Brain segmentation in magnetic resonance human head scans using multi-seeded region growing

This paper presents a skull stripping method to segment the brain from MRI human head scans using multi-seeded region growing technique. The proposed method has two stages. In Stage-1, the brain in the middle slice is segmented, the brains in the remaining slices are segmented in Stage-2. In each stage, the proposed method is required to identify the rough brain mask. The fine brain region in the rough brain mask is segmented using multi-seeded region growing approach. The proposed method uses multiple seed points which are selected automatically based on the intensity profile of grey matter (GM), white matter (WM) and cerebrospinal fluid (CSF) of the brain image. The proposed brain segmentation method using multi-seeded region growing (BSMRG) was validated using 100 volumes of T1, T2 and PD-weighted MR brain images obtained from Internet Brain Segmentation Repository (IBSR), LONI and Whole Brain Atlas (WBA). The best Dice (D) value of 0·971 and Jaccard (J) value of 0·944 were recorded by the proposed BSMRG method on IBSR dataset. For LONI dataset, the best values of D?=?0·979 and J?=?0·960 were obtained for the sagittal oriented images by the proposed method. The performance consistency of the proposed method was tested on the brain images of all types and orientation and have and produced better and stable results than the existing methods Brain Extraction Tool (BET), Brain Surface Extraction (BSE), Watershed Algorithm (WAT), Hybrid Watershed Algorithm (HWA) and Skull Stripping using Graph Cuts (GCUT).     

Neural network approach to segmentation of magnetic resonance head images

A novel image segmentation scheme based on a neural network has been implemented to segment magnetic resonance head images. A three-layer perceptron-type neural network, trained with backward error propagation algorithm was used. The scheme utilizes first-echo intensity and computed T₂ values to construct a two-parameter space for classification. After training on a selected slice, the method successfully segments all slices for a given subject without any further human interaction.     

Research on the magnetic resonance imaging brain tumor segmentation algorithm based on DO-UNet

With the social and economic development and the improvement of people's living standards, smart medical care is booming, and medical image processing is becoming more and more popular in research, of which brain tumor segmentation is an important branch of medical image processing. However, the manual segmentation method of brain tumors requires a lot of time and effort from the doctor and has a great impact on the treatment of patients. In order to solve this problem, we propose a DO-UNet model for magnetic resonance imaging brain tumor image segmentation based on attention mechanism and multi-scale feature fusion to realize fully automatic segmentation of brain tumors. Firstly, we replace the convolution blocks in the original U-Net model with the residual modules to prevent the gradient disappearing. Secondly, the multi-scale feature fusion is added to the skip connection of U-Net to fuse the low-level features and high-level features more effectively. In addition, in the decoding stage, we add an attention mechanism to increase the weight of effective information and avoid information redundancy. Finally, we replace the traditional convolution in the model with DO-Conv to speed up the network training and improve the segmentation accuracy. In order to evaluate the model, we used the BraTS2018, BraTS2019, and BraTS2020 datasets to train the improved model and validate it online, respectively. Experimental results show that the DO-UNet model can effectively improve the accuracy of brain tumor segmentation and has good segmentation performance.     

Optical head tracking for functional magnetic resonance imaging using structured light

An accurate motion-tracking technique is needed to compensate for subject motion during functional magnetic resonance imaging (fMRI) procedures. Here, a novel approach to motion metrology is discussed. A structured light pattern specifically coded for digital signal processing is positioned onto a fiduciary of the patient. As the patient undergoes spatial transformations in 6 DoF (degrees of freedom), a high-resolution CCD camera captures successive images for analysis on a computing platform. A high-speed image processing algorithm is used to calculate spatial transformations in a time frame commensurate with patient movements (10-100 ms) and with a precision of at least 0.5 microm for translations and 0.1 deg for rotations.     

Label-free magnetic resonance imaging to locate live cells in three-dimensional porous scaffolds

Porous scaffolds are widely tested materials used for various purposes in tissue engineering. A critical feature of a porous scaffold is its ability to allow cell migration and growth on its inner surface. Up to now, there has not been a method to locate live cells deep inside a material, or in an entire structure, using real-time imaging and a non-destructive technique. Herein, we seek to demonstrate the feasibility of the magnetic resonance imaging (MRI) technique as a method to detect and locate in vitro non-labelled live cells in an entire porous material. Our results show that the use of optimized MRI parameters (4.7 T; repetition time = 3000 ms; echo time = 20 ms; resolution 39 × 39 µm) makes it possible to obtain images of the scaffold structure and to locate live non-labelled cells in the entire material, with a signal intensity higher than that obtained in the culture medium. In the current study, cells are visualized and located in different kinds of porous scaffolds. Moreover, further development of this MRI method might be useful in several three-dimensional biomaterial tests such as cell distribution studies, routine qualitative testing methods and in situ monitoring of cells inside scaffolds.     

Sub-surface imaging with the magnetic resonance force microscope

The magnetic resonance force microscope (MRFM) is based on mechanical detection of magnetic resonance signals. The force between the field gradient due to a small permanent magnet and the spin magnetization in the sample is used to drive the oscillation of a high Q, low spring-constant micro-mechanical resonator (e.g. atomic force microscope cantilever). This same field gradient also enables microscopic magnetic resonance imaging. We will discuss the characteristics and capabilities of the electron spin MRFM we have fabricated. Our MRFM has a sensitivity of 3×10¹¹ electron spins at room temperature in an applied field of 253 Gauss. Its vertical resolution is 1 micron. One- and two-dimensional scans of a particle beneath the silicon cantilever have been performed which demonstrate the sub-surface spatial imaging capabilities. We also discuss recent advances in the miniaturization of two crucial MRFM components: the micromechanical resonator and the micromagnetic tip.     

Volumetry and topography of the human brain by magnetic resonance imaging

Software, termed Morph©, is described for the morphometric analysis of magnetic resonance images of the human brain. Algorithms for objective contrast border recognition, surface feature classification, and surface feature contour unfolding are evaluated. Intraoperator and interoperator variabilities and errors were determined to be less than 2% over a group of operators (n = 6) for the known volume of a cerebral hemisphere obtained at autopsy. Volumetric errors were measured to be ± 3% for simulated objects and less than 1% for images of phantoms. Contours of brains of normal elderly subjects (n = 6) and patients with probable Alzheimer's disease (n = 6), segmented into sulcal and gyral features to determine gyrification indices, showed concordance with literature values. Flat maps or topograms were obtained of the convoluted cortex by unfolding the segmented contours. The areas of surface features were readily obtained. The activation of the frontal eye fields (FEF) defined by functional magnetic resonance imaging (fMRI) with an oculomotor control task was mapped onto a topogram of the precentral sulcus. This software provides accurate volumetric analysis with additional topographical tools for characterizing convoluted cortical features and for presenting three‐dimensional fMRI activation patterns as two‐dimensional maps. © 2001 John Wiley & Sons, Inc. Int J Imaging Syst Technol 11, 198–208, 2000     

3D brain magnetic resonance imaging segmentation by using bitplane and adaptive fast marching

Diagnosis using medical images helps doctors detect diseases and treat patients effectively. A system that segments objects automatically from magnetic resonance imaging (MRI) plays an important role when doctors diagnose injuries and brain diseases. This article presents a method for automatic brain, scalp, and skull segmentation from MRI that uses Bitplane and the Adaptive Fast Marching method (FMM). We focus on the segmentation of these tissues, especially the brain, because they are the essential objects, and their segmentation is the first step in the segmentation of other tissues. First, the type of each slice is set based on the shape of the brain, and the head region is segmented by removing its background. Second, the sure region and the unsure region are segmented based on the Bitplane method. Finally, this work proposes an approach for classification that is based on the Adaptive FMM. This approach is evaluated with the BrainWeb and Neurodevelopmental MRI databases and compared with other methods. The Dice Averages for brain, scalp, and skull segmentation are 96%, 80%, and 93%, respectively, on the BrainWeb database and 91%, 67%, and 80%, respectively, on the Neurodevelopmental MRI database.     

Targeted nanoparticles for the non-invasive detection of traumatic brain injury by optical imaging and fluorine magnetic resonance imaging

Necrosis is a form of cell death that occurs only under pathological conditions such as ischemic diseases and traumatic brain injury (TBI). Non-invasive imaging of the affected tissue is a key component of novel therapeutic interventions and measurement of treatment responses in patients. Here, we report a bimodal approach for the detection and monitoring of TBI. PEGylated poly(lactic-co-glycolic acid) (PLGA) nanoparticles (NPs), encapsulating both near infrared (NIR) fluorophores and perfluorocarbons (PFCs), were targeted to necrotic cells. We used cyanine dyes such as IRDye 800CW, for which we have previously demonstrated specific targeting to intracellular proteins of cells that have lost membrane integrity. Here, we show specific in vivo detection of necrosis by optical imaging and fluorine magnetic resonance imaging (¹⁹F MRI) using newly designed PLGA NP(NIR700 + PFC)-PEG-800CW. Quantitative ex vivo optical imaging and ¹⁹F MR spectroscopy of NIR-PFC content in injured brain regions and in major organs were well correlated. Both modalities allowed the in vivo identification of necrotic brain lesions in a mouse model of TBI, with optical imaging being more sensitive than ¹⁹F MRI. Our results confirm increased blood pool residence time of PLGA NPs coated with a PEG layer and the successful targeting of TBI-damaged tissue. A single PLGA NP containing NIR-PFC enables both rapid qualitative optical monitoring of the TBI state and quantitative 3D information from deeper tissues on the extent of the lesion by MRI. These necrosis-targeting PLGA NPs can potentially be used for clinical diagnosis of brain injuries.

Open image in new window

     

Edge detection using Chebyshev's orthogonal polynomial and brain extraction from magnetic resonance images of human head

In this article, we propose a new edge detecting method based on the transform coefficients obtained by a point spread function constructed out of Chebyshev's orthogonal polynomials. This edge detector finds edges similar to that of Prewitt and Roberts but is robust against additive and multiplicative noises. We also propose a new scheme to extract brain portion from the magnetic resonance images (MRI) of human head scan by making use of the of the new edge detector. The proposed scheme involves edge detection, morphological operations, and largest connected component analysis. Experiments conducted by applying the proposed scheme on 19 volumes of MRI collected from Internet Brain Segmentation Repository (IBSR) show that the proposed brain extraction scheme performed better than the popular Brain Extraction Tool (BET). The performance of the proposed scheme is measured by computing the Dice coefficient (D) and Jaccard similarity index (J). The proposed method produced a value of 0.9068 for D and 0.8321 for J.     

Nuclear magnetic resonance imaging with 90-nm resolution

Magnetic resonance imaging (MRI) is a powerful imaging technique that typically operates on the scale of millimetres to micrometres. Conventional MRI is based on the manipulation of nuclear spins with radio-frequency fields, and the subsequent detection of spins with induction-based techniques. An alternative approach, magnetic resonance force microscopy (MRFM), uses force detection to overcome the sensitivity limitations of conventional MRI. Here, we show that the two-dimensional imaging of nuclear spins can be extended to a spatial resolution better than 100 nm using MRFM. The imaging of 19F nuclei in a patterned CaF(2) test object was enabled by a detection sensitivity of roughly 1,200 nuclear spins at a temperature of 600 mK. To achieve this sensitivity, we developed high-moment magnetic tips that produced field gradients up to 1.4 x 10(6) T m(-1), and implemented a measurement protocol based on force-gradient detection of naturally occurring spin fluctuations. The resulting detection volume was less than 650 zeptolitres. This is 60,000 times smaller than the previous smallest volume for nuclear magnetic resonance microscopy, and demonstrates the feasibility of pushing MRI into the nanoscale regime.     

Coregistration of diffuse optical spectroscopy and magnetic resonance imaging in a rat tumor model

We report coregistration of near-infrared diffuse optical spectroscopy (DOS) and magnetic resonance imaging (MRI) for the study of animal model tumors. A combined broadband steady-state and frequency-domain apparatus was used to determine tissue oxyhemoglobin, deoxyhemoglobin, and water concentration locally in tumors. Simultaneous MRI coregistration provided structural (T2-weighted) and contrast-enhanced images of the tumor that were correlated with the optical measurements. By use of Monte Carlo simulations, the optically sampled volume was superimposed on the MR images, showing precisely which tissue structure was probed optically. DOS and MRI coregistration measurements were performed on seven rats over 20 days and were separated into three tumor tissue classifications: viable, edematous, and necrotic. A ratio of water concentration to total hemoglobin concentration, as measured optically, was performed for each tissue type and showed values for edematous tissue to be greater than viable tissue (1.2 +/- 0.49 M/microM versus 0.48 +/- 0.15 M/microM). Tissue hemoglobin oxygen saturation (StO2) also showed a large variation between tissue types: viable tissue had an optically measured StO2 value of 61 +/- 5%, whereas StO2 determined for necrotic tissue was 43 +/- 6%.     

In vivo quantification of optical contrast agent dynamics in rat tumors by use of diffuse optical spectroscopy with magnetic resonance imaging coregistration

We present a study of the dynamics of optical contrast agents indocyanine green (ICG) and methylene blue (MB) in an adenocarcinoma rat tumor model. Measurements are conducted with a combined frequency-domain and steady-state optical technique that facilitates rapid measurement of tissue absorption in the 650-1000-nm spectral region. Tumors were also imaged by use of contrast-enhanced magnetic resonance imaging (MRI) and coregistered with the location of the optical probe. The absolute concentrations of contrast agent, oxyhemoglobin, deoxyhemoglobin, and water are measured simultaneously each second for approximately 10 min. The differing tissue uptake kinetics of ICG and MB in these late-stage tumors arise from differences in their effective molecular weights. ICG, because of its binding to plasma proteins, behaves as a macromolecular contrast agent with a low vascular permeability. A compartmental model describing ICG dynamics is used to quantify physiologic parameters related to capillary permeability. In contrast, MB behaves as a small-molecular-weight contrast agent that leaks rapidly from the vasculature into the extravascular, extracellular space, and is sensitive to blood flow and the arterial input function.     

Influence of multiple scattering on three-dimensional imaging with optical diffraction tomography

Optical diffraction tomography is an imaging technique that permits retrieval of the map of permittivity of an object from its scattered far field. Most reconstruction procedures assume that single scattering is dominant so that the scattered far field is linearly linked to the permittivity. In this work, we present a nonlinear inversion method and apply it to complex three-dimensional samples. We show that multiple scattering permits one to obtain a power of resolution beyond the classical limit imposed by the use of propagative incident and diffracted waves. Moreover, we stress that our imaging method is robust with respect to correlated and uncorrelated noise.     

Diffuse optical tomography system to image brain activation with improved spatial resolution and validation with functional magnetic resonance imaging

Although most current diffuse optical brain imaging systems use only nearest- neighbor measurement geometry, the spatial resolution and quantitative accuracy of the imaging can be improved through the collection of overlapping sets of measurements. A continuous-wave diffuse optical imaging system that combines frequency encoding with time-division multiplexing to facilitate overlapping measurements of brain activation is described. Phantom measurements to confirm the expected improvement in spatial resolution and quantitative accuracy are presented. Experimental results showing the application of this instrument for imaging human brain activation are also presented. The observed improvement in spatial resolution is confirmed by functional magnetic resonance imaging.     

Automatic cervical cancer segmentation in multimodal magnetic resonance imaging using an EfficientNet encoder in UNet++ architecture

Automatic cervical cancer segmentation in multimodal magnetic resonance imaging (MRI) is essential because tumor location and delineation can support patients' diagnosis and treatment planning. To meet this clinical demand, we present an encoder–decoder deep learning architecture which employs an EfficientNet encoder in the UNet++ architecture (E-UNet++). EfficientNet helps in effectively encoding multiscale image features. The nested decoders with skip connections aggregate multiscale features from low-level to high-level, which helps in detecting fine-grained details. A cohort of 228 cervical cancer patients with multimodal MRI sequences, including T2-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient imaging, contrast enhancement T1-weighted imaging, and dynamic contrast-enhanced imaging (DCE), has been explored. Evaluations are performed by considering either single or multimodal MRI with standard segmentation quantitative metrics: dice similarity coefficient (DSC), intersection over union (IOU), and 95% Hausdorff distance (HD). Our results show that the E-UNet++ model can achieve DSC values of 0.681–0.786, IOU values of 0.558–0.678, and 95% HD values of 3.779–7.411 pixels in different single sequences. Meanwhile, it provides DSC values of 0.644 and 0.687 on three DCE subsequences and all MRI sequences together. Our designed model is superior to other comparative models, which shows the potential to be used as an artificial intelligence tool for cervical cancer segmentation in multimodal MRI.     

Unsupervised learning-based clustering approach for smart identification of pathologies and segmentation of tissues in brain magnetic resonance imaging

Human-made/developed algorithms provide automatic identification and segmentation of the tissues, lesions and tumor regions available in brain magnetic resonance scan images, which invocates predicaments such as high computational cost and low accuracy rate. Such hassles are reconciled with the utilization of an unsupervised approach in combination with clustering techniques. Initially, static features are chosen from the input image, which is fed to the self-organizing map (SOM), where the algorithm employs the dimensionality reduction of input images. Consecutively, the reduced SOM prototype of data is clustered by the modified fuzzy K-means (MFKM) algorithm. The MFKM algorithm can be modified in terms of membership variables because it operates with spatial information and converges quickly, and this would be of greater benefit to radiologists as they reduce the wrong predictions and voluminous time that normally occur owing to human involvement. The proposed algorithm provides 98.77% sensitivity and 97.5% specificity, which are better than any other traditional algorithms mentioned in this article.     

Increasing the sensitivity of magnetic resonance spectroscopy and imaging

Nuclear magnetic resonance and magnetic resonance imaging are two of the most important techniques in analytical chemistry and noninvasive medical imaging, respectively. They share a common physical basis, one aspect of which is a low intrinsic sensitivity relative to complementary techniques. Encouragingly, recent advances in physics, chemistry, engineering, and data processing have enabled significant increases in sensitivity, as measured by both increased signal-to-noise and reduced data acquisition times, allowing previously unattainable data to be acquired and also new types of experiments to be designed.     

Optoelectronic parallel watershed implementation for segmentation of magnetic resonance brain images

An optoelectronic implementation for the morphological watershed transform is proposed. Fiber-optic programmable logic arrays are used in the implementation because of their high fan factors at high clock speeds. Image segmentation is one of the main applications of the watershed transform. Based on the optoelectronic implementation, an algorithm for the segmentation of axial magnetic resonance (MR) head images to extract information on brain matter is presented. Simulation results for the different steps of the segmentation process are presented.