Automatic Brain Extraction for Rodent MRI Images

Liu, Yikang; Unsal, Hayreddin S; Yi, Tao; Zhang, Nanyin

doi:10.1007/s12021-020-09453-z

Cited by 29 publications

(43 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…use of both T2w RARE and T2 * w EPI images to train our U-Net architecture. Compared to the pioneering techniques RATS (Oguz et al, 2014), PCNN (Chou et al, 2011), and SHERM (Liu et al, 2020), our proposed U-Net architecture is more robust, likely due to its capability to explore and learn the hierarchical features from the training dataset without requiring additional parameter adjustments. U-Net combines the location information from the downsampling path with the contextual information in the upsampling path to obtain a combination of localization and contextualization necessary to predict a reliable segmentation (Ronneberger et al, 2015).…”

Section: Discussionmentioning

confidence: 99%

“…To demonstrate the reliability of our proposed method, we compared our U-Net method with the most prominently used methods for rat brain segmentation: RATS ( Oguz et al, 2014 ), PCNN ( Chou et al, 2011 ), and SHERM ( Liu et al, 2020 ). All images were bias-corrected for field inhomogeneities using Advanced Normalization Tools (ANTs).…”

Section: Methodsmentioning

confidence: 99%

“…For the PCNN algorithm, the brain size range was set to 1000–3000 mm 3 for rat images and 350–550 mm 3 for mouse images ( Chou et al, 2011 ). For SHERM, the brain size range was set to 500–1900 mm 3 for rat images and 300–550 mm 3 for mouse images ( Liu et al, 2020 ). The default convexity threshold in SHERM, defined as the ratio between the volume of a region and that of its convex hull, was set to 0.85 to discard brain mask candidates.…”

Section: Methodsmentioning

confidence: 99%

“…To date, several attempts have been made to address rodent skull-segmentation ( Pfefferbaum et al, 2004 ; Sharief et al, 2008 ; Bendazzoli et al, 2019 ; Feo and Giove, 2019 ; Lohmeier et al, 2019 ; Liu et al, 2020 ). To date, the most prominent tools for rodent MRI skull stripping are Pulse-Coupled Neural Network (PCNN)-based brain extraction proposed by Chou et al (2011) , Rapid Automatic Tissue Segmentation (RATS) pioneered by Oguz et al (2014) , and, and SHape descriptor selected External Regions after Morphologically filtering (SHERM) by Liu et al (2020) . Pulse-Coupled Neural Network is a biomimetic neural network initially developed for cat visual cortex segmentation ( Kuntimad and Ranganath, 1999 ) that utilizes an iterative process to assign labels to adjacent pixels with similar intensity profiles.…”

Section: Introductionmentioning

confidence: 99%

“…While the RATS method has superior performance on T1-weighed images (T1w; Oguz et al, 2014 ), it is worth noting that T2-weighted images (T2w) and T2 ∗ -weighted images (T2 ∗ w) are also common choices in high-field brain function studies. The recently proposed SHape descriptor SHERM ( Liu et al, 2020 ) method identifies a set of brain mask candidates, extracted from MRI images with multiple kernel sizes that matches the shape of the brain template. One common limitation of these brain segmentation methods is that the performance varies by brain size, shape, texture, and contrast, and therefore the technique needs to be optimized for each MRI protocol.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic Skull Stripping of Rat and Mouse Brain MRI Data Using U-Net

et al. 2020

View full text Add to dashboard Cite

Accurate removal of magnetic resonance imaging (MRI) signal outside the brain, a.k.a., skull stripping, is a key step in the brain image pre-processing pipelines. In rodents, this is mostly achieved by manually editing a brain mask, which is time-consuming and operator dependent. Automating this step is particularly challenging in rodents as compared to humans, because of differences in brain/scalp tissue geometry, image resolution with respect to brain-scalp distance, and tissue contrast around the skull. In this study, we proposed a deep-learning-based framework, U-Net, to automatically identify the rodent brain boundaries in MR images. The U-Net method is robust against inter-subject variability and eliminates operator dependence. To benchmark the efficiency of this method, we trained and validated our model using both in-house collected and publicly available datasets. In comparison to current state-of-the-art methods, our approach achieved superior averaged Dice similarity coefficient to ground truth T2-weighted rapid acquisition with relaxation enhancement and T2 *-weighted echo planar imaging data in both rats and mice (all p < 0.05), demonstrating robust performance of our approach across various MRI protocols.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Skull Stripping of Rat and Mouse Brain MRI Data Using U-Net

et al. 2020

View full text Add to dashboard Cite

show abstract

Quantitative neurotoxicology: Potential role of artificial intelligence/deep learning approach

Srivastava

Hanig

2020

J of Applied Toxicology

View full text Add to dashboard Cite

Neurotoxicity studies are important in the preclinical stages of drug development process, because exposure to certain compounds that may enter the brain across a permeable blood brain barrier damages neurons and other supporting cells such as astrocytes. This could, in turn, lead to various neurological disorders such as Parkinson's or Huntington's disease as well as various dementias. Toxicity assessment is often done by pathologists after these exposures by qualitatively or semiquantitatively grading the severity of neurotoxicity in histopathology slides. Quantification of the extent of neurotoxicity supports qualitative histopathological analysis and provides a better understanding of the global extent of brain damage. Stereological techniques such as the utilization of an optical fractionator provide an unbiased quantification of the neuronal damage; however, the process is time‐consuming. Advent of whole slide imaging (WSI) introduced digital image analysis which made quantification of neurotoxicity automated, faster and with reduced bias, making statistical comparisons possible. Although automated to a certain level, simple digital image analysis requires manual efforts of experts which is time‐consuming and limits analysis of large datasets. Digital image analysis coupled with a deep learning artificial intelligence model provides a good alternative solution to time‐consuming stereological and simple digital analysis. Deep learning models could be trained to identify damaged or dead neurons in an automated fashion. This review has focused on and discusses studies demonstrating the role of deep learning in segmentation of brain regions, toxicity detection and quantification of degenerated neurons as well as the estimation of area/volume of degeneration.

show abstract

Automatic brain extraction and hemisphere segmentation in rat brain MR images after stroke using deformable models

et al. 2021

View full text Add to dashboard Cite

Experimental ischemic stroke models play an essential role in understanding the mechanisms of cerebral ischemia and evaluating the development of pathological extent. An important precursor to the investigation of ischemic strokes associated with rodents is the brain extraction and hemisphere segmentation in rat brain diffusion-weighted imaging (DWI) and T2-weighted MRI (T2WI) images. Accurate and reliable image segmentation tools for extracting the rat brain and hemispheres in the MR images are critical in subsequent processes, such as lesion identification and injury analysis. This study is an attempt to investigate rat brain extraction and hemisphere segmentation algorithms that are practicable in both DWI and T2WI images. Methods: To automatically perform brain extraction, the proposed framework is based on an efficient geometric deformable model. By introducing an additional image force in response to the rat brain characteristics into the skull stripping model, we establish a unique rat brain extraction scheme in DWI and T2WI images. For the subsequent hemisphere segmentation, we develop an efficient brain feature detection algorithm to approximately separate the rat brain. A refinement process is enforced by constructing a gradient vector flow in the proximity of the midsurface, where a parametric active contour is attracted to achieve hemisphere segmentation. Results: Extensive experiments with 55 DWI and T2WI subjects were executed in comparison with the state-of -the-art methods. Experimental results indicated that our rat brain extraction and hemisphere segmentation schemes outperformed the competitive methods and exhibited high performance both qualitatively and quantitatively. For rat brain extraction, the average Dice scores were 97.13% and 97.42% in DWI and T2WI image volumes, respectively. Rat hemisphere segmentation results based on the Hausdorff distance metric revealed average values of 0.17 and 0.15 mm for DWI and T2WI subjects, respectively. Conclusions: We believe that the established frameworks are advantageous to facilitate preclinical stroke investigation and relevant neuroscience research that requires accurate brain extraction and hemisphere segmentation using rat DWI and T2WI images.

show abstract

Automatic Brain Extraction for Rodent MRI Images

Cited by 29 publications

References 45 publications

Automatic Skull Stripping of Rat and Mouse Brain MRI Data Using U-Net

Automatic Skull Stripping of Rat and Mouse Brain MRI Data Using U-Net

Quantitative neurotoxicology: Potential role of artificial intelligence/deep learning approach

Automatic brain extraction and hemisphere segmentation in rat brain MR images after stroke using deformable models

Contact Info

Product

Resources

About