3D deep supervision mechanism is introduced into the network to speed up the convergence of the network and help the network learn semantic features better. Finally, inter-scale dense connections are designed in the decoder of the network to prevent the loss of high-level semantic information during the decoding process and effectively integrate multi-scale feature information. The public datasets 3Dircadb were used to perform liver vessel segmentation experiments. The average dice and sensitivity of the proposed method reached 71.6 and 75.4%, respectively, which are higher than those of the original network. The experimental results show that the improved V-Net network can automatically and accurately segment labeled or even other unlabeled liver vessels from the CT images.

AAR-LN-DQ: Automatic anatomy recognition based disease quantification in thoracic lymph node zones via FDG PET/CT images without Nodal Delineation

PURPOSE

The derivation of quantitative information from medical images in a practical manner is essential for quantitative radiology (QR) to become a clinical reality, but still faces a major hurdle because of image segmentation challenges. With the goal of performing disease quantification in lymph node (LN) stations without explicit nodal delineation, this paper presents a novel approach for disease quantification (DQ) by automatic recognition of LN zones and detection of malignant lymph nodes within thoracic LN zones via positron emission tomography/computed tomography (PET/CT) images. Named AAR-LN-DQ, this approach decouples DQ methods from explicit nodal segmentation via an LN recognition strategy involving a novel globular filter and a deep neural network called SegNet.

METHOD

The methodology consists of four main steps: (a) Building lymph node zone models by automatic anatomy recognition (AAR) method. It incorporates novel aspects of model building that relate to finding an optimal hierarchy for organs and lymph node zones in the thorax. (b) Recognizing lymph node zones by the built lymph node models. (c) Detecting pathologic LNs in the recognized zones by using a novel globular filter (g-filter) and a multi-level support vector machine (SVM) classifier. Here, we make use of the general globular shape of LNs to first localize them and then use a multi-level SVM classifier to identify pathologic LNs from among the LNs localized by the g-filter. Alternatively, we designed a deep neural network called SegNet which is trained to directly recognize pathologic nodes within AAR localized LN zones. (d) Disease quantification based on identified pathologic LNs within localized zones. A fuzzy disease map is devised to express the degree of disease burden at each voxel within the identified LNs to simultaneously handle several uncertain phenomena such as PET partial volume effects, uncertainty in localization of LNs, and gradation of disease content at the voxel level. We focused on the task of disease quantification in patients with lymphoma based on PET/CT acquisitions and devised a method of evaluation. Model building was carried out using 42 near-normal patient datasets via contrast-enhanced CT examinations of their thorax. PET/CT datasets from an additional 63 lymphoma patients were utilized for evaluating the AAR-LN-DQ methodology. We assess the accuracy of the three main processes involved in AAR-LN-DQ via fivefold cross validation: lymph node zone recognition, abnormal lymph node localization, and disease quantification.

RESULTS

The recognition and scale error for LN zones were 12.28 mm ± 1.99 and 0.94 ± 0.02, respectively, on normal CT datasets. On abnormal PET/CT datasets, the sensitivity and specificity of pathologic LN recognition were 84.1% ± 0.115 and 98.5% ± 0.003, respectively, for the g-filter-SVM strategy, and 91.3% ± 0.110 and 96.1% ± 0.016, respectively, for the SegNet method. Finally, the mean absolute percent errors for disease quantification of the recognized abnormal LNs were 8% ± 0.09 and 14% ± 0.10 for the g-filter-SVM method and the best SegNet strategy, respectively.

CONCLUSIONS

Accurate disease quantification on PET/CT images without performing explicit delineation of lymph nodes is feasible following lymph node zone and pathologic LN localization. It is very useful to perform LN zone recognition by AAR as this step can cover most (95.8%) of the abnormal LNs and drastically reduce the regions to search for abnormal LNs. This also improves the specificity of deep networks such as SegNet significantly. It is possible to utilize general shape information about LNs such as their globular nature via g-filter and to arrive at high recognition rates for abnormal LNs in conjunction with a traditional classifier such as SVM. Finally, the disease map concept is effective for estimating disease burden, irrespective of how the LNs are identified, to handle various uncertainties without having to address them explicitly one by one.

Automatic liver vessel segmentation using 3D region growing and hybrid active contour model

This paper proposes a new automatic method for liver vessel segmentation by exploiting intensity and shape constraints of 3D vessels. The core of the proposed method is to apply two different strategies: 3D region growing facilitated by bi-Gaussian filter for thin vessel segmentation, and hybrid active contour model combined with K-means clustering for thick vessel segmentation. They are then integrated to generate final segmentation results. The proposed method is validated on abdominal computed tomography angiography (CTA) images, and obtains an average accuracy, sensitivity, specificity, Dice, Jaccard, and RMSD of 98.2%, 68.3%, 99.2%, 73.0%, 66.1%, and 2.56 mm, respectively. Experimental results show that our method is capable of segmenting complex liver vessels with more continuous and complete thin vessel details, and outperforms several existing 3D vessel segmentation algorithms.

Combining deep learning with anatomical analysis for segmentation of the portal vein for liver SBRT planning

Automated segmentation of the portal vein (PV) for liver radiotherapy planning is a challenging task due to potentially low vasculature contrast, complex PV anatomy and image artifacts originated from fiducial markers and vasculature stents. In this paper, we propose a novel framework for automated segmentation of the PV from computed tomography (CT) images. We apply convolutional neural networks (CNNs) to learn the consistent appearance patterns of the PV using a training set of CT images with reference annotations and then enhance the PV in previously unseen CT images. Markov random fields (MRFs) were further used to smooth the results of the enhancement of the CNN enhancement and remove isolated mis-segmented regions. Finally, CNN-MRF-based enhancement was augmented with PV centerline detection that relied on PV anatomical properties such as tubularity and branch composition. The framework was validated on a clinical database with 72 CT images of patients scheduled for liver stereotactic body radiation therapy. The obtained accuracy of the segmentation was [Formula: see text] 0.83 and [Formula: see text] 1.08 mm in terms of the median Dice coefficient and mean symmetric surface distance, respectively, when segmentation is encompassed into the PV region of interest. The obtained results indicate that CNNs and anatomical analysis can be used for the accurate segmentation of the PV and potentially integrated into liver radiation therapy planning.

Automated mediastinal lymph node detection from CT volumes based on intensity targeted radial structure tensor analysis

This paper presents a local intensity structure analysis based on an intensity targeted radial structure tensor (ITRST) and the blob-like structure enhancement filter based on it (ITRST filter) for the mediastinal lymph node detection algorithm from chest computed tomography (CT) volumes. Although the filter based on radial structure tensor analysis (RST filter) based on conventional RST analysis can be utilized to detect lymph nodes, some lymph nodes adjacent to regions with extremely high or low intensities cannot be detected. Therefore, we propose the ITRST filter, which integrates the prior knowledge on detection target intensity range into the RST filter. Our lymph node detection algorithm consists of two steps: (1) obtaining candidate regions using the ITRST filter and (2) removing false positives (FPs) using the support vector machine classifier. We evaluated lymph node detection performance of the ITRST filter on 47 contrast-enhanced chest CT volumes and compared it with the RST and Hessian filters. The detection rate of the ITRST filter was 84.2% with 9.1 FPs/volume for lymph nodes whose short axis was at least 10 mm, which outperformed the RST and Hessian filters.

Multiscale Centerline Detection

Finding the centerline and estimating the radius of linear structures is a critical first step in many applications, ranging from road delineation in 2D aerial images to modeling blood vessels, lung bronchi, and dendritic arbors in 3D biomedical image stacks. Existing techniques rely either on filters designed to respond to ideal cylindrical structures or on classification techniques. The former tend to become unreliable when the linear structures are very irregular while the latter often has difficulties distinguishing centerline locations from neighboring ones, thus losing accuracy. We solve this problem by reformulating centerline detection in terms of a regression problem. We first train regressors to return the distances to the closest centerline in scale-space, and we apply them to the input images or volumes. The centerlines and the corresponding scale then correspond to the regressors local maxima, which can be easily identified. We show that our method outperforms state-of-the-art techniques for various 2D and 3D datasets. Moreover, our approach is very generic and also performs well on contour detection. We show an improvement above recent contour detection algorithms on the BSDS500 dataset.

Vascular segmentation in hepatic CT images using adaptive threshold fuzzy connectedness method

Background

Fuzzy connectedness method has shown its effectiveness for fuzzy object extraction in recent years. However, two problems may occur when applying it to hepatic vessel segmentation task. One is the excessive computational cost, and the other is the difficulty of choosing a proper threshold value for final segmentation.

Methods

In this paper, an accelerated strategy based on a lookup table was presented first which can reduce the connectivity scene calculation time and achieve a speed-up factor of above 2. When the computing of the fuzzy connectedness relations is finished, a threshold is needed to generate the final result. Currently the threshold is preset by users. Since different thresholds may produce different outcomes, how to determine a proper threshold is crucial. According to our analysis of the hepatic vessel structure, a watershed-like method was used to find the optimal threshold. Meanwhile, by using Ostu algorithm to calculate the parameters for affinity relations and assigning the seed with the mean value, it is able to reduce the influence on the segmentation result caused by the location of the seed and enhance the robustness of fuzzy connectedness method.

Results

Experiments based on four different datasets demonstrate the efficiency of the lookup table strategy. These experiments also show that an adaptive threshold found by watershed-like method can always generate correct segmentation results of hepatic vessels. Comparing to a refined region-growing algorithm that has been widely used for hepatic vessel segmentation, fuzzy connectedness method has advantages in detecting vascular edge and generating more than one vessel system through the weak connectivity of the vessel ends.

Conclusions

An improved algorithm based on fuzzy connectedness method is proposed. This algorithm has improved the performance of fuzzy connectedness method in hepatic vessel segmentation.

A vessel active contour model for vascular segmentation

This paper proposes a vessel active contour model based on local intensity weighting and a vessel vector field. Firstly, the energy function we define is evaluated along the evolving curve instead of all image points, and the function value at each point on the curve is based on the interior and exterior weighted means in a local neighborhood of the point, which is good for dealing with the intensity inhomogeneity. Secondly, a vascular vector field derived from a vesselness measure is employed to guide the contour to evolve along the vessel central skeleton into thin and weak vessels. Thirdly, an automatic initialization method that makes the model converge rapidly is developed, and it avoids repeated trails in conventional local region active contour models. Finally, a speed-up strategy is implemented by labeling the steadily evolved points, and it avoids the repeated computation of these points in the subsequent iterations. Experiments using synthetic and real vessel images validate the proposed model. Comparisons with the localized active contour model, local binary fitting model, and vascular active contour model show that the proposed model is more accurate, efficient, and suitable for extraction of the vessel tree from different medical images.

Subtraction micro-computed tomography of angiogenesis and osteogenesis during bone repair using synchrotron radiation with a novel contrast agent

Quantitative three-dimensional (3D) imaging of angiogenesis during bone repair remains an experimental challenge. We developed a novel contrast agent containing 0.07- to 0.1-μm particles of zirconium dioxide (ZrCA) and established subtraction μCT using synchrotron radiation (sSRCT) for quantitative imaging of angiogenesis and bone repair. This method was applied to a rat model of tibial bone repair 3 days (DAY3; n = 2), 5 days (DAY5; n = 8), or 10 days (DAY10; n = 8) after drill-hole injury. Using the same drill-hole defect model, its potential use was illustrated by comparison of bone repair between hindlimbs subjected to mechanical unloading (n = 6) and normal weight bearing (n = 6) for 10 days. Following vascular casting with ZrCA, the defect site was scanned with 17.9- and 18.1-keV X-rays. In the latter, image contrast between ZrCA-filled vasculature and bone was enhanced owing to the sharp absorption jump of zirconium dioxide at 18.0 keV (k-edge). The two scan data sets were reconstructed with 2.74-μm voxel resolution, registered by mutual information, and digitally subtracted to extract the contrast-enhanced vascular image. K2HPO4 phantom solutions were scanned at 17.9 keV for quantitative evaluation of bone mineral. Angiogenesis had already started, but new bone formation was not found on DAY3. New bone emerged near the defect boundary on DAY5 and took the form of trabecular-like structure invaded by microvessels on DAY10. Vascular and bone volume fractions, blood vessel and bone thicknesses, and mineralization were higher on DAY10 than on DAY5. All these parameters were found to be decreased after 10 days of hindlimb unloading, indicating the possible involvement of angiogenesis in bone repair impairment caused by reduced mechanical stimuli. In conclusion, the combined technique of sSRCT and ZrCA vascular casting is suitable for quantitative 3D imaging of angiogenesis and its surrounding bone regeneration. This method will be useful for better understanding the linkage between angiogenesis and bone repair.