Consistent segmentation using a Rician classifier

Automatic development of 3D anatomical models of border zone and core scar regions in the left ventricle

Patients with myocardial infarction are at elevated risk of sudden cardiac death, and scar tissue arising from infarction is known to play a role. The accurate identification of scars therefore is crucial for risk assessment, quantification and guiding interventions. Typically, core scars and grey peripheral zones are identified by radiologists and clinicians based on cardiac late gadolinium enhancement magnetic resonance images (LGE-MRI). Scar regions from LGE-MRI vary in size, shape, heterogeneity, artifacts, and image resolution. Thus, manual segmentation is time consuming, and influenced by the observer's experience (bias effect). We propose a fully automatic framework that develops 3D anatomical models of the left ventricle with border zone and core scar regions that are free from bias effect. Our myocardium (SOCRATIS), border scar and core scar (BZ-SOCRATIS) segmentation pipelines were evaluated using internal and external validation datasets. The automatic myocardium segmentation framework performed a Dice score of 81.9% and 70.0% in the internal and external validation dataset. The automatic scar segmentation pipeline achieved a Dice score of 60.9% for the core scar segmentation and 43.7% for the border zone scar segmentation in the internal dataset and in the external dataset a Dice score of 44.2% for the core scar segmentation and 54.8% for the border scar segmentation respectively. To the best of our knowledge, this is the first study outlining a fully automatic framework to develop 3D anatomical models of the left ventricle with border zone and core scar regions. Our method exhibits high performance without the need for training or tuning in an unseen cohort (unsupervised).

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

In this paper, we propose a novel squeeze M-SegNet (SM-SegNet) architecture featuring a fire module to perform accurate as well as fast segmentation of the brain on magnetic resonance imaging (MRI) scans. The proposed model utilizes uniform input patches, combined-connections, long skip connections, and squeeze-expand convolutional layers from the fire module to segment brain MRI data. The proposed SM-SegNet architecture involves a multi-scale deep network on the encoder side and deep supervision on the decoder side, which uses combined-connections (skip connections and pooling indices) from the encoder to the decoder layer. The multi-scale side input layers support the deep network layers' extraction of discriminative feature information, and the decoder side provides deep supervision to reduce the gradient problem. By using combined-connections, extracted features can be transferred from the encoder to the decoder resulting in recovering spatial information, which makes the model converge faster. Long skip connections were used to stabilize the gradient updates in the network. Owing to the adoption of the fire module, the proposed model was significantly faster to train and offered a more efficient memory usage with 83% fewer parameters than previously developed methods, owing to the adoption of the fire module. The proposed method was evaluated using the open-access series of imaging studies (OASIS) and the internet brain segmentation registry (IBSR) datasets. The experimental results demonstrate that the proposed SM-SegNet architecture achieves segmentation accuracies of 95% for cerebrospinal fluid, 95% for gray matter, and 96% for white matter, which outperforms the existing methods in both subjective and objective metrics in brain MRI segmentation.

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).

Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture

Accurate segmentation of brain magnetic resonance imaging (MRI) is an essential step in quantifying the changes in brain structure. Deep learning in recent years has been extensively used for brain image segmentation with highly promising performance. In particular, the U-net architecture has been widely used for segmentation in various biomedical related fields. In this paper, we propose a patch-wise U-net architecture for the automatic segmentation of brain structures in structural MRI. In the proposed brain segmentation method, the non-overlapping patch-wise U-net is used to overcome the drawbacks of conventional U-net with more retention of local information. In our proposed method, the slices from an MRI scan are divided into non-overlapping patches that are fed into the U-net model along with their corresponding patches of ground truth so as to train the network. The experimental results show that the proposed patch-wise U-net model achieves a Dice similarity coefficient (DSC) score of 0.93 in average and outperforms the conventional U-net and the SegNet-based methods by 3% and 10%, respectively, for on Open Access Series of Imaging Studies (OASIS) and Internet Brain Segmentation Repository (IBSR) dataset.

Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.

Random forest regression for magnetic resonance image synthesis

By choosing different pulse sequences and their parameters, magnetic resonance imaging (MRI) can generate a large variety of tissue contrasts. This very flexibility, however, can yield inconsistencies with MRI acquisitions across datasets or scanning sessions that can in turn cause inconsistent automated image analysis. Although image synthesis of MR images has been shown to be helpful in addressing this problem, an inability to synthesize both T2-weighted brain images that include the skull and FLuid Attenuated Inversion Recovery (FLAIR) images has been reported. The method described herein, called REPLICA, addresses these limitations. REPLICA is a supervised random forest image synthesis approach that learns a nonlinear regression to predict intensities of alternate tissue contrasts given specific input tissue contrasts. Experimental results include direct image comparisons between synthetic and real images, results from image analysis tasks on both synthetic and real images, and comparison against other state-of-the-art image synthesis methods. REPLICA is computationally fast, and is shown to be comparable to other methods on tasks they are able to perform. Additionally REPLICA has the capability to synthesize both T2-weighted images of the full head and FLAIR images, and perform intensity standardization between different imaging datasets.

MR image synthesis by contrast learning on neighborhood ensembles

Automatic processing of magnetic resonance images is a vital part of neuroscience research. Yet even the best and most widely used medical image processing methods will not produce consistent results when their input images are acquired with different pulse sequences. Although intensity standardization and image synthesis methods have been introduced to address this problem, their performance remains dependent on knowledge and consistency of the pulse sequences used to acquire the images. In this paper, an image synthesis approach that first estimates the pulse sequence parameters of the subject image is presented. The estimated parameters are then used with a collection of atlas or training images to generate a new atlas image having the same contrast as the subject image. This additional image provides an ideal source from which to synthesize any other target pulse sequence image contained in the atlas. In particular, a nonlinear regression intensity mapping is trained from the new atlas image to the target atlas image and then applied to the subject image to yield the particular target pulse sequence within the atlas. Both intensity standardization and synthesis of missing tissue contrasts can be achieved using this framework. The approach was evaluated on both simulated and real data, and shown to be superior in both intensity standardization and synthesis to other established methods.

Three-dimensional brain magnetic resonance imaging segmentation via knowledge-driven decision theory

Brain tissue segmentation on magnetic resonance (MR) imaging is a difficult task because of significant intensity overlap between the tissue classes. We present a new knowledge-driven decision theory (KDT) approach that incorporates prior information of the relative extents of intensity overlap between tissue class pairs for volumetric MR tissue segmentation. The proposed approach better handles intensity overlap between tissues without explicitly employing methods for removal of MR image corruptions (such as bias field). Adaptive tissue class priors are employed that combine probabilistic atlas maps with spatial contextual information obtained from Markov random fields to guide tissue segmentation. The energy function is minimized using a variational level-set-based framework, which has shown great promise for MR image analysis. We evaluate the proposed method on two well-established real MR datasets with expert ground-truth segmentations and compare our approach against existing segmentation methods. KDT has low-computational complexity and shows better segmentation performance than other segmentation methods evaluated using these MR datasets.

Comparison of 10 brain tissue segmentation methods using revisited IBSR annotations

PURPOSE

Ground-truth annotations from the well-known Internet Brain Segmentation Repository (IBSR) datasets consider Sulcal cerebrospinal fluid (SCSF) voxels as gray matter. This can lead to bias when evaluating the performance of tissue segmentation methods. In this work we compare the accuracy of 10 brain tissue segmentation methods analyzing the effects of SCSF ground-truth voxels on accuracy estimations.

MATERIALS AND METHODS

The set of methods is composed by FAST, SPM5, SPM8, GAMIXTURE, ANN, FCM, KNN, SVPASEG, FANTASM, and PVC. Methods are evaluated using original IBSR ground-truth and ranked by means of their performance on pairwise comparisons using permutation tests. Afterward, the evaluation is repeated using IBSR ground-truth without considering SCSF.

RESULTS

The Dice coefficient of all methods is affected by changes in SCSF annotations, especially on SPM5, SPM8 and FAST. When not considering SCSF voxels, SVPASEG (0.90 ± 0.01) and SPM8 (0.91 ± 0.01) are the methods from our study that appear more suitable for gray matter tissue segmentation, while FAST (0.89 ± 0.02) is the best tool for segmenting white matter tissue.

CONCLUSION

The performance and the accuracy of methods on IBSR images vary notably when not considering SCSF voxels. The fact that three of the most common methods (FAST, SPM5, and SPM8) report an important change in their accuracy suggest to consider these differences in labeling for new comparative studies.

Magnetic Resonance Image Example-Based Contrast Synthesis

The performance of image analysis algorithms applied to magnetic resonance images is strongly influenced by the pulse sequences used to acquire the images. Algorithms are typically optimized for a targeted tissue contrast obtained from a particular implementation of a pulse sequence on a specific scanner. There are many practical situations, including multi-institution trials, rapid emergency scans, and scientific use of historical data, where the images are not acquired according to an optimal protocol or the desired tissue contrast is entirely missing. This paper introduces an image restoration technique that recovers images with both the desired tissue contrast and a normalized intensity profile. This is done using patches in the acquired images and an atlas containing patches of the acquired and desired tissue contrasts. The method is an example-based approach relying on sparse reconstruction from image patches. Its performance in demonstrated using several examples, including image intensity normalization, missing tissue contrast recovery, automatic segmentation, and multimodal registration. These examples demonstrate potential practical uses and also illustrate limitations of our approach.

Automatic segmentation of corpus callosum using Gaussian mixture modeling and Fuzzy C means methods

This paper presents a comparative study of the success and performance of the Gaussian mixture modeling and Fuzzy C means methods to determine the volume and cross-sectionals areas of the corpus callosum (CC) using simulated and real MR brain images. The Gaussian mixture model (GMM) utilizes weighted sum of Gaussian distributions by applying statistical decision procedures to define image classes. In the Fuzzy C means (FCM), the image classes are represented by certain membership function according to fuzziness information expressing the distance from the cluster centers. In this study, automatic segmentation for midsagittal section of the CC was achieved from simulated and real brain images. The volume of CC was obtained using sagittal sections areas. To compare the success of the methods, segmentation accuracy, Jaccard similarity and time consuming for segmentation were calculated. The results show that the GMM method resulted by a small margin in more accurate segmentation (midsagittal section segmentation accuracy 98.3% and 97.01% for GMM and FCM); however the FCM method resulted in faster segmentation than GMM. With this study, an accurate and automatic segmentation system that allows opportunity for quantitative comparison to doctors in the planning of treatment and the diagnosis of diseases affecting the size of the CC was developed. This study can be adapted to perform segmentation on other regions of the brain, thus, it can be operated as practical use in the clinic.