Fully automated liver segmentation from SPIR image series

MA-SOCRATIS: An automatic pipeline for robust segmentation of the left ventricle and scar

Multi-atlas segmentation of cardiac regions and total infarct scar (MA-SOCRATIS) is an unsupervised automatic pipeline to segment left ventricular myocardium and scar from late gadolinium enhanced MR images (LGE-MRI) of the heart. We implement two different pipelines for myocardial and scar segmentation from short axis LGE-MRI. Myocardial segmentation has two steps; initial segmentation and re-estimation. The initial segmentation step makes a first estimate of myocardium boundaries by using multi-atlas segmentation techniques. The re-estimation step refines the myocardial segmentation by a combination of k-means clustering and a geometric median shape variation technique. An active contour technique determines the unhealthy and healthy myocardial wall. The scar segmentation pipeline is a combination of a Rician-Gaussian mixture model and full width at half maximum (FWHM) thresholding, to determine the intensity pixels in scar regions. Following this step a watershed method with an automatic seed-points framework segments the final scar region. MA-SOCRATIS was evaluated using two different datasets. In both datasets ground truths were based on manual segmentation of short axis images from LGE-MRI scans. The first dataset included 40 patients from the MS-CMRSeg 2019 challenge dataset (STACOM at MICCAI 2019). The second is a collection of 20 patients with scar regions that are challenging to segment. MA-SOCRATIS achieved robust and accurate performance in automatic segmentation of myocardium and scar regions without the need of training or tuning in both cohorts, compared with state-of-the-art techniques (intra-observer and inter observer myocardium segmentation: 81.9% and 70% average Dice value, and scar (intra-observer and inter observer segmentation: 70.5% and 70.5% average Dice value).

A neutrosophic-entropy based adaptive thresholding segmentation algorithm: A special application in MR images of Parkinson's disease

Brain MR images are composed of three main regions such as gray matter, white matter and cerebrospinal fluid. Radiologists and medical practitioners make decisions through evaluating the developments in these regions. Study of these MR images suffers from two major issues such as: (a) the boundaries of their gray matter and white matter regions are ambiguous and unclear in nature, and (b) their regions are formed with unclear inhomogeneous gray structures. These two issues make the diagnosis of critical diseases very complex. To solve these issues, this study presented a method of image segmentation based on the neutrosophic set (NS) theory and neutrosophic entropy information (NEI). By nature, the proposed method is adaptive to select the threshold value and is entitled as neutrosophic-entropy based adaptive thresholding segmentation algorithm (NEATSA). In this study, experimental results were provided through the segmentation of Parkinson's disease (PD) MR images. Experimental results, including statistical analyses showed that NEATSA can segment the main regions of MR images very clearly compared to the well-known methods of image segmentation available in literature of pattern recognition and computer vision domains.

Deep Learning-Based Classification of Liver Cancer Histopathology Images Using Only Global Labels

Liver cancer is a leading cause of cancer deaths worldwide due to its high morbidity and mortality. Histopathological image analysis (HIA) is a crucial step in the early diagnosis of liver cancer and is routinely performed manually. However, this process is time-consuming, error-prone, and easily affected by the expertise of pathologists. Recently, computer-aided methods have been widely applied to medical image analysis; however, the current medical image analysis studies have not yet focused on the histopathological morphology of liver cancer due to its complex features and the insufficiency of training images with detailed annotations. This paper proposes a deep learning method for liver cancer histopathological image classification using only global labels. To compensate for the lack of detailed cancer region annotations in those images, patch features are extracted and fully utilized. Transfer learning is used to obtain the patch-level features and then combined with multiple-instance learning to acquire the image-level features for classification. The method proposed here solves the processing of large-scale images and training sample insufficiency in liver cancer histopathological images for image classification. The proposed method can distinguish and classify liver histopathological images as abnormal or normal with high accuracy, thus providing support for the early diagnosis of liver cancer.

A robust multi-variability model based liver segmentation algorithm for CT-scan and MRI modalities

Developing methods to segment the liver in medical images, study and analyze it remains a significant challenge. The shape of the liver can vary considerably from one patient to another, and adjacent organs are visualized in medical images with similar intensities, making the boundaries of the liver ambiguous. Consequently, automatic or semi-automatic segmentation of liver is a difficult task. Moreover, scanning systems and magnetic resonance imaging have different settings and parameters. Thus the images obtained differ from one machine to another. In this article, we propose an automatic model-based segmentation that allows building a faithful 3-D representation of the liver, with a mean Dice value equal to 90.3% on CT and MRI datasets. We compare our algorithm with a semi-automatic method and with other approaches according to the state of the art. Our method works with different data sources, we use a large quantity of CT and MRI images from machines in various hospitals and multiple DICOM images available from public challenges. Finally, for evaluation of liver segmentation approaches in state of the art, robustness is not adequacy addressed with a precise definition. Another originality of this article is the introduction of a novel measure of robustness, which takes into account the liver variability at different scales.

Disease quantification on PET/CT images without explicit object delineation

PURPOSE

The derivation of quantitative information from images in a clinically practical way continues to face a major hurdle because of image segmentation challenges. This paper presents a novel approach, called automatic anatomy recognition-disease quantification (AAR-DQ), for disease quantification (DQ) on positron emission tomography/computed tomography (PET/CT) images. This approach explores how to decouple DQ methods from explicit dependence on object (e.g., organ) delineation through the use of only object recognition results from our recently developed automatic anatomy recognition (AAR) method to quantify disease burden.

METHOD

The AAR-DQ process starts off with the AAR approach for modeling anatomy and automatically recognizing objects on low-dose CT images of PET/CT acquisitions. It incorporates novel aspects of model building that relate to finding an optimal disease map for each organ. The parameters of the disease map are estimated from a set of training image data sets including normal subjects and patients with metastatic cancer. The result of recognition for an object on a patient image is the location of a fuzzy model for the object which is optimally adjusted for the image. The model is used as a fuzzy mask on the PET image for estimating a fuzzy disease map for the specific patient and subsequently for quantifying disease based on this map. This process handles blur arising in PET images from partial volume effect entirely through accurate fuzzy mapping to account for heterogeneity and gradation of disease content at the voxel level without explicitly performing correction for the partial volume effect. Disease quantification is performed from the fuzzy disease map in terms of total lesion glycolysis (TLG) and standardized uptake value (SUV) statistics. We also demonstrate that the method of disease quantification is applicable even when the "object" of interest is recognized manually with a simple and quick action such as interactively specifying a 3D box ROI. Depending on the degree of automaticity for object and lesion recognition on PET/CT, DQ can be performed at the object level either semi-automatically (DQ-MO) or automatically (DQ-AO), or at the lesion level either semi-automatically (DQ-ML) or automatically.

RESULTS

We utilized 67 data sets in total: 16 normal data sets used for model building, and 20 phantom data sets plus 31 patient data sets (with various types of metastatic cancer) used for testing the three methods DQ-AO, DQ-MO, and DQ-ML. The parameters of the disease map were estimated using the leave-one-out strategy. The organs of focus were left and right lungs and liver, and the disease quantities measured were TLG, SUV_Mean, and SUV_Max. On phantom data sets, overall error for the three parameters were approximately 6%, 3%, and 0%, respectively, with TLG error varying from 2% for large "lesions" (37 mm diameter) to 37% for small "lesions" (10 mm diameter). On patient data sets, for non-conspicuous lesions, those overall errors were approximately 19%, 14% and 0%; for conspicuous lesions, these overall errors were approximately 9%, 7%, 0%, respectively, with errors in estimation being generally smaller for liver than for lungs, although without statistical significance.

CONCLUSIONS

Accurate disease quantification on PET/CT images without performing explicit delineation of lesions is feasible following object recognition. Method DQ-MO generally yields more accurate results than DQ-AO although the difference is statistically not significant. Compared to current methods from the literature, almost all of which focus only on lesion-level DQ and not organ-level DQ, our results were comparable for large lesions and were superior for smaller lesions, with less demand on training data and computational resources. DQ-AO and even DQ-MO seem to have the potential for quantifying disease burden body-wide routinely via the AAR-DQ approach.

An automated liver tumour segmentation from abdominal CT scans for hepatic surgical planning

PURPOSE

Segmentation of liver tumours is an important part of the 3D visualisation of the liver anatomy for surgical planning. The spatial relationship between tumours and other structures inside the liver forms the basis of preoperative surgical risk assessment. However, the automatic segmentation of liver tumours from abdominal CT scans is riddled with challenges. Tumours located at the border of the liver impose a big challenge as the surrounding tissues could have similar intensities.

METHODS

In this work, we introduce a fully automated liver tumour segmentation approach in contrast-enhanced CT datasets. The method is a multi-stage technique which starts with contrast enhancement of the tumours using anisotropic filtering, followed by adaptive thresholding to extract the initial mask of the tumours from an identified liver region of interest. Localised level set-based active contours are used to extend the mask to the tumour boundaries.

RESULTS

The proposed method is validated on the IRCAD database with pathologies that offer highly variable and complex liver tumours. The results are compared quantitatively to the ground truth, which is delineated by experts. We achieved an average dice similarity coefficient of 75% over all patients with liver tumours in the database with overall absolute relative volume difference of 11%. This is comparable to other recent works, which include semiautomated methods, although they were validated on different datasets.

CONCLUSIONS

The proposed approach aims to segment tumours inside the liver envelope automatically with a level of accuracy adequate for its use as a tool for surgical planning using abdominal CT images. The approach will be validated on larger datasets in the future.

Segmentation of liver and vessels from CT images and classification of liver segments for preoperative liver surgical planning in living donor liver transplantation

BACKGROUND AND OBJECTIVE

The present study developed an effective surgical planning method consisting of a liver extraction stage, a vessel extraction stage, and a liver segment classification stage based on abdominal computerized tomography (CT) images.

METHODS

An automatic seed point identification method, customized level set methods, and an automated thresholding method were applied in this study to extraction of the liver, portal vein (PV), and hepatic vein (HV) from CT images. Then, a semi-automatic method was developed to separate PV and HV. Lastly, a local searching method was proposed for identification of PV branches and the nearest neighbor approximation method was applied to classifying liver segments.

RESULTS

Onsite evaluation of liver segmentation provided by the SLIVER07 website showed that the liver segmentation method achieved an average volumetric overlap accuracy of 95.2%. An expert radiologist evaluation of vessel segmentation showed no false positive errors or misconnections between PV and HV in the extracted vessel trees. Clinical evaluation of liver segment classification using 43 CT datasets from two medical centers showed that the proposed method achieved high accuracy in liver graft volumetry (absolute error, AE = 45.2 ± 20.9 ml; percentage of AE, %AE = 6.8% ± 3.2%; percentage of %AE > 10% = 16.3%; percentage of %AE > 20% = none) and the classified segment boundaries agreed with the intraoperative surgical cutting boundaries by visual inspection.

CONCLUSIONS

The method in this study is effective in segmentation of liver and vessels and classification of liver segments and can be applied to preoperative liver surgical planning in living donor liver transplantation.

Automatic liver segmentation from abdominal CT volumes using graph cuts and border marching

BACKGROUND AND OBJECTIVE

Identifying liver regions from abdominal computed tomography (CT) volumes is an important task for computer-aided liver disease diagnosis and surgical planning. This paper presents a fully automatic method for liver segmentation from CT volumes based on graph cuts and border marching.

METHODS

An initial slice is segmented by density peak clustering. Based on pixel- and patch-wise features, an intensity model and a PCA-based regional appearance model are developed to enhance the contrast between liver and background. Then, these models as well as the location constraint estimated iteratively are integrated into graph cuts in order to segment the liver in each slice automatically. Finally, a vessel compensation method based on the border marching is used to increase the segmentation accuracy.

RESULTS

Experiments are conducted on a clinical data set we created and also on the MICCAI2007 Grand Challenge liver data. The results show that the proposed intensity, appearance models, and the location constraint are significantly effective for liver recognition, and the undersegmented vessels can be compensated by the border marching based method. The segmentation performances in terms of VOE, RVD, ASD, RMSD, and MSD as well as the average running time achieved by our method on the SLIVER07 public database are 5.8 ± 3.2%, -0.1 ± 4.1%, 1.0 ± 0.5mm, 2.0 ± 1.2mm, 21.2 ± 9.3mm, and 4.7 minutes, respectively, which are superior to those of existing methods.

CONCLUSIONS

The proposed method does not require time-consuming training process and statistical model construction, and is capable of dealing with complicated shapes and intensity variations successfully.

Vessel segmentation from abdominal magnetic resonance images: adaptive and reconstructive approach

The liver vessels, which have low signal and run next to brighter bile ducts, are difficult to segment from MR images. This study presents a fully automated and adaptive method to segment portal and hepatic veins on magnetic resonance images. In the proposed approach, segmentation of these vessels is achieved in four stages: (i) initial segmentation, (ii) refinement, (iii) reconstruction, and (iv) post-processing. In the initial segmentation stage, k-means clustering is used, the results of which are refined iteratively with linear contrast stretching algorithm in the next stage, generating a mask image. In the reconstruction stage, vessel regions are reconstructed with the marker image from the first stage and the mask image from the second stage. Experimental data sets include slices that show fat tissues, which have the same gray level values with vessels, outside the margin of the liver. These structures are removed in the last stage. Results show that the proposed approach is more efficient than other thresholding-based methods. Copyright © 2016 John Wiley & Sons, Ltd.

Prioritization of liver MRI for distinguishing focal lesions

Liver cancer is one of the leading causes of cancer-related mortality worldwide. Magnetic resonance imaging (MRI) is a non-invasive imaging technique that is often used by radiologists for diagnosis and surgical planning. Analysis of a large amount of liver MRI data for each patient limits the radiologist's efficiency and may lead to misdiagnoses. The redundant MRI data, especially from dynamic contrast enhanced (DCE) sequences, is also a bottleneck in transmitting the images via the internet or PACS for remote consultancy in a reasonable amount of time. This study included 25 patients (aged between 20 and 70 years) with liver cysts (seven cases), hemangiomas (eight cases), or hepatic cell carcinomas (10 cases). DCE T1WI MRI was performed for all the patients. The diagnosis reference included typical MRI findings and post-surgery pathology. The methods were as follows: (i) MRI sequence pre-processing based on large vessels variation level set method to remove non-liver parts from MRI images; (ii) human visual model features (luminance, motion, and contour) extraction and fusion; (iii) anomaly-based MRI ranking; and (iv) methods assessment with the 25 patients' DCE MRI data. The prioritization methods applied to the DCE images could automatically assimilate and determine the content of the medical images, identifying the liver cysts, hemangiomas, and carcinomas. The average uniformity between radiologists and prioritization with the proposed method was 0.805, 0.838, and 0.818 for cysts, hemangiomas, and carcinomas, respectively, which indicates that the proposed method is an efficient method for liver DCE image prioritization.

Fully automated liver segmentation using Sobolev gradient-based level set evolution

Quantitative analysis and precise measurements on the liver have vital importance for pre-evaluation of surgical operations and require high accuracy in liver segmentation from all slices in a data set. However, automated liver segmentation from medical image data sets is more challenging than segmentation of any other organ due to various reasons such as vascular structures in the liver, high variability of liver shapes, similar intensity values, and unclear edges between liver and its adjacent organs. In this study, a variational level set-based segmentation approach is proposed to be efficient in terms of processing time and accuracy. The efficiency of this method is achieved by (1) automated initialization of a large initial contour, (2) using an adaptive signed pressure force function, and also (3) evolution of the level set with Sobolev gradient. Experimental results show that the proposed fully automated segmentation technique avoids local minima and stops evolution of the active contour at desired liver boundaries with high speed and accuracy. Copyright © 2016 John Wiley & Sons, Ltd.

3D active surfaces for liver segmentation in multisequence MRI images

Biopsies for diagnosis can sometimes be replaced by non-invasive techniques such as CT and MRI. Surgeons require accurate and efficient methods that allow proper segmentation of the organs in order to ensure the most reliable intervention planning. Automated liver segmentation is a difficult and open problem where CT has been more widely explored than MRI. MRI liver segmentation represents a challenge due to the presence of characteristic artifacts, such as partial volumes, noise and low contrast. In this paper, we present a novel method for multichannel MRI automatic liver segmentation. The proposed method consists of the minimization of a 3D active surface by means of the dual approach to the variational formulation of the underlying problem. This active surface evolves over a probability map that is based on a new compact descriptor comprising spatial and multisequence information which is further modeled by means of a liver statistical model. This proposed 3D active surface approach naturally integrates volumetric regularization in the statistical model. The advantages of the compact visual descriptor together with the proposed approach result in a fast and accurate 3D segmentation method. The method was tested on 18 healthy liver studies and results were compared to a gold standard made by expert radiologists. Comparisons with other state-of-the-art approaches are provided by means of nine well established quality metrics. The obtained results improve these methodologies, achieving a Dice Similarity Coefficient of 98.59.