The Coronavirus Disease 2019 (COVID-19) pandemic that affects the world since 2020 generated a great amount of research interest in how to provide aid to medical staff on triage, diagnosis, and prognosis. This work proposes an automated segmentation model over Computed Tomography (CT) scans, segmenting the lung and COVID-19 related lung findings at the same time. Manual segmentation is a time-consuming and complex task, especially when applied to high-resolution CT scans, resulting in a lack of gold standards annotation. Thanks to data provided by the RadVid19 Brazilian initiative, providing over a hundred annotated High Resolution CT (HRCT), we analyze the performance of three convolutional neural networks for the segmentation of lung and COVID findings: a 3D UNet architecture; a modified EfficientDet (2D) architecture; and 3D and 2D variations of the MobileNetV3 architecture. Our method achieved first place in the RadVid19 challenge, among 13 other competitors’ submissions. Additionally, we evaluate the model with the best result on the challenge in four public CT datasets, comparing our results against other related works, and studying the effects of using different annotations in training and testing. Our best method achieved on testing upwards of 0.98 Lung and 0.73 Findings 3D Dice and reached state-of-the-art performance on public data.
Current techniques trying to predict Alzheimer's disease at an early-stage explore the structural information of T1-weighted MR Images. Among these techniques, deep convolutional neural network (CNN) is the most promising since it has been successfully used in a variety of medical imaging problems. However, the majority of works on Alzheimer's Disease tackle the binary classification problem only, i.e., to distinguish Normal Controls from Alzheimer's Disease patients. Only a few works deal with the multiclass problem, namely, patient classification into one of the three groups: Normal Control (NC), Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI). In this paper, our primary goal is to tackle the 3-class AD classification problem using T1-weighted MRI and a 2D CNN approach. We used the first two layers of ResNet34 as feature extractor and then trained a classifier using 64 × 64 sized patches from coronal 2D MRI slices. Our extended-2D CNN proposal explores the MRI volumetric information, by using non-consecutive 2D slices as input channels of the CNN, while maintaining the low computational costs associated with a 2D approach. The proposed model, trained and tested on images from ADNI dataset, achieved an accuracy of 68.6% for the multiclass problem, presenting the best performance when compared to state-of-the-art AD classification methods, even the 3D-CNN based ones.
Lesions in the brain white matter are among the most frequently observed incidental findings on MR images. This paper presents a 3D texture-based classification to distinguish normal appearing white matter from white matter containing lesions, and compares it with the 2D approach. Texture analysis were based on 55 texture attributes extracted from gray-level histogram, gray-level co-occurrence matrix, run-length matrix and gradient. The results show that the 3D approach achieves an accuracy rate of 99.28%, against 97.41% of the 2D approach by using a support vector machine classifier. Furthermore, the most discriminating texture attributes on both 2D and 3D cases were obtained from the image histogram and co-occurrence matrix.
The corpus callosum is the major brain structure responsible for inter{hemispheric communication between neurons. Many studies seek to relate corpus callosum attributes to patient characteristics, cerebral diseases and psychological disorders. Most of those studies rely on 2D analysis of the corpus callosum in the mid-sagittal plane. However, it is common to find conflicting results among studies, once many ignore methodological issues and define the mid-sagittal plane based on precary or invalid criteria with respect to the corpus callosum. In this work we propose a novel method to determine the mid-callosal plane using the corpus callosum internal preferred diffusion directions obtained from diffusion tensor images. This plane is analogous to the mid-sagittal plane, but intended to serve exclusively as the corpus callosum reference. Our method elucidates the great potential the directional information of the corpus callosum fibers have to indicate its own referential. Results from experiments with five image pairs from distinct subjects, obtained under the same conditions, demonstrate the method effectiveness to find the corpus callosum symmetric axis relative to the axial plane.
Medical imaging research depends basically on the availability of large image collections, image processing and analysis algorithms, hardware and a multidisciplinary research team. It has to be reproducible, free of errors, fast, accessible through a large variety of devices spread around research centers and conducted simultaneously by a multidisciplinary team. Therefore, we propose a collaborative research environment, named Adessowiki, where tools and datasets are integrated and readily available in the Internet through a web browser. Moreover, processing history and all intermediate results are stored and displayed in automatic generated web pages for each object in the research project or clinical study. It requires no installation or configuration from the client side and offers centralized tools and specialized hardware resources, since processing takes place in the cloud.
Brain white matter lesions found upon magnetic resonance imaging are often observed in psychiatric or neurological patients. Individuals with these lesions present a more significant cognitive impairment when compared with individuals without them. We propose a computerized method to distinguish tissue containing white matter lesions of different etiologies (e.g., demyelinating or ischemic) using texture-based classifiers. Texture attributes were extracted from manually selected regions of interest and used to train and test supervised classifiers. Experiments were conducted to evaluate texture attribute discrimination and classifiers’ performances. The most discriminating texture attributes were obtained from the gray-level histogram and from the co-occurrence matrix. The best classifier was the support vector machine, which achieved an accuracy of 87.9% in distinguishing lesions with different etiologies and an accuracy of 99.29% in distinguishing normal white matter from white matter lesions.
The brain white matter is responsible for the transmission of electrical signals through the central nervous system.
Lesions in the brain white matter, called white matter hyperintensity (WMH), can cause a significant functional deficit.
WMH are commonly seen in normal aging, but also in a number of neurological and psychiatric disorders. We propose
here an automatic method for WHM analysis in order to distinguish regions of interest between normal and non-normal
white matter (identification task) and also to distinguish different types of lesions based on their etiology: demyelinating
or ischemic (classification task). The method combines texture analysis with the use of classifiers, such as Support
Vector Machine (SVM), Nearst Neighboor (1NN), Linear Discriminant Analysis (LDA) and Optimum Path Forest
(OPF). Experiments with real brain MRI data showed that the proposed method is suitable to identify and classify the
brain lesions.
The corpus callosum (CC) is one of the most important white matter structures of the brain, interconnecting the two
cerebral hemispheres, and is related to several neurodegenerative diseases. Since segmentation is usually the first step for
studies in this structure, and manual volumetric segmentation is a very time-consuming task, it is important to have a
robust automatic method for CC segmentation. We propose here an approach for fully automatic 3D segmentation of the
CC in the magnetic resonance diffusion tensor images. The method uses the watershed transform and is performed on the
fractional anisotropy (FA) map weighted by the projection of the principal eigenvector in the left-right direction. The
section of the CC in the midsagittal slice is used as seed for the volumetric segmentation. Experiments with real diffusion
MRI data showed that the proposed method is able to quickly segment the CC without any user intervention, with great
results when compared to manual segmentation. Since it is simple, fast and does not require parameter settings, the
proposed method is well suited for clinical applications.
This paper presents a segmentation technique for diffusion tensor imaging (DTI). This technique is based on a
tensorial morphological gradient (TMG), defined as the maximum dissimilarity over the neighborhood. Once
this gradient is computed, the tensorial segmentation problem becomes an scalar one, which can be solved
by conventional techniques, such as watershed transform and thresholding. Similarity functions, namely the
dot product, the tensorial dot product, the J-divergence and the Frobenius norm, were compared, in order to
understand their differences regarding the measurement of tensor dissimilarities. The study showed that the dot
product and the tensorial dot product turned out to be inappropriate for computation of the TMG, while the
Frobenius norm and the J-divergence were both capable of measuring tensor dissimilarities, despite the distortion
of Frobenius norm, since it is not an affine invariant measure. In order to validate the TMG as a solution for DTI
segmentation, its computation was performed using distinct similarity measures and structuring elements. TMG
results were also compared to fractional anisotropy. Finally, synthetic and real DTI were used in the method
validation. Experiments showed that the TMG enables the segmentation of DTI by watershed transform or by a
simple choice of a threshold. The strength of the proposed segmentation method is its simplicity and robustness,
consequences of TMG computation. It enables the use, not only of well-known algorithms and tools from the
mathematical morphology, but also of any other segmentation method to segment DTI, since TMG computation
transforms tensorial images in scalar ones.
This work proposes the segmentation of grayscale image from of its hierarchical region based representation. The Maxtree structure has demonstrated to be useful for this purpose, offering a semantic vision of the image, therefore, reducing the number of elements to process in relation to the pixel based representation. In this way, a particular searching in this tree can be used to determine regions of interest with lesser computational effort. A generic application of detection of peaks is proposed through searching nodes to kup steps from leaves in the Max-tree (this operator will be called k-max), being each node corresponds to a connected component. The results are compared with the optimal thresholding and the H-maxima technique.
Morphological image processing, now a standard part of the imaging scientist's toolbox, can be applied to a wide range of industrial applications. Concentrating on applications, this book shows how to analyze a problem and then develop successful algorithms based on the analysis. The book is hands-on in a very real sense: readers can download a demonstration toolbox of techniques and images from the web so they can process the images according to examples in the text.
The Image Foresting Transform (IFT) reduces optimal image partition problems from seed pixels into a shortest-path forest problem in a graph, whose solution can be obtained in linear time. It has allowed a unified and efficient approach to edge tracking, region growing, watershed transforms, multiscale skeletonization, and Euclidean distance transform. In this paper, we extend the IFT to introduce two connected operators: cutting-off-domes and filling-up-basins. The former simplifies grayscale images by reducing the height of its domes, while the latter reduces the depth of its basins. By automatically or interactively specifying seed pixels in the image and computing a shortest-path forest, whose trees are rooted at these seeds, the IFT creates a simplified image where the brightness of each pixel is associated with the length of the corresponding shortest-path. A label assigned to each seed is propagated, resulting a labeled image that corresponds to the watershed partitioning from markers. The proposed operators may also be used to provide regional image filtering and labeling of connected components. We combine the cutting-off-domes and filling-up-basins to implement regional minima/maxima, h-domes/basins, opening/closing by reconstruction, leveling, area opening/closing, closing of holes, and removal of pikes. Their applications are illustrated with respect to medical image segmentation.
Oftenly the evaluation of a cornea is made using a Slit Lamp where the aspect of the cells is qualitatively observed, there are elaborated apparels and consequently much more expensive that accomplish a quantitative analysis of the endothelium cells. To overcome the limitations of subjective analysis, manipulation difficulties and high cost, we developed a system coupled to the Slit Lamp (that magnifies 290X the cells) exhibiting the image in a computer monitor and a software dedicated for identification and counting the endothelium cells to at a low cost standardizing the diagnosis for the donated corneas.
A magnifying optical system (250-400X) attached to a Slit Lamp has been developed in order to evaluate the endothelium of donated corneas. The images from the endothelium are captured by a CCD and displayed in a PC monitor. The cost of the system is relatively low compared to the specular microscopes that are on the market for donated corneas (66% less expensive). The system offers two kinds of computer evaluation: interactive and automatic. The interactive counting of the endothelial cells provides a window of any shape and size desired by the clinician, where the cells are clicked by the mouse and the developed software estimates the number of endothelial cells in the cornea as a whole. The automatic counting of the cells is done by an image processing, where the cells are recognized by the developed software, without any interference of the clinician, and counted automatically. The most important features of this system compared to most that are on the market are: there are two ways for the clinical to count the cells and both can be used simultaneously (the automatic provides a quick counting of the cells and the interactive provides a wanted clinical interference on the result); many parts of the cornea can be evaluated and an average counting is provided (usually just the central part of the cornea is analyzed); real time image is provided instead of just a static image, which allows the clinician to have more information about the cornea such as the evaluation of the cells in the snail tracks.
Tangible solutions to practical image segmentation are vital to ensure progress in many applications of medical imaging. Toward this goal, we previously proposed a theory and algorithms for fuzzy connected object definition in n- dimensional images. Their effectiveness has been demonstrated in several applications including multiple sclerosis lesion detection/delineation, MR Angiography, and craniofacial imaging. The purpose of this work is to extend the earlier theory and algorithms to fuzzy connected object definition that considers all relevant objects in the image simultaneously. In the previous theory, delineation of the final object from the fuzzy connectivity scene required the selection of a threshold that specifies the weakest `hanging-togetherness' of image elements relative to each other in the object. Selection of such a threshold was not trivial and has been an active research area. In the proposed method of relative fuzzy connectivity, instead of defining an object on its own based on the strength of connectedness, all co-objects of importance that are present in the image are also considered and the objects are let to compete among themselves in having image elements as their members. In this competition, every pair of elements in the image will have a strength of connectedness in each object. The object in which this strength is highest will claim membership of the elements. This approach to fuzzy object definition using a relative strength of connectedness eliminates the need for a threshold of strength of connectedness that was part of the previous definition. It seems to be more natural since it relies on the fact that an object gets defined in an image by the presence of other objects that coexist in the image. All specified objects are defined simultaneously in this approach. The concept of iterative relative fuzzy connectivity has also been introduced. Robustness of relative fuzzy objects with respect to selection of reference image elements has been established. The effectiveness of the proposed method has been demonstrated using a patient's 3D contrast enhanced MR angiogram and a 2D phantom scene.
This work describes a real-time continuous broiler weighting system based on machine vision, used for size sort planning in a process plant. We demonstrate that this technology can be used successfully as an alternative to classical electromechanical carcasses weighting system. A digitized silhouette image of the carcass hung by its feet is divided in six regions: the legs, the wings, the neck and the breast. Once the parts are separated, their individual areas are measured and used in a polynomial equation that predicts the overall bird weight. A sample of 1400 birds were collected, labeled and weighted in a precision scale, in different days and different hours. We found an error standard deviation of 78 grams for broilers weighing from 750 to 2100 grams. The morphological image processing algorithms demonstrated to be robust to extract the individual parts of the carcass.
KEYWORDS: Optical character recognition, Image segmentation, Image processing, Mathematical morphology, Information fusion, Prototyping, Image compression, Mathematics, System integration, Picture Archiving and Communication System
We present the prototype of an OCR that was designed and implemented at the Institute of Mathematics and Statistics of the University of Sao Paulo. The remarkable characteristic of this system is that all the necessary image processing tasks are performed by Mathematical Morphology operators (the so called morphological operators). Thus, we have developed morphological operators to segment scanned images (i.e., identify objects as characters, words and paragraphs), and recognize font styles and character semantics. The morphological operators that perform segmentation were designed by classical heuristic techniques, while the ones that recognize fonts and characters were designed automatically by new computational learning techniques. The fundamental idea under these techniques is the estimation of a morphological operator from observations of input-output image pairs, that describe its ideal performance. The morphological operators designed have been integrated in a system that translate scanned images into RTF text files, with reasonable correction and time performance. This system has been developed in the KHOROS platform, using the MMach (for morphological operators design heuristically) and PAC (for morphological operators designed by learning) toolboxes.
This paper presents mathematical morphology tools for 3D image analysis, namely, the geodesic granulometries and the neck histogram. The family of openings which constitutes the geodesic granulometries is parameterized by the radius of the digital disks utilized as structuring elements. We demonstrate the validity of the granulometry thus obtained. The resulting granulometric distributions are determined by the underlying metric associated with the digital disks. Next we propose an algorithm to compute the neck histogram, which is an analysis tool that gives statistical information concerning the occurrence of constrictions in the object studied. Finally, we demonstrate the applicaiton of the proposed analysis tools in the characterization of a 3D experimental sample designed as a model for a porous medium.
Mathematical Morphology is a general theory that studies the decompositions of mappings between complete lattices in terms of some families of simple mappings: dilations, erosions, anti-dilations and anti-erosions. Nowadays, this theory is largely used in Image Processing and Computer Vision to extract information from images. The KHOROS system is an open and general environment for Image Processing and Visualization that has become very popular. One of the main characteristics of KHOROS is its flexibility, since it runs out on standard machines, supports several standard data formats, uses a visual programming language, and has tools to help the user to build and install his own programs. A set of new programs can be organized as a subsystem, called Toolbox. This paper presents a fast and comprehensive Mathematical Morphology Toolbox for the KHOROS system, that deals with binary, gray- scale and multiple band images. Each program has specialized algorithms for binary and gray- scale images, that are chosen automatically according to the input data. These implemented algorithms running on current general purpose workstations are as fast as the equivalent ones running on specialized hardware with 1986 technology.
Sectional images generated by medical scanners usually have lower interslice resolution than resolution within the slices. Shape-based interpolation is a method of interpolation that can be applied to the segmented 3-D volume to create an isotropic data set. It uses a distance transform applied to every slice prior to estimation of intermediate binary slices. Gray-level interpolation has been the classical way of estimating intermediate slices. The method reported here is a combination of these two forms of interpolation, using the local gradient as a normalizing factor of the combination. Overall, this combination of the methods performs better than either of them applied individually.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.