Automated segmentation of mouse brain images using extended MRF

Utilizing deep learning via the 3D U-net neural network for the delineation of brain stroke lesions in MRI image

The segmentation of acute stroke lesions plays a vital role in healthcare by assisting doctors in making prompt and well-informed treatment choices. Although Magnetic Resonance Imaging (MRI) is a time-intensive procedure, it produces high-fidelity images widely regarded as the most reliable diagnostic tool available. Employing deep learning techniques for automated stroke lesion segmentation can offer valuable insights into the precise location and extent of affected tissue, enabling medical professionals to effectively evaluate treatment risks and make informed assessments. In this research, a deep learning approach is introduced for segmenting acute and sub-acute stroke lesions from MRI images. To enhance feature learning through brain hemisphere symmetry, pre-processing techniques are applied to the data. To tackle the class imbalance challenge, we employed a strategy of using small patches with balanced sampling during training, along with a dynamically weighted loss function that incorporates f1-score and IOU-score (Intersection over Union). Furthermore, the 3D U-Net architecture is used to generate predictions for complete patches, employing a high degree of overlap between patches to minimize the requirement for subsequent post-processing steps. The 3D U-Net model, utilizing ResnetV2 as the pre-trained encoder for IOU-score and Seresnext101 for f1-score, stands as the leading state-of-the-art (SOTA) model for segmentation tasks. However, recent research has introduced a novel model that surpasses these metrics and demonstrates superior performance compared to other backbone architectures. The f1-score and IOU-score were computed for various backbones, with Seresnext101 achieving the highest f1-score and ResnetV2 performing the highest IOU-score. These calculations were conducted using a threshold value of 0.5. This research proposes a valuable model based on transfer learning for the classification of brain diseases in MRI scans. The achieved f1-score using the recommended classifiers demonstrates the effectiveness of the approach employed in this study. The findings indicate that Seresnext101 attains the highest f1-score of 0.94226, while ResnetV2 achieves the best IOU-score of 0.88342, making it the preferred architecture for segmentation methods. Furthermore, the study presents experimental results of the 3D U-Net model applied to brain stroke lesion segmentation, suggesting prospects for researchers interested in segmenting brain strokes and enhancing 3D U-Net models.

Automatic Cerebral Hemisphere Segmentation in Rat MRI with Ischemic Lesions via Attention-based Convolutional Neural Networks

We present MedicDeepLabv3+, a convolutional neural network that is the first completely automatic method to segment cerebral hemispheres in magnetic resonance (MR) volumes of rats with ischemic lesions. MedicDeepLabv3+ improves the state-of-the-art DeepLabv3+ with an advanced decoder, incorporating spatial attention layers and additional skip connections that, as we show in our experiments, lead to more precise segmentations. MedicDeepLabv3+ requires no MR image preprocessing, such as bias-field correction or registration to a template, produces segmentations in less than a second, and its GPU memory requirements can be adjusted based on the available resources. We optimized MedicDeepLabv3+ and six other state-of-the-art convolutional neural networks (DeepLabv3+, UNet, HighRes3DNet, V-Net, VoxResNet, Demon) on a heterogeneous training set comprised by MR volumes from 11 cohorts acquired at different lesion stages. Then, we evaluated the trained models and two approaches specifically designed for rodent MRI skull stripping (RATS and RBET) on a large dataset of 655 MR rat brain volumes. In our experiments, MedicDeepLabv3+ outperformed the other methods, yielding an average Dice coefficient of 0.952 and 0.944 in the brain and contralateral hemisphere regions. Additionally, we show that despite limiting the GPU memory and the training data, our MedicDeepLabv3+ also provided satisfactory segmentations. In conclusion, our method, publicly available at https://github.com/jmlipman/MedicDeepLabv3Plus , yielded excellent results in multiple scenarios, demonstrating its capability to reduce human workload in rat neuroimaging studies.

Deep learning facilitates fully automated brain image registration of optoacoustic tomography and magnetic resonance imaging

Multispectral optoacoustic tomography (MSOT) is an emerging optical imaging method providing multiplex molecular and functional information from the rodent brain. It can be greatly augmented by magnetic resonance imaging (MRI) which offers excellent soft-tissue contrast and high-resolution brain anatomy. Nevertheless, registration of MSOT-MRI images remains challenging, chiefly due to the entirely different image contrast rendered by these two modalities. Previously reported registration algorithms mostly relied on manual user-dependent brain segmentation, which compromised data interpretation and quantification. Here we propose a fully automated registration method for MSOT-MRI multimodal imaging empowered by deep learning. The automated workflow includes neural network-based image segmentation to generate suitable masks, which are subsequently registered using an additional neural network. The performance of the algorithm is showcased with datasets acquired by cross-sectional MSOT and high-field MRI preclinical scanners. The automated registration method is further validated with manual and half-automated registration, demonstrating its robustness and accuracy.

An End-to-end System for Automatic Characterization of Iba1 Immunopositive Microglia in Whole Slide Imaging

Traumatic brain injury (TBI) is one of the leading causes of death and disability worldwide. Detailed studies of the microglial response after TBI require high throughput quantification of changes in microglial count and morphology in histological sections throughout the brain. In this paper, we present a fully automated end-to-end system that is capable of assessing microglial activation in white matter regions on whole slide images of Iba1 stained sections. Our approach involves the division of the full brain slides into smaller image patches that are subsequently automatically classified into white and grey matter sections. On the patches classified as white matter, we jointly apply functional minimization methods and deep learning classification to identify Iba1-immunopositive microglia. Detected cells are then automatically traced to preserve their complex branching structure after which fractal analysis is applied to determine the activation states of the cells. The resulting system detects white matter regions with 84% accuracy, detects microglia with a performance level of 0.70 (F1 score, the harmonic mean of precision and sensitivity) and performs binary microglia morphology classification with a 70% accuracy. This automated pipeline performs these analyses at a 20-fold increase in speed when compared to a human pathologist. Moreover, we have demonstrated robustness to variations in stain intensity common for Iba1 immunostaining. A preliminary analysis was conducted that indicated that this pipeline can identify differences in microglia response due to TBI. An automated solution to microglia cell analysis can greatly increase standardized analysis of brain slides, allowing pathologists and neuroscientists to focus on characterizing the associated underlying diseases and injuries.

DCS-SVM: a novel semi-automated method for human brain MR image segmentation

In this paper, a novel method is proposed which appropriately segments magnetic resonance (MR) brain images into three main tissues. This paper proposes an extension of our previous work in which we suggested a combination of multiple classifiers (CMC)-based methods named dynamic classifier selection-dynamic local training local Tanimoto index (DCS-DLTLTI) for MR brain image segmentation into three main cerebral tissues. This idea is used here and a novel method is developed that tries to use more complex and accurate classifiers like support vector machine (SVM) in the ensemble. This work is challenging because the CMC-based methods are time consuming, especially on huge datasets like three-dimensional (3D) brain MR images. Moreover, SVM is a powerful method that is used for modeling datasets with complex feature space, but it also has huge computational cost for big datasets, especially those with strong interclass variability problems and with more than two classes such as 3D brain images; therefore, we cannot use SVM in DCS-DLTLTI. Therefore, we propose a novel approach named "DCS-SVM" to use SVM in DCS-DLTLTI to improve the accuracy of segmentation results. The proposed method is applied on well-known datasets of the Internet Brain Segmentation Repository (IBSR) and promising results are obtained.

SEGMENTATION OF BRAIN MRIs BY SUPPORT VECTOR MACHINE: DETECTION AND CHARACTERIZATION OF STROKES

The aim of our work is the segmentation of healthy and pathological brains to obtain brain structures and extract strokes. We used real magnetic resonance (MR) images weighted on diffusion. The brain was isolated, and the images were filtered by an anisotropic filter, and then segmented by support vector machines (SVMs). We first applied the method on synthetic images to test the performance of the algorithm and adjust the parameters. Then, we compared our results with those obtained by a cooperative approach proposed in a previous paper.

Automatic classification framework for ventricular septal defects: a pilot study on high-throughput mouse embryo cardiac phenotyping

Intensive international efforts are underway toward phenotyping the entire mouse genome by modifying all its [Formula: see text] genes one-by-one for comparative studies. A workload of this scale has triggered numerous studies harnessing image informatics for the identification of morphological defects. However, existing work in this line primarily rests on abnormality detection via structural volumetrics between wild-type and gene-modified mice, which generally fails when the pathology involves no severe volume changes, such as ventricular septal defects (VSDs) in the heart. Furthermore, in embryo cardiac phenotyping, the lack of relevant work in embryonic heart segmentation, the limited availability of public atlases, and the general requirement of manual labor for the actual phenotype classification after abnormality detection, along with other limitations, have collectively restricted existing practices from meeting the high-throughput demands. This study proposes, to the best of our knowledge, the first fully automatic VSD classification framework in mouse embryo imaging. Our approach leverages a combination of atlas-based segmentation and snake evolution techniques to derive the segmentation of heart ventricles, where VSD classification is achieved by checking whether the left and right ventricles border or overlap with each other. A pilot study has validated our approach at a proof-of-concept level and achieved a classification accuracy of 100% through a series of empirical experiments on a database of 15 images.

Labeling colorectal NBI zoom-videoendoscope image sequences with MRF and SVM

In this paper, we propose a sequence labeling method by using SVM posterior probabilities with a Markov Random Field (MRF) model for colorectal Narrow Band Imaging (NBI) zoom-videoendoscope. Classifying each frame of a video sequence by SVM classifiers independently leads to an output sequence which is unstable and hard to understand by endoscopists. To make it more stable and readable, we use an MRF model to label the sequence of posterior probabilities. In addition, we introduce class asymmetry for the NBI images in order to keep and enhance frames where there is a possibility that cancers might have been detected. Experimental results with NBI video sequences demonstrate that the proposed MRF model with class asymmetry performs much better than a model without asymmetry.

Statistical Interspace Models (SIMs): Application to Robust 3D Spine Segmentation

Statistical shape models (SSM) are used to introduce shape priors in the segmentation of medical images. However, such models require large training datasets in the case of multi-object structures, since it is required to obtain not only the individual shape variations but also the relative position and orientation among objects. A solution to overcome this limitation is to model each individual shape independently. However, this approach does not take into account the relative position, orientations and shapes among the parts of an articulated object, which may result in unrealistic geometries, such as with object overlaps. In this article, we propose a new Statistical Model, the Statistical Interspace Model (SIM), which provides information about the interaction of all the individual structures by modeling the interspace between them. The SIM is described using relative position vectors between pair of points that belong to different objects that are facing each other. These vectors are divided into their magnitude and direction, each of these groups modeled as independent manifolds. The SIM was included in a segmentation framework that contains an SSM per individual object. This framework was tested using three distinct types of datasets of CT images of the spine. Results show that the SIM completely eliminated the inter-process overlap while improving the segmentation accuracy.

Automated segmentation of mouse brain images using multi-atlas multi-ROI deformation and label fusion

We propose an automated multi-atlas and multi-ROI based segmentation method for both skull-stripping of mouse brain and the ROI-labeling of mouse brain structures from the three dimensional (3D) magnetic resonance images (MRI). Three main steps are involved in our method. First, a region of interest (ROI) guided warping algorithm is designed to register multi-atlas images to the subject space, by considering more on the matching of image contents around the ROI boundaries which are more important for ROI labeling. Then, a multi-atlas and multi-ROI based deformable segmentation method is adopted to refine the ROI labeling result by deforming each ROI surface via boundary recognizers (i.e., SVM classifiers) trained on local surface patches. Finally, a local-mutual-information (MI) based multi-label fusion technique is proposed for allowing the atlases with better local image similarity with the subject to have more contributions in label fusion. The experimental results show that our method works better than the conventional methods on both in vitro and in vivo mouse brain datasets.

Performing label-fusion-based segmentation using multiple automatically generated templates

Classically, model-based segmentation procedures match magnetic resonance imaging (MRI) volumes to an expertly labeled atlas using nonlinear registration. The accuracy of these techniques are limited due to atlas biases, misregistration, and resampling error. Multi-atlas-based approaches are used as a remedy and involve matching each subject to a number of manually labeled templates. This approach yields numerous independent segmentations that are fused using a voxel-by-voxel label-voting procedure. In this article, we demonstrate how the multi-atlas approach can be extended to work with input atlases that are unique and extremely time consuming to construct by generating a library of multiple automatically generated templates of different brains (MAGeT Brain). We demonstrate the efficacy of our method for the mouse and human using two different nonlinear registration algorithms (ANIMAL and ANTs). The input atlases consist a high-resolution mouse brain atlas and an atlas of the human basal ganglia and thalamus derived from serial histological data. MAGeT Brain segmentation improves the identification of the mouse anterior commissure (mean Dice Kappa values (κ = 0.801), but may be encountering a ceiling effect for hippocampal segmentations. Applying MAGeT Brain to human subcortical structures improves segmentation accuracy for all structures compared to regular model-based techniques (κ = 0.845, 0.752, and 0.861 for the striatum, globus pallidus, and thalamus, respectively). Experiments performed with three manually derived input templates suggest that MAGeT Brain can approach or exceed the accuracy of multi-atlas label-fusion segmentation (κ = 0.894, 0.815, and 0.895 for the striatum, globus pallidus, and thalamus, respectively).

Atlas-based automatic mouse brain image segmentation revisited: model complexity vs. image registration

Although many atlas-based segmentation methods have been developed and validated for the human brain, limited work has been done for the mouse brain. This paper investigated roles of image registration and segmentation model complexity in the mouse brain segmentation. We employed four segmentation models [single atlas, multiatlas, simultaneous truth and performance level estimation (STAPLE) and Markov random field (MRF) via four different image registration algorithms (affine, B-spline free-form deformation (FFD), Demons and large deformation diffeomorphic metric mapping (LDDMM)] for delineating 19 structures from in vivo magnetic resonance microscopy images. We validated their accuracies against manual segmentation. Our results revealed that LDDMM outperformed Demons, FFD and affine in any of the segmentation models. Under the same registration, increasing segmentation model complexity from single atlas to multiatlas, STAPLE or MRF significantly improved the segmentation accuracy. Interestingly, the multiatlas-based segmentation using nonlinear registrations (FFD, Demons and LDDMM) had similar performance to their STAPLE counterparts, while they both outperformed their MRF counterparts. Furthermore, when the single-atlas affine segmentation was used as reference, the improvement due to nonlinear registrations (FFD, Demons and LDDMM) in the single-atlas segmentation model was greater than that due to increasing model complexity (multiatlas, STAPLE and MRF affine segmentation). Hence, we concluded that image registration plays a more crucial role in the atlas-based automatic mouse brain segmentation as compared to model complexity. Multiple atlases with LDDMM can best improve the segmentation accuracy in the mouse brain among all segmentation models tested in this study.

3-dimensional imaging modalities for phenotyping genetically engineered mice

A variety of 3-dimensional (3D) digital imaging modalities are available for whole-body assessment of genetically engineered mice: magnetic resonance microscopy (MRM), X-ray microcomputed tomography (microCT), optical projection tomography (OPT), episcopic and cryoimaging, and ultrasound biomicroscopy (UBM). Embryo and adult mouse phenotyping can be accomplished at microscopy or near microscopy spatial resolutions using these modalities. MRM and microCT are particularly well-suited for evaluating structural information at the organ level, whereas episcopic and OPT imaging provide structural and functional information from molecular fluorescence imaging at the cellular level. UBM can be used to monitor embryonic development longitudinally in utero. Specimens are not significantly altered during preparation, and structures can be viewed in their native orientations. Technologies for rapid automated data acquisition and high-throughput phenotyping have been developed and continually improve as this exciting field evolves.

A prior feature SVM-MRF based method for mouse brain segmentation

We introduce an automated method, called prior feature Support Vector Machine-Markov Random Field (pSVMRF), to segment three-dimensional mouse brain Magnetic Resonance Microscopy (MRM) images. Our earlier work, extended MRF (eMRF) integrated Support Vector Machine (SVM) and Markov Random Field (MRF) approaches, leading to improved segmentation accuracy; however, the computation of eMRF is very expensive, which may limit its performance on segmentation and robustness. In this study pSVMRF reduces training and testing time for SVM, while boosting segmentation performance. Unlike the eMRF approach, where MR intensity information and location priors are linearly combined, pSVMRF combines this information in a nonlinear fashion, and enhances the discriminative ability of the algorithm. We validate the proposed method using MR imaging of unstained and actively stained mouse brain specimens, and compare segmentation accuracy with two existing methods: eMRF and MRF. C57BL/6 mice are used for training and testing, using cross validation. For formalin fixed C57BL/6 specimens, pSVMRF outperforms both eMRF and MRF. The segmentation accuracy for C57BL/6 brains, stained or not, was similar for larger structures like hippocampus and caudate putamen, (~87%), but increased substantially for smaller regions like susbtantia nigra (from 78.36% to 91.55%), and anterior commissure (from ~50% to ~80%). To test segmentation robustness against increased anatomical variability we add two strains, BXD29 and a transgenic mouse model of Alzheimer's disease. Segmentation accuracy for new strains is 80% for hippocampus, and caudate putamen, indicating that pSVMRF is a promising approach for phenotyping mouse models of human brain disorders.

Robust automatic rodent brain extraction using 3-D pulse-coupled neural networks (PCNN)

Brain extraction is an important preprocessing step for further processing (e.g., registration and morphometric analysis) of brain MRI data. Due to the operator-dependent and time-consuming nature of manual extraction, automated or semi-automated methods are essential for large-scale studies. Automatic methods are widely available for human brain imaging, but they are not optimized for rodent brains and hence may not perform well. To date, little work has been done on rodent brain extraction. We present an extended pulse-coupled neural network algorithm that operates in 3-D on the entire image volume. We evaluated its performance under varying SNR and resolution and tested this method against the brain-surface extractor (BSE) and a level-set algorithm proposed for mouse brain. The results show that this method outperforms existing methods and is robust under low SNR and with partial volume effects at lower resolutions. Together with the advantage of minimal user intervention, this method will facilitate automatic processing of large-scale rodent brain studies.

Morphological studies of the murine heart based on probabilistic and statistical atlases

This study directly compares morphological features of the mouse heart in its end-relaxed state based on constructed morphometric maps and atlases using principal component analysis in C57BL/6J (n=8) and DBA (n=5) mice. In probabilistic atlases, a gradient probability exists for both strains in longitudinal locations from base to apex. Based on the statistical atlases, differences in size (49.8%), apical direction (15.6%), basal ventricular blood pool size (13.2%), and papillary muscle shape and position (17.2%) account for the most significant modes of shape variability for the left ventricle of the C57BL/6J mice. For DBA mice, differences in left ventricular size and direction (67.4%), basal size (15.7%), and position of papillary muscles (16.8%) account for significant variability.

Longitudinal characterization of brain atrophy of a Huntington's disease mouse model by automated morphological analyses of magnetic resonance images

Mouse models of human diseases play crucial roles in understanding disease mechanisms and developing therapeutic measures. Huntington's disease (HD) is characterized by striatal atrophy that begins long before the onset of motor symptoms. In symptomatic HD, striatal volumes decline predictably with disease course. Thus, imaging based volumetric measures have been proposed as outcomes for presymptomatic as well as symptomatic clinical trials of HD. Magnetic resonance imaging of the mouse brain structures is becoming widely available and has been proposed as one of the biomarkers of disease progression and drug efficacy testing. However, three-dimensional and quantitative morphological analyses of the brains are not straightforward. In this paper, we describe a tool for automated segmentation and voxel-based morphological analyses of the mouse brains. This tool was applied to a well-established mouse model of Huntington's disease, the R6/2 transgenic mouse strain. Comparison between the automated and manual segmentation results showed excellent agreement in most brain regions. The automated method was able to sensitively detect atrophy as early as 4 weeks of age and accurately follow disease progression. Comparison between ex vivo and in vivo MRI suggests that the ex vivo end-point measurement of brain morphology is also a valid approach except for the morphology of the ventricles. This is the first report of longitudinal characterization of brain atrophy in a mouse model of Huntington's disease by using automatic morphological analysis.

Genetic dissection of the mouse CNS using magnetic resonance microscopy

PURPOSE OF REVIEW

Advances in magnetic resonance microscopy (MRM) make it practical to map gene variants responsible for structural variation in brains of many species, including mice and humans. We review results of a systematic genetic analysis of MRM data using as a case study a family of well characterized lines of mice.

RECENT ADVANCES

MRM has matured to the point that we can generate high contrast, high-resolution images even for species as small as a mouse, with a brain merely 1/3000th the size of humans. We generated 21.5-micron data sets for a diverse panel of BXD mouse strains to gauge the extent of genetic variation, and as a prelude to comprehensive genetic and genomic analyses. Here we review MRM capabilities and image segmentation methods; heritability of brain variation; covariation of the sizes of brain regions; and correlations between MRM and classical histological data sets.

SUMMARY

The combination of high throughput MRM and genomics will improve our understanding of the genetic basis of structure-function correlations. Sophisticated mouse models will be critical in converting correlations into mechanisms and in determining genetic and epigenetic causes of differences in disease susceptibility.