Interactive segmentation of abdominal aortic aneurysms in CTA images

A model-based approach to interactive segmentation of abdominal aortic aneurysms from CTA data is presented. After manual delineation of the aneurysm sac in the first slice, the method automatically detects the contour in subsequent slices, using the result from the previous slice as a reference. If an obtained contour is not sufficiently accurate, the user can intervene and provide an additional manual reference contour. The method is inspired by the active shape model (ASM) segmentation scheme (), in which a statistical shape model, derived from corresponding landmark points in manually labeled training images, is fitted to the image in an iterative manner. In our method, a shape model of the contours in two adjacent image slices is progressively fitted to the entire volume. The contour obtained in one slice thus constrains the possible shapes in the next slice. The optimal fit is determined on the basis of multi-resolution gray level models constructed from gray value patches sampled around each landmark. We propose to use the similarity of adjacent image slices for this gray level model, and compare these to single-slice features that are more generally used with ASM. The performance of various image features is evaluated in leave-one-out experiments on 23 data sets. Features that use the similarity of adjacent image slices outperform measures based on single-slice features in all cases. The average number of slices in our datasets is 51, while on average eight manual initializations are required, which decreases operator segmentation time by a factor of 6.     

Posterior shape models

We present a method to compute the conditional distribution of a statistical shape model given partial data. The result is a “posterior shape model”, which is again a statistical shape model of the same form as the original model. This allows its direct use in the variety of algorithms that include prior knowledge about the variability of a class of shapes with a statistical shape model. Posterior shape models then provide a statistically sound yet easy method to integrate partial data into these algorithms. Usually, shape models represent a complete organ, for instance in our experiments the femur bone, modeled by a multivariate normal distribution. But because in many application certain parts of the shape are known a priori, it is of great interest to model the posterior distribution of the whole shape given the known parts. These could be isolated landmark points or larger portions of the shape, like the healthy part of a pathological or damaged organ. However, because for most shape models the dimensionality of the data is much higher than the number of examples, the normal distribution is singular, and the conditional distribution not readily available. In this paper, we present two main contributions: First, we show how the posterior model can be efficiently computed as a statistical shape model in standard form and used in any shape model algorithm. We complement this paper with a freely available implementation of our algorithms. Second, we show that most common approaches put forth in the literature to overcome this are equivalent to probabilistic principal component analysis (PPCA), and Gaussian Process regression. To illustrate the use of posterior shape models, we apply them on two problems from medical image analysis: model-based image segmentation incorporating prior knowledge from landmarks, and the prediction of anatomically correct knee shapes for trochlear dysplasia patients, which constitutes a novel medical application. Our experiments confirm that the use of conditional shape models for image segmentation improves the overall segmentation accuracy and robustness.     

Fully automatic segmentation of the Femur from 3D-CT images using primitive shape recognition and statistical shape models

Purpose

Femur segmentation is well established and widely used in computer-assisted orthopedic surgery. However, most of the robust segmentation methods such as statistical shape models (SSM) require human intervention to provide an initial position for the SSM. In this paper, we propose to overcome this problem and provide a fully automatic femur segmentation method for CT images based on primitive shape recognition and SSM.

Method

Femur segmentation in CT scans was performed using primitive shape recognition based on a robust algorithm such as the Hough transform and RANdom SAmple Consensus. The proposed method is divided into 3 steps: (1) detection of the femoral head as sphere and the femoral shaft as cylinder in the SSM and the CT images, (2) rigid registration between primitives of SSM and CT image to initialize the SSM into the CT image, and (3) fitting of the SSM to the CT image edge using an affine transformation followed by a nonlinear fitting.

Results

The automated method provided good results even with a high number of outliers. The difference of segmentation error between the proposed automatic initialization method and a manual initialization method is less than 1 mm.

Conclusion

The proposed method detects primitive shape position to initialize the SSM into the target image. Based on primitive shapes, this method overcomes the problem of inter-patient variability. Moreover, the results demonstrate that our method of primitive shape recognition can be used for 3D SSM initialization to achieve fully automatic segmentation of the femur.     

Optimizing boundary detection via Simulated Search with applications to multi-modal heart segmentation

Segmentation of medical images can be achieved with the help of model-based algorithms. Reliable boundary detection is a crucial component to obtain robust and accurate segmentation results and to enable full automation. This is especially important if the anatomy being segmented is too variable to initialize a mean shape model such that all surface regions are close to the desired contours. Several boundary detection algorithms are widely used in the literature. Most use some trained image appearance model to characterize and detect the desired boundaries. Although parameters of the boundary detection can vary over the model surface and are trained on images, their performance (i.e., accuracy and reliability of boundary detection) can only be assessed as an integral part of the entire segmentation algorithm. In particular, assessment of boundary detection cannot be done locally and independently on model parameterization and internal energies controlling geometric model properties.In this paper, we propose a new method for the local assessment of boundary detection called Simulated Search. This method takes any boundary detection function and evaluates its performance for a single model landmark in terms of an estimated geometric boundary detection error. In consequence, boundary detection can be optimized per landmark during model training. We demonstrate the success of the method for cardiac image segmentation. In particular we show that the Simulated Search improves the capture range and the accuracy of the boundary detection compared to a traditional training scheme. We also illustrate how the Simulated Search can be used to identify suitable classes of features when addressing a new segmentation task. Finally, we show that the Simulated Search enables multi-modal heart segmentation using a single algorithmic framework. On computed tomography and magnetic resonance images, average segmentation errors (surface-to-surface distances) for the four chambers and the trunks of the large vessels are in the order of 0.8 mm. For 3D rotational X-ray angiography images of the left atrium and pulmonary veins, the average error is 1.3 mm. In all modalities, the locally optimized boundary detection enables fully automatic segmentation.     

SPASM: a 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data

A new technique (SPASM) based on a 3D-ASM is presented for automatic segmentation of cardiac MRI image data sets consisting of multiple planes with arbitrary orientations, and with large undersampled regions. Model landmark positions are updated in a two-stage iterative process. First, landmark positions close to intersections with images are updated. Second, the update information is propagated to the regions without image information, such that new locations for the whole set of the model landmarks are obtained. Feature point detection is performed by a fuzzy inference system, based on fuzzy C-means clustering. Model parameters were optimized on a computer cluster and the computational load distributed by grid computing. SPASM was applied to image data sets with an increasing sparsity (from 2 to 11 slices) comprising images with different orientations and stemming from different MRI acquisition protocols. Segmentation outcomes and calculated volumes were compared to manual segmentation on a dense short-axis data configuration in a 3D manner. For all data configurations, (sub-)pixel accuracy was achieved. Performance differences between data configurations were significantly different (p<0.05) for SA data sets with less than 6 slices, but not clinically relevant (volume differences<4 ml). Comparison to results from other 3D model-based methods showed that SPASM performs comparable to or better than these other methods, but SPASM uses considerably less image data. Sensitivity to initial model placement proved to be limited within a range of position perturbations of approximately 20 mm in all directions.     

Evaluation of image features and search strategies for segmentation of bone structures in radiographs using Active Shape Models

In this paper, we evaluate various image features and different search strategies for fitting Active Shape Models (ASM) to bone object boundaries in digitized radiographs. The original ASM method iteratively refines the pose and shape parameters of the point distribution model driving the ASM by a least squares fit of the shape to update the target points at the estimated object boundary position, as determined by a suitable object boundary criterion. We propose an improved search procedure that is more robust against outlier configurations in the boundary target points by requiring subsequent shape changes to be smooth, which is imposed by a smoothness constraint on the displacement of neighbouring target points at each iteration and implemented by a minimal cost path approach. We compare the original ASM search method and our improved search algorithm with a third method that does not rely on iteratively refined target point positions, but instead optimizes a global Bayesian objective function derived from statistical a priori contour shape and image models. Extensive validation of these methods on a database containing more than 400 images of the femur, humerus and calcaneus using the manual expert segmentation as ground truth shows that our minimal cost path method is the most robust. We also evaluate various measures for capturing local image appearance around each boundary point and conclude that the Mahalanobis distance applied to normalized image intensity profiles extracted normal to the shape is the most suitable criterion among the tested ones for guiding the ASM optimization.     

Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification

Morphological abnormalities of the femoroacetabular (hip) joint are among the most common human musculoskeletal disorders and often develop asymptomatically at early easily treatable stages. In this paper, we propose an automated framework for landmark-based detection and quantification of hip abnormalities from magnetic resonance (MR) images. The framework relies on a novel idea of multi-landmark environment analysis with reinforcement learning. In particular, we merge the concepts of the graphical lasso and Morris sensitivity analysis with deep neural networks to quantitatively estimate the contribution of individual landmark and landmark subgroup locations to the other landmark locations. Convolutional neural networks for image segmentation are utilized to propose the initial landmark locations, and landmark detection is then formulated as a reinforcement learning (RL) problem, where each landmark-agent can adjust its position by observing the local MR image neighborhood and the locations of the most-contributive landmarks. The framework was validated on T1-, T2- and proton density-weighted MR images of 260 patients with the aim to measure the lateral center-edge angle (LCEA), femoral neck-shaft angle (NSA), and the anterior and posterior acetabular sector angles (AASA and PASA) of the hip, and derive the quantitative abnormality metrics from these angles. The framework was successfully tested using the UNet and feature pyramid network (FPN) segmentation architectures for landmark proposal generation, and the deep Q-network (DeepQN), deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and actor-critic policy gradient (A2C) RL networks for landmark position optimization. The resulting overall landmark detection error of 1.5 mm and angle measurement error of 1.4° indicates a superior performance in comparison to existing methods. Moreover, the automatically estimated abnormality labels were in 95% agreement with those generated by an expert radiologist.     

Context-guided fully convolutional networks for joint craniomaxillofacial bone segmentation and landmark digitization

Cone-beam computed tomography (CBCT) scans are commonly used in diagnosing and planning surgical or orthodontic treatment to correct craniomaxillofacial (CMF) deformities. Based on CBCT images, it is clinically essential to generate an accurate 3D model of CMF structures (e.g., midface, and mandible) and digitize anatomical landmarks. This process often involves two tasks, i.e., bone segmentation and anatomical landmark digitization. Because landmarks usually lie on the boundaries of segmented bone regions, the tasks of bone segmentation and landmark digitization could be highly associated. Also, the spatial context information (e.g., displacements from voxels to landmarks) in CBCT images is intuitively important for accurately indicating the spatial association between voxels and landmarks. However, most of the existing studies simply treat bone segmentation and landmark digitization as two standalone tasks without considering their inherent relationship, and rarely take advantage of the spatial context information contained in CBCT images. To address these issues, we propose a Joint bone Segmentation and landmark Digitization (JSD) framework via context-guided fully convolutional networks (FCNs). Specifically, we first utilize displacement maps to model the spatial context information in CBCT images, where each element in the displacement map denotes the displacement from a voxel to a particular landmark. An FCN is learned to construct the mapping from the input image to its corresponding displacement maps. Using the learned displacement maps as guidance, we further develop a multi-task FCN model to perform bone segmentation and landmark digitization jointly. We validate the proposed JSD method on 107 subjects, and the experimental results demonstrate that our method is superior to the state-of-the-art approaches in both tasks of bone segmentation and landmark digitization.     

3D image segmentation of deformable objects with joint shape-intensity prior models using level sets

We propose a novel method for 3D image segmentation, where a Bayesian formulation, based on joint prior knowledge of the object shape and the image gray levels, along with information derived from the input image, is employed. Our method is motivated by the observation that the shape of an object and the gray level variation in an image have consistent relations that provide configurations and context that aid in segmentation. We define a maximum a posteriori (MAP) estimation model using the joint prior information of the object shape and the image gray levels to realize image segmentation. We introduce a representation for the joint density function of the object and the image gray level values, and define a joint probability distribution over the variations of the object shape and the gray levels contained in a set of training images. By estimating the MAP shape of the object, we formulate the shape-intensity model in terms of level set functions as opposed to landmark points of the object shape. In addition, we evaluate the performance of the level set representation of the object shape by comparing it with the point distribution model (PDM). We found the algorithm to be robust to noise and able to handle multidimensional data, while able to avoid the need for explicit point correspondences during the training phase. Results and validation from various experiments on 2D and 3D medical images are shown.     

A comprehensive study of stent visualization enhancement in X-ray images by image processing means

In this work we propose a comprehensive study of Digital Stent Enhancement (DSE), from the analysis of the requirements to the validation of the proposed solution. First, we derive the stent visualization requirements in the context of the clinical application and workflow. Then, we propose a DSE algorithm combining automatic detection, tracking, registration and contrast enhancement. The most original parts of our solution: landmark segmentation and non-linear image registration are detailed. Finally, we validate the algorithm on a large number of synthetic and clinical cases. Performance is characterized in terms of automation, image quality and execution time. This work is, to the best of our knowledge, the first comprehensive article on DSE, covering problem statement, proposed solution, and validation strategies.     

LMISA: A lightweight multi-modality image segmentation network via domain adaptation using gradient magnitude and shape constraint

In medical image segmentation, supervised machine learning models trained using one image modality (e.g. computed tomography (CT)) are often prone to failure when applied to another image modality (e.g. magnetic resonance imaging (MRI)) even for the same organ. This is due to the significant intensity variations of different image modalities. In this paper, we propose a novel end-to-end deep neural network to achieve multi-modality image segmentation, where image labels of only one modality (source domain) are available for model training and the image labels for the other modality (target domain) are not available. In our method, a multi-resolution locally normalized gradient magnitude approach is firstly applied to images of both domains for minimizing the intensity discrepancy. Subsequently, a dual task encoder-decoder network including image segmentation and reconstruction is utilized to effectively adapt a segmentation network to the unlabeled target domain. Additionally, a shape constraint is imposed by leveraging adversarial learning. Finally, images from the target domain are segmented, as the network learns a consistent latent feature representation with shape awareness from both domains. We implement both 2D and 3D versions of our method, in which we evaluate CT and MRI images for kidney and cardiac tissue segmentation. For kidney, a public CT dataset (KiTS19, MICCAI 2019) and a local MRI dataset were utilized. The cardiac dataset was from the Multi-Modality Whole Heart Segmentation (MMWHS) challenge 2017. Experimental results reveal that our proposed method achieves significantly higher performance with a much lower model complexity in comparison with other state-of-the-art methods. More importantly, our method is also capable of producing superior segmentation results than other methods for images of an unseen target domain without model retraining. The code is available at GitHub (https://github.com/MinaJf/LMISA) to encourage method comparison and further research.     

Cephalogram synthesis and landmark detection in dental cone-beam CT systems

Due to the lack of a standardized 3D cephalometric analysis methodology, 2D cephalograms synthesized from 3D cone-beam computed tomography (CBCT) volumes are widely used for cephalometric analysis in dental CBCT systems. However, compared with conventional X-ray film based cephalograms, such synthetic cephalograms lack image contrast and resolution, which impairs cephalometric landmark identification. In addition, the increased radiation dose applied to acquire the scan for 3D reconstruction causes potential health risks. In this work, we propose a sigmoid-based intensity transform that uses the nonlinear optical property of X-ray films to increase image contrast of synthetic cephalograms from 3D volumes. To improve image resolution, super resolution deep learning techniques are investigated. For low dose purpose, the pixel-to-pixel generative adversarial network (pix2pixGAN) is proposed for 2D cephalogram synthesis directly from two cone-beam projections. For landmark detection in the synthetic cephalograms, an efficient automatic landmark detection method using the combination of LeNet-5 and ResNet50 is proposed. Our experiments demonstrate the efficacy of pix2pixGAN in 2D cephalogram synthesis, achieving an average peak signal-to-noise ratio (PSNR) value of 33.8 with reference to the cephalograms synthesized from 3D CBCT volumes. Pix2pixGAN also achieves the best performance in super resolution, achieving an average PSNR value of 32.5 without the introduction of checkerboard or jagging artifacts. Our proposed automatic landmark detection method achieves 86.7% successful detection rate in the 2 mm clinical acceptable range on the ISBI Test1 data, which is comparable to the state-of-the-art methods. The method trained on conventional cephalograms can be directly applied to landmark detection in the synthetic cephalograms, achieving 93.0% and 80.7% successful detection rate in 4 mm precision range for synthetic cephalograms from 3D volumes and 2D projections, respectively.     

Development and comparison of new hybrid motion tracking for bronchoscopic navigation

This paper presents a new hybrid camera motion tracking method for bronchoscopic navigation combining SIFT, epipolar geometry analysis, Kalman filtering, and image registration. In a thorough evaluation, we compare it to state-of-the-art tracking methods. Our hybrid algorithm for predicting bronchoscope motion uses SIFT features and epipolar constraints to obtain an estimate for inter-frame pose displacements and Kalman filtering to find an estimate for the magnitude of the motion. We then execute bronchoscope tracking by performing image registration initialized by these estimates. This procedure registers the actual bronchoscopic video and the virtual camera images generated from 3D chest CT data taken prior to bronchoscopic examination for continuous bronchoscopic navigation. A comparative assessment of our new method and the state-of-the-art methods is performed on actual patient data and phantom data. Experimental results from both datasets demonstrate a significant performance boost of navigation using our new method. Our hybrid method is a promising means for bronchoscope tracking, and outperforms other methods based solely on Kalman filtering or image features and image registration.     

A deep learning approach for the analysis of masses in mammograms with minimal user intervention

We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal-to-noise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down into three stages: mass detection, mass segmentation, and mass classification. For the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimisation. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose the use of a deep learning classifier, which is pre-trained with a regression to hand-crafted feature values and fine-tuned based on the annotations of the breast mass classification dataset. We test our proposed system on the publicly available INbreast dataset and compare the results with the current state-of-the-art methodologies. This evaluation shows that our system detects 90% of masses at 1 false positive per image, has a segmentation accuracy of around 0.85 (Dice index) on the correctly detected masses, and overall classifies masses as malignant or benign with sensitivity (Se) of 0.98 and specificity (Sp) of 0.7.     

Robust statistical shape models for MRI bone segmentation in presence of small field of view

Accurate bone modeling from medical images is essential in the diagnosis and treatment of patients because it supports the detection of abnormal bone morphology, which is often responsible for many musculoskeletal diseases (MSDs) of human articulations. In a clinical setting, images of the suspected joints are acquired in a high resolution but with a small field of view (FOV) in order to maximize the image quality while reducing acquisition time. However bones are only partially visible in such small FOVs. This presents difficult challenges in automated bone segmentation and thus limits the application of sophisticated algorithms such as statistical shape models (SSM), which have been generally proven to be an efficient technique for bone segmentation. Indeed, the reduced image information affects the initialization and evolution of these deformable model-based approaches. In this paper, we present a robust multi-resolution SSM algorithm with an adapted initialization to address the segmentation of MRI bone images acquired in small FOVs for modeling and computer-aided diagnosis. Our innovation stems from the derivation of a robust SSM based on complete and corrupted shapes, as well as from a simultaneous optimization of transformation and shape parameters to yield an efficient initialization technique. We demonstrate our segmentation algorithm using 86 clinical MRI images of the femur and hip bones. These images have a varied resolution and limited FOVs. The results of our segmentation (e.g., average distance error of 1.12 ± 0.46 mm) are within the needs of image-based clinical diagnosis.     

Landmark constellation models for medical image content identification and localization

Purpose

Many medical imaging tasks require the detection and localization of anatomical landmarks, for example for the initialization of model-based segmentation or to detect anatomical regions present in an image. A large number of landmark and object localization methods have been described in the literature. The detection of single landmarks may be insufficient to achieve robust localization across a variety of imaging settings and subjects. Furthermore, methods like the generalized Hough transform yield the most likely location of an object, but not an indication whether or not the landmark was actually present in the image.

Methods

For these reasons, we developed a simple and computationally efficient method combining localization results from multiple landmarks to achieve robust localization and to compute a localization confidence measure. For each anatomical region, we train a constellation model indicating the mean relative locations and location variability of a set of landmarks. This model is registered to the landmarks detected in a test image via point-based registration, using closed-form solutions. Three different outlier suppression schemes are compared, two using iterative re-weighting based on the residual landmark registration errors and the third being a variant of RANSAC. The mean weighted residual registration error serves as a confidence measure to distinguish true from false localization results. The method is optimized and evaluated on synthetic data, evaluating both the localization accuracy and the ability to classify good from bad registration results based on the residual registration error.

Results

Two application examples are presented: the identification of the imaged anatomical region in trauma CT scans and the initialization of model-based segmentation for C-arm CT scans with different target regions. The identification of the target region with the presented method was in 96 % of the cases correct.

Conclusion

The presented method is a simple solution for combining multiple landmark localization results. With appropriate parameters, outlier suppression clearly improves the localization performance over model registration without outlier suppression. The optimum choice of method and parameters depends on the expected level of noise and outliers in the application at hand, as well as on the focus on localization, classification, or both. The method allows detecting and localizing anatomical fields of view in medical images and is well suited to support a wide range of applications comprising image content identification, anatomical navigation and visualization, or initializing the pose of organ shape models.

     

Statistical model-based segmentation of the proximal femur in digital antero-posterior (AP) pelvic radiographs

Purpose

   Segmentation of the proximal femur in digital antero-posterior (AP) pelvic radiographs is required to create a three-dimensional model of the hip joint for use in planning and treatment. However, manually extracting the femoral contour is tedious and prone to subjective bias, while automatic segmentation must accommodate poor image quality, anatomical structure overlap, and femur deformity. A new method was developed for femur segmentation in AP pelvic radiographs.

Methods

   Using manual annotations on 100 AP pelvic radiographs, a statistical shape model (SSM) and a statistical appearance model (SAM) of the femur contour were constructed. The SSM and SAM were used to segment new AP pelvic radiographs with a three-stage approach. At initialization, the mean SSM model is coarsely registered to the femur in the AP radiograph through a scaled rigid registration. Mahalanobis distance defined on the SAM is employed as the search criteria for each annotated suggested landmark location. Dynamic programming was used to eliminate ambiguities. After all landmarks are assigned, a regularized non-rigid registration method deforms the current mean shape of SSM to produce a new segmentation of proximal femur. The second and third stages are iteratively executed to convergence.

Results

   A set of 100 clinical AP pelvic radiographs (not used for training) were evaluated. The mean segmentation error was $0.96\,\hbox {mm} \pm 0.35\,\hbox {mm}$ , requiring $<\!5$  s per case when implemented with Matlab. The influence of the initialization on segmentation results was tested by six clinicians, demonstrating no significance difference.

Conclusions

   A fast, robust and accurate method for femur segmentation in digital AP pelvic radiographs was developed by combining SSM and SAM with dynamic programming. This method can be extended to segmentation of other bony structures such as the pelvis.     

基于配准与ASM方法的医学图像分割

目的随着医学图像数据的急剧增长,建立从医学图像中自动分割特定解剖结构的算法。方法首先,获取的脑图像体数据集通过与参考体数据集的配准,使对应层图像包含与参考数据相似的解剖结构;然后利用训练得到的统计形状模型自动定位、分割指定的解剖结构。结果实验表明这种算法能取得良好的分割结果。结论本文提出的基于互信息的图像配准和统计形状模型的分割算法,能够实现从体数据中自动定位解剖结构所在的图像位置并分割出目标结构。     

Landmark-guided diffeomorphic demons algorithm and its application to automatic segmentation of the whole spine and pelvis in CT images

Purpose

A fully automatic multiatlas-based method for segmentation of the spine and pelvis in a torso CT volume is proposed. A novel landmark-guided diffeomorphic demons algorithm is used to register a given CT image to multiple atlas volumes. This algorithm can utilize both grayscale image information and given landmark coordinate information optimally.

Methods

The segmentation has four steps. Firstly, 170 bony landmarks are detected in the given volume. Using these landmark positions, an atlas selection procedure is performed to reduce the computational cost of the following registration. Then the chosen atlas volumes are registered to the given CT image. Finally, voxelwise label voting is performed to determine the final segmentation result.

Results

The proposed method was evaluated using 50 torso CT datasets as well as the public SpineWeb dataset. As a result, a mean distance error of \(0.59\pm 0.14\hbox { mm}\) and a mean Dice coefficient of \(0.90\pm 0.02\) were achieved for the whole spine and the pelvic bones, which are competitive with other state-of-the-art methods.

Conclusion

From the experimental results, the usefulness of the proposed segmentation method was validated.

     

Renal compartment segmentation in DCE-MRI images

Renal compartment segmentation from Dynamic Contrast-Enhanced MRI (DCE-MRI) images is an important task for functional kidney evaluation. Despite advancement in segmentation methods, most of them focus on segmenting an entire kidney on CT images, there still lacks effective and automatic solutions for accurate segmentation of internal renal structures (i.e. cortex, medulla and renal pelvis) from DCE-MRI images. In this paper, we introduce a method for renal compartment segmentation which can robustly achieve high segmentation accuracy for a wide range of DCE-MRI data, and meanwhile requires little manual operations and parameter settings. The proposed method consists of five main steps. First, we pre-process the image time series to reduce the motion artifacts caused by the movement of the patients during the scans and enhance the kidney regions. Second, the kidney is segmented as a whole based on the concept of Maximally Stable Temporal Volume (MSTV). The proposed MSTV detects anatomical structures that are homogeneous in the spatial domain and stable in terms of temporal dynamics. MSTV-based kidney segmentation is robust to noises and does not require a training phase. It can well adapt to kidney shape variations caused by renal dysfunction. Third, voxels in the segmented kidney are described by principal components (PCs) to remove temporal redundancy and noises. And then k-means clustering of PCs is applied to separate voxels into multiple clusters. Fourth, the clusters are automatically labeled as cortex, medulla and pelvis based on voxels’ geometric locations and intensity distribution. Finally, an iterative refinement method is introduced to further remove noises in each segmented compartment. Experiments on 14 real clinical kidney datasets and 12 synthetic dataset demonstrate that results produced by our method match very well with those segmented manually and the performance of our method is superior to the other five existing methods.