Segmentation of the aorta in systolic phase from 4D flow MRI: multi-atlas vs. deep learning.

OBJECTIVE: In the management of the aortic aneurysm, 4D flow magnetic resonance Imaging provides valuable information for the computation of new biomarkers using computational fluid dynamics (CFD). However, accurate segmentation of the aorta is required. Thus, our objective is to evaluate the performance of two automatic segmentation methods on the calculation of aortic wall pressure. METHODS: Automatic segmentation of the aorta was performed with methods based on deep learning and multi-atlas using the systolic phase in the 4D flow MRI magnitude image of 36 patients. Using mesh morphing, isotopological meshes were generated, and CFD was performed to calculate the aortic wall pressure. Node-to-node comparisons of the pressure results were made to identify the most robust automatic method respect to the pressures obtained with a manually segmented model. RESULTS: Deep learning approach presented the best segmentation performance with a mean Dice similarity coefficient and a mean Hausdorff distance (HD) equal to 0.92+/- 0.02 and 21.02+/- 24.20 mm, respectively. At the global level HD is affected by the performance in the abdominal aorta. Locally, this distance decreases to 9.41+/- 3.45 and 5.82+/- 6.23 for the ascending and descending thoracic aorta, respectively. Moreover, with respect to the pressures from the manual segmentations, the differences in the pressures computed from deep learning were lower than those computed from multi-atlas method. CONCLUSION: To reduce biases in the calculation of aortic wall pressure, accurate segmentation is needed, particularly in regions with high blood flow velocities. Thus, the deep learning segmen-tation method should be preferred.

An Efficient Optimization Approach for Glioma Tumor Segmentation in Brain MRI.

Glioma is an aggressive type of cancer that develops in the brain or spinal cord. Due to many differences in its shape and appearance, accurate segmentation of glioma for identifying all parts of the tumor and its surrounding cancerous tissues is a challenging task. In recent researches, the combination of multi-atlas segmentation and machine learning methods provides robust and accurate results by learning from annotated atlas datasets. To overcome the side effects of limited existing information on atlas-based segmentation, and the long training phase of learning methods, we proposed a semi-supervised unified framework for multi-label segmentation that formulates this problem in terms of a Markov Random Field energy optimization on a parametric graph. To evaluate the proposed framework, we apply it to publicly available BRATS datasets, including low- and high-grade glioma tumors. Experimental results indicate competitive performance compared to the state-of-the-art methods. Compared with the top ranked methods, the proposed framework obtains the best dice score for segmenting of "whole tumor" (WT), "tumor core" (TC ) and "enhancing active tumor" (ET) regions. The achieved accuracy is 94[Formula: see text] characterized by the mean dice score. The motivation of using MRF graph is to map the segmentation problem to an optimization model in a graphical environment. Therefore, by defining perfect graph structure and optimum constraints and flows in the continuous max-flow model, the segmentation is performed precisely.

White-matter-nulled MPRAGE at 7T reveals thalamic lesions and atrophy of specific thalamic nuclei in multiple sclerosis.

BACKGROUND: Investigating the degeneration of specific thalamic nuclei in multiple sclerosis (MS) remains challenging. METHODS: White-matter-nulled (WMn) MPRAGE, MP-FLAIR, and standard T1-weighted magnetic resonance imaging (MRI) were performed on MS patients (n = 15) and matched controls (n = 12). Thalamic lesions were counted in individual sequences and lesion contrast-to-noise ratio (CNR) was measured. Volumes of 12 thalamic nuclei were measured using an automatic segmentation pipeline specifically developed for WMn-MPRAGE. RESULTS: WMn-MPRAGE showed more thalamic MS lesions (n = 35 in 9 out of 15 patients) than MP-FLAIR (n = 25) and standard T1 (n = 23), which was associated with significant improvement of CNR (p < 0.0001). MS patients had whole thalamus atrophy (p = 0.003) with lower volumes found for the anteroventral (p < 0.001), the pulvinar (p < 0.0001), and the habenular (p = 0.004) nuclei. CONCLUSION: WMn-MPRAGE and automatic thalamic segmentation can highlight thalamic MS lesions and measure patterns of focal thalamic atrophy.

Thalamus Optimized Multi Atlas Segmentation (THOMAS): fast, fully automated segmentation of thalamic nuclei from structural MRI.

The thalamus and its nuclei are largely indistinguishable on standard T1 or T2 weighted MRI. While diffusion tensor imaging based methods have been proposed to segment the thalamic nuclei based on the angular orientation of the principal diffusion tensor, these are based on echo planar imaging which is inherently limited in spatial resolution and suffers from distortion. We present a multi-atlas segmentation technique based on white-matter-nulled MP-RAGE imaging that segments the thalamus into 12 nuclei with computation times on the order of 10 min on a desktop PC; we call this method THOMAS (THalamus Optimized Multi Atlas Segmentation). THOMAS was rigorously evaluated on 7T MRI data acquired from healthy volunteers and patients with multiple sclerosis by comparing against manual segmentations delineated by a neuroradiologist, guided by the Morel atlas. Segmentation accuracy was very high, with uniformly high Dice indices: at least 0.85 for large nuclei like the pulvinar and mediodorsal nuclei and at least 0.7 even for small structures such as the habenular, centromedian, and lateral and medial geniculate nuclei. Volume similarity indices ranged from 0.82 for the smaller nuclei to 0.97 for the larger nuclei. Volumetry revealed that the volumes of the right anteroventral, right ventral posterior lateral, and both right and left pulvinar nuclei were significantly lower in MS patients compared to controls, after adjusting for age, sex and intracranial volume. Lastly, we evaluated the potential of this method for targeting the Vim nucleus for deep brain surgery and focused ultrasound thalamotomy by overlaying the Vim nucleus segmented from pre-operative data on post-operative data. The locations of the ablated region and active DBS contact corresponded well with the segmented Vim nucleus. Our fast, direct structural MRI based segmentation method opens the door for MRI guided intra-operative procedures like thalamotomy and asleep DBS electrode placement as well as for accurate quantification of thalamic nuclear volumes to follow progression of neurological disorders.

Multi-atlas active contour segmentation method using template optimization algorithm.

BACKGROUND: Brain image segmentation is the basis and key to brain disease diagnosis, treatment planning and tissue 3D reconstruction. The accuracy of segmentation directly affects the therapeutic effect. Manual segmentation of these images is time-consuming and subjective. Therefore, it is important to research semi-automatic and automatic image segmentation methods. In this paper, we propose a semi-automatic image segmentation method combined with a multi-atlas registration method and an active contour model (ACM). METHOD: We propose a multi-atlas active contour segmentation method using a template optimization algorithm. First, a multi-atlas registration method is used to obtain the prior shape information of the target tissue, and then a label fusion algorithm is used to generate the initial template. Second, a template optimization algorithm is used to reduce the multi-atlas registration errors and generate the initial active contour (IAC). Finally, a ACM is used to segment the target tissue. RESULTS: The proposed method was applied to the challenging publicly available MR datasets IBSR and MRBrainS13. In the MRBrainS13 datasets, we obtained an average thalamus Dice similarity coefficient of 0.927 ± 0.014 and an average Hausdorff distance (HD) of 2.92 ± 0.53. In the IBSR datasets, we obtained a white matter (WM) average Dice similarity coefficient of 0.827 ± 0.04 and a gray gray matter (GM) average Dice similarity coefficient of 0.853 ± 0.03. CONCLUSION: In this paper, we propose a semi-automatic brain image segmentation method. The main contributions of this paper are as follows: 1) Our method uses a multi-atlas registration method based on affine transformation, which effectively reduces the multi-atlas registration time compared to the complex nonlinear registration method. The average registration time of each target image in the IBSR datasets is 255 s, and the average registration time of each target image in the MRBrainS13 datasets is 409 s. 2) We used a template optimization algorithm to improve registration error and generate a continuous IAC. 3) Finally, we used a ACM to segment the target tissue and obtain a smooth continuous target contour.

Anthropometer3D: Automatic Multi-Slice Segmentation Software for the Measurement of Anthropometric Parameters from CT of PET/CT.

Anthropometric parameters like muscle body mass (MBM), fat body mass (FBM), lean body mass (LBM), visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT) are used in oncology. Our aim was to develop and evaluate the software Anthropometer3D measuring these anthropometric parameters on the CT of PET/CT. This software performs a multi-atlas segmentation of CT of PET/CT with extrapolation coefficients for the body parts beyond the usual acquisition range (from the ischia to the eyes). The multi-atlas database is composed of 30 truncated CTs manually segmented to isolate three types of voxels (muscle, fat, and visceral fat). To evaluate Anthropomer3D, a leave-one-out cross-validation was performed to measure MBM, FBM, LBM, VAT, and SAT. The reference standard was based on the manual segmentation of the corresponding whole-body CT. A manual segmentation of one CT slice at level L3 was also used. Correlations were analyzed using Dice coefficient, intra-class coefficient correlation (ICC), and Bland-Altman plot. The population was heterogeneous (sex ratio 1:1; mean age 57 years old [min 23; max 74]; mean BMI 27 kg/m2 [min 18; max 40]). Dice coefficients between reference standard and Anthropometer3D were excellent (mean+/-SD): muscle 0.95 ± 0.02, fat 1.00 ± 0.01, and visceral fat 0.97 ± 0.02. The ICC was almost perfect (minimal value of 95% CI of 0.97). All Bland-Altman plot values (mean difference, 95% CI and slopes) were better for Anthropometer3D compared to L3 level segmentation. Anthropometer3D allows multiple anthropometric measurements based on an automatic multi-slice segmentation. It is more precise than estimates using L3 level segmentation.

Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases.

As longitudinal and multi-site studies become increasingly frequent in neuroimaging, maintaining longitudinal and inter-scanner consistency of brain parcellation has become a major challenge due to variation in scanner models and/or image acquisition protocols across scanners and sites. We present a new automated segmentation method specifically designed to achieve a consistent parcellation of anatomical brain structures in such heterogeneous datasets. Our method combines a site-specific atlas creation strategy with a state-of-the-art multi-atlas anatomical label fusion framework. Site-specific atlases are computed such that they preserve image intensity characteristics of each site's scanner and acquisition protocol, while atlas pairs share anatomical labels in a way consistent with inter-scanner acquisition variations. This harmonization of atlases improves inter-study and longitudinal consistency of segmentations in the subsequent consensus labeling step. We tested this approach on a large sample of older adults from the Baltimore Longitudinal Study of Aging (BLSA) who had longitudinal scans acquired using two scanners that vary with respect to vendor and image acquisition protocol. We compared the proposed method to standard multi-atlas segmentation for both cross-sectional and longitudinal analyses. The harmonization significantly reduced scanner-related differences in the age trends of ROI volumes, improved longitudinal consistency of segmentations, and resulted in higher across-scanner intra-class correlations, particularly in the white matter.

Supervoxel based method for multi-atlas segmentation of brain MR images.

Multi-atlas segmentation has been widely applied to the analysis of brain MR images. However, the state-of-the-art techniques in multi-atlas segmentation, including both patch-based and learning-based methods, are strongly dependent on the pairwise registration or exhibit huge spatial inconsistency. The paper proposes a new segmentation framework based on supervoxels to solve the existing challenges of previous methods. The supervoxel is an aggregation of voxels with similar attributes, which can be used to replace the voxel grid. By formulating the segmentation as a tissue labeling problem associated with a maximum-a-posteriori inference in Markov random field, the problem is solved via a graphical model with supervoxels being considered as the nodes. In addition, a dense labeling scheme is developed to refine the supervoxel labeling results, and the spatial consistency is incorporated in the proposed method. The proposed approach is robust to the pairwise registration errors and of high computational efficiency. Extensive experimental evaluations on three publically available brain MR datasets demonstrate the effectiveness and superior performance of the proposed approach.

An efficient and accurate method for robust inter-dataset brain extraction and comparisons with 9 other methods.

Brain extraction is an important first step in many magnetic resonance neuroimaging studies. Due to variability in brain morphology and in the appearance of the brain due to differences in scanner acquisition parameters, the development of a generally applicable brain extraction algorithm has proven challenging. Learning-based brain extraction algorithms in particular perform well when the target and training images are sufficiently similar, but often perform worse when this condition is not met. In this study, we propose a new patch-based multi-atlas segmentation method for brain extraction which is specifically developed for accurate and robust processing across datasets. Using a diverse collection of labeled images from 5 different datasets, extensive comparisons were made with 9 other commonly used brain extraction methods, both before and after applying error correction (a machine learning method for automatically correcting segmentation errors) to each method. The proposed method performed equal to or better than the other methods in each of two segmentation scenarios: a challenging inter-dataset segmentation scenario in which no dataset-specific atlases were used (mean Dice coefficient 98.57%, volumetric correlation 0.994 across datasets following error correction), and an intra-dataset segmentation scenario in which only dataset-specific atlases were used (mean Dice coefficient 99.02%, volumetric correlation 0.998 across datasets following error correction). Furthermore, combined with error correction, the proposed method runs in less than one-tenth of the time required by the other top-performing methods in the challenging inter-dataset comparisons. Validation on an independent multi-centre dataset also confirmed the excellent performance of the proposed method.

Multi-object Model-Based Multi-atlas Segmentation Constrained Grid Cut for Automatic Segmentation of Lumbar Vertebrae from CT Images.

In this chapter, we present a multi-object model-based multi-atlas segmentation constrained grid cut method for automatic segmentation of lumbar vertebrae from a given lumbar spinal CT image. More specifically, our automatic lumbar vertebrae segmentation method consists of two steps: affine atlas-target registration-based label fusion and bone-sheetness assisted multi-label grid cut which has the inherent advantage of automatic separation of the five lumbar vertebrae from each other. We evaluate our method on 21 clinical lumbar spinal CT images with the associated manual segmentation and conduct a leave-one-out study. Our method achieved an average Dice coefficient of 93.9 ± 1.0% and an average symmetric surface distance of 0.41 ± 0.08 mm.

Simultaneous total intracranial volume and posterior fossa volume estimation using multi-atlas label fusion.

Total intracranial volume (TICV) is an essential covariate in brain volumetric analyses. The prevalent brain imaging software packages provide automatic TICV estimates. FreeSurfer and FSL estimate TICV using a scaling factor while SPM12 accumulates probabilities of brain tissues. None of the three provide explicit skull/CSF boundary (SCB) since it is challenging to distinguish these dark structures in a T1-weighted image. However, explicit SCB not only leads to a natural way of obtaining TICV (i.e., counting voxels inside the skull) but also allows sub-definition of TICV, for example, the posterior fossa volume (PFV). In this article, they proposed to use multi-atlas label fusion to obtain TICV and PFV simultaneously. The main contributions are: (1) TICV and PFV are simultaneously obtained with explicit SCB from a single T1-weighted image. (2) TICV and PFV labels are added to the widely used BrainCOLOR atlases. (3) Detailed mathematical derivation of non-local spatial STAPLE (NLSS) label fusion is presented. As the skull is clearly distinguished in CT images, we use a semi-manual procedure to obtain atlases with TICV and PFV labels using 20 subjects who both have a MR and CT scan. The proposed method provides simultaneous TICV and PFV estimation while achieving more accurate TICV estimation compared with FreeSurfer, FSL, SPM12, and the previously proposed STAPLE based approach. The newly developed TICV and PFV labels for the OASIS BrainCOLOR atlases provide acceptable performance, which enables simultaneous TICV and PFV estimation during whole brain segmentation. The NLSS method and the new atlases have been made freely available. Hum Brain Mapp 38:599-616, 2017. © 2016 Wiley Periodicals, Inc.

Robust multi-atlas label propagation by deep sparse representation.

Recently, multi-atlas patch-based label fusion has achieved many successes in medical imaging area. The basic assumption in the current state-of-the-art approaches is that the image patch at the target image point can be represented by a patch dictionary consisting of atlas patches from registered atlas images. Therefore, the label at the target image point can be determined by fusing labels of atlas image patches with similar anatomical structures. However, such assumption on image patch representation does not always hold in label fusion since (1) the image content within the patch may be corrupted due to noise and artifact; and (2) the distribution of morphometric patterns among atlas patches might be unbalanced such that the majority patterns can dominate label fusion result over other minority patterns. The violation of the above basic assumptions could significantly undermine the label fusion accuracy. To overcome these issues, we first consider forming label-specific group for the atlas patches with the same label. Then, we alter the conventional flat and shallow dictionary to a deep multi-layer structure, where the top layer (label-specific dictionaries) consists of groups of representative atlas patches and the subsequent layers (residual dictionaries) hierarchically encode the patchwise residual information in different scales. Thus, the label fusion follows the representation consensus across representative dictionaries. However, the representation of target patch in each group is iteratively optimized by using the representative atlas patches in each label-specific dictionary exclusively to match the principal patterns and also using all residual patterns across groups collaboratively to overcome the issue that some groups might be absent of certain variation patterns presented in the target image patch. Promising segmentation results have been achieved in labeling hippocampus on ADNI dataset, as well as basal ganglia and brainstem structures, compared to other counterpart label fusion methods.

MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection.

Atlas-based automated anatomical labeling is a fundamental tool in medical image segmentation, as it defines regions of interest for subsequent analysis of structural and functional image data. The extensive investigation of multi-atlas warping and fusion techniques over the past 5 or more years has clearly demonstrated the advantages of consensus-based segmentation. However, the common approach is to use multiple atlases with a single registration method and parameter set, which is not necessarily optimal for every individual scan, anatomical region, and problem/data-type. Different registration criteria and parameter sets yield different solutions, each providing complementary information. Herein, we present a consensus labeling framework that generates a broad ensemble of labeled atlases in target image space via the use of several warping algorithms, regularization parameters, and atlases. The label fusion integrates two complementary sources of information: a local similarity ranking to select locally optimal atlases and a boundary modulation term to refine the segmentation consistently with the target image's intensity profile. The ensemble approach consistently outperforms segmentations using individual warping methods alone, achieving high accuracy on several benchmark datasets. The MUSE methodology has been used for processing thousands of scans from various datasets, producing robust and consistent results. MUSE is publicly available both as a downloadable software package, and as an application that can be run on the CBICA Image Processing Portal (https://ipp.cbica.upenn.edu), a web based platform for remote processing of medical images.

Consistent cortical reconstruction and multi-atlas brain segmentation.

Whole brain segmentation and cortical surface reconstruction are two essential techniques for investigating the human brain. Spatial inconsistences, which can hinder further integrated analyses of brain structure, can result due to these two tasks typically being conducted independently of each other. FreeSurfer obtains self-consistent whole brain segmentations and cortical surfaces. It starts with subcortical segmentation, then carries out cortical surface reconstruction, and ends with cortical segmentation and labeling. However, this "segmentation to surface to parcellation" strategy has shown limitations in various cohorts such as older populations with large ventricles. In this work, we propose a novel "multi-atlas segmentation to surface" method called Multi-atlas CRUISE (MaCRUISE), which achieves self-consistent whole brain segmentations and cortical surfaces by combining multi-atlas segmentation with the cortical reconstruction method CRUISE. A modification called MaCRUISE(+) is designed to perform well when white matter lesions are present. Comparing to the benchmarks CRUISE and FreeSurfer, the surface accuracy of MaCRUISE and MaCRUISE(+) is validated using two independent datasets with expertly placed cortical landmarks. A third independent dataset with expertly delineated volumetric labels is employed to compare segmentation performance. Finally, 200MR volumetric images from an older adult sample are used to assess the robustness of MaCRUISE and FreeSurfer. The advantages of MaCRUISE are: (1) MaCRUISE constructs self-consistent voxelwise segmentations and cortical surfaces, while MaCRUISE(+) is robust to white matter pathology. (2) MaCRUISE achieves more accurate whole brain segmentations than independently conducting the multi-atlas segmentation. (3) MaCRUISE is comparable in accuracy to FreeSurfer (when FreeSurfer does not exhibit global failures) while achieving greater robustness across an older adult population. MaCRUISE has been made freely available in open source.

Automatic and quantitative assessment of regional muscle volume by multi-atlas segmentation using whole-body water-fat MRI.

PURPOSE: To develop and demonstrate a rapid whole-body magnetic resonance imaging (MRI) method for automatic quantification of total and regional skeletal muscle volume. MATERIALS AND METHODS: The method was based on a multi-atlas segmentation of intensity corrected water-fat separated image volumes. Automatic lean muscle tissue segmentations were achieved by nonrigid registration of atlas datasets with 10 different manually segmented muscle groups. Ten subjects scanned at 1.5 T and 3.0 T were used as atlases, initial validation and optimization. Further validation used 11 subjects scanned at 3.0 T. The automated and manual segmentations were compared using intraclass correlation, true positive volume fractions, and delta volumes. RESULTS: For the 1.5 T datasets, the intraclass correlation, true positive volume fractions (mean ± standard deviation, SD), and delta volumes (mean ± SD) were 0.99, 0.91 ± 0.02, -0.10 ± 0.70L (whole body), 0.99, 0.93 ± 0.02, 0.01 ± 0.07L (left anterior thigh), and 0.98, 0.80 ± 0.07, -0.08 ± 0.15L (left abdomen). The corresponding values at 3.0 T were 0.97, 0.92 ± 0.03, -0.17 ± 1.37L (whole body), 0.99, 0.93 ± 0.03, 0.03 ± 0.08L (left anterior thigh), and 0.89, 0.90 ± 0.04, -0.03 ± 0.42L (left abdomen). The validation datasets showed similar results. CONCLUSION: The method accurately quantified the whole-body skeletal muscle volume and the volume of separate muscle groups independent of field strength and image resolution.

Performance of single and multi-atlas based automated landmarking methods compared to expert annotations in volumetric microCT datasets of mouse mandibles.

BACKGROUND: Here we present an application of advanced registration and atlas building framework DRAMMS to the automated annotation of mouse mandibles through a series of tests using single and multi-atlas segmentation paradigms and compare the outcomes to the current gold standard, manual annotation. RESULTS: Our results showed multi-atlas annotation procedure yields landmark precisions within the human observer error range. The mean shape estimates from gold standard and multi-atlas annotation procedure were statistically indistinguishable for both Euclidean Distance Matrix Analysis (mean form matrix) and Generalized Procrustes Analysis (Goodall F-test). Further research needs to be done to validate the consistency of variance-covariance matrix estimates from both methods with larger sample sizes. CONCLUSION: Multi-atlas annotation procedure shows promise as a framework to facilitate truly high-throughput phenomic analyses by channeling investigators efforts to annotate only a small portion of their datasets.

Deep label fusion: A generalizable hybrid multi-atlas and deep convolutional neural network for medical image segmentation.

Deep convolutional neural networks (DCNN) achieve very high accuracy in segmenting various anatomical structures in medical images but often suffer from relatively poor generalizability. Multi-atlas segmentation (MAS), while less accurate than DCNN in many applications, tends to generalize well to unseen datasets with different characteristics from the training dataset. Several groups have attempted to integrate the power of DCNN to learn complex data representations and the robustness of MAS to changes in image characteristics. However, these studies primarily focused on replacing individual components of MAS with DCNN models and reported marginal improvements in accuracy. In this study we describe and evaluate a 3D end-to-end hybrid MAS and DCNN segmentation pipeline, called Deep Label Fusion (DLF). The DLF pipeline consists of two main components with learnable weights, including a weighted voting subnet that mimics the MAS algorithm and a fine-tuning subnet that corrects residual segmentation errors to improve final segmentation accuracy. We evaluate DLF on five datasets that represent a diversity of anatomical structures (medial temporal lobe subregions and lumbar vertebrae) and imaging modalities (multi-modality, multi-field-strength MRI and Computational Tomography). These experiments show that DLF achieves comparable segmentation accuracy to nnU-Net (Isensee et al., 2020), the state-of-the-art DCNN pipeline, when evaluated on a dataset with similar characteristics to the training datasets, while outperforming nnU-Net on tasks that involve generalization to datasets with different characteristics (different MRI field strength or different patient population). DLF is also shown to consistently improve upon conventional MAS methods. In addition, a modality augmentation strategy tailored for multimodal imaging is proposed and demonstrated to be beneficial in improving the segmentation accuracy of learning-based methods, including DLF and DCNN, in missing data scenarios in test time as well as increasing the interpretability of the contribution of each individual modality.

HGM-cNet: Integrating hippocampal gray matter probability map into a cascaded deep learning framework improves hippocampus segmentation.

A robust cascaded deep learning framework with integrated hippocampal gray matter (HGM) probability map was developed to improve the hippocampus segmentation (called HGM-cNet) due to its significance in various neuropsychiatric disorders such as Alzheimer's disease (AD). Particularly, the HGM-cNet cascaded two identical convolutional neural networks (CNN), where each CNN was devised by incorporating Attention Block, Residual Block, and DropBlock into the typical encoder-decoder architecture. The two CNNs were skip-connected between encoder components at each scale. The adoption of the cascaded deep learning framework was to conveniently incorporate the HGM probability map with the feature map generated by the first CNN. Experiments on 135T1-weighted MRI scans and manual hippocampal labels from publicly available ADNI-HarP dataset demonstrated that the proposed HGM-cNet outperformed seven multi-atlas-based hippocampus segmentation methods and six deep learning methods under comparison in most evaluation metrics. The Dice (average > 0.89 for both left and right hippocampus) was increased by around or more than 1% over other methods. The HGM-cNet also achieved a superior hippocampus segmentation performance in each group of cognitive normal, mild cognitive impairment, and AD. The stability, conveniences and generalizability of the cascaded deep learning framework with integrated HGM probability map in improving hippocampus segmentation was validated by replacing the proposed CNN with 3D-UNet, Atten-UNet, HippoDeep, QuickNet, DeepHarp, and TransBTS models. The integration of the HGM probability map in the cascaded deep learning framework was also demonstrated to facilitate capturing hippocampal atrophy more accurately than alternative methods in AD analysis. The codes are publicly available at https://github.com/Liu1436510768/HGM-cNet.git.

DeepHeartCT: A fully automatic artificial intelligence hybrid framework based on convolutional neural network and multi-atlas segmentation for multi-structure cardiac computed tomography angiography image segmentation.

Cardiac computed tomography angiography (CTA) is an emerging imaging modality for assessing coronary artery as well as various cardiovascular structures. Recently, deep learning (DL) methods have been successfully applied to many applications of medical image analysis including cardiac CTA structure segmentation. However, DL requires a large amounts of data and high-quality labels for training which can be burdensome to obtain due to its labor-intensive nature. In this study, we aim to develop a fully automatic artificial intelligence (AI) system, named DeepHeartCT, for accurate and rapid cardiac CTA segmentation based on DL. The proposed system was trained using a large clinical dataset with computer-generated labels to segment various cardiovascular structures including left and right ventricles (LV, RV), left and right atria (LA, RA), and LV myocardium (LVM). This new system was trained directly using high-quality computer labels generated from our previously developed multi-atlas based AI system. In addition, a reverse ranking strategy was proposed to assess the segmentation quality in the absence of manual reference labels. This strategy allowed the new framework to assemble optimal computer-generated labels from a large dataset for effective training of a deep convolutional neural network (CNN). A large clinical cardiac CTA studies (n = 1,064) were used to train and validate our framework. The trained model was then tested on another independent dataset with manual labels (n = 60). The Dice score, Hausdorff distance and mean surface distance were used to quantify the segmentation accuracy. The proposed DeepHeartCT framework yields a high median Dice score of 0.90 [interquartile range (IQR), 0.90-0.91], a low median Hausdorff distance of 7 mm (IQR, 4-15 mm) and a low mean surface distance of 0.80 mm (IQR, 0.57-1.29 mm) across all segmented structures. An additional experiment was conducted to evaluate the proposed DL-based AI framework trained with a small vs. large dataset. The results show our framework also performed well when trained on a small optimal training dataset (n = 110) with a significantly reduced training time. These results demonstrated that the proposed DeepHeartCT framework provides accurate and rapid cardiac CTA segmentation that can be readily generalized for handling large-scale medical imaging applications.

VOTENET++: REGISTRATION REFINEMENT FOR MULTI-ATLAS SEGMENTATION.

Multi-atlas segmentation (MAS) is a popular image segmentation technique for medical images. In this work, we improve the performance of MAS by correcting registration errors before label fusion. Specifically, we use a volumetric displacement field to refine registrations based on image anatomical appearance and predicted labels. We show the influence of the initial spatial alignment as well as the beneficial effect of using label information for MAS performance. Experiments demonstrate that the proposed refinement approach improves MAS performance on a 3D magnetic resonance dataset of the knee.