Digital image analysis as a tool to estimate legume contributions in legume-grass swards

Summary: Productivity and forage quality of legume-grass swards are important factors for successful arable farming in both organic and conventional farming systems. For these objectives the botanical composition of the swards is of particular importance, especially, the content of legumes due to their ability to fix airborne nitrogen. As it can vary considerably within a field, a non-destructive detection method while doing other tasks would facilitate a more targeted sward management and could predict the nitrogen supply of the soil for the subsequent crop. This study was undertaken to explore the potential of digital image analysis (DIA) for a non destructive prediction of legume dry matter (DM) contribution of legume-grass mixtures. For this purpose an experiment was conducted in a greenhouse, comprising a sample size of 64 experimental swards such as pure swards of red clover (Trifolium pratense L.), white clover (Trifolium repens L.) and lucerne (Medicago sativa L.) as well as binary mixtures of each legume with perennial ryegrass (Lolium perenne L.). Growth stages ranged from tillering to heading and the proportion of legumes from 0 to 80 %. Based on digital sward images three steps were considered in order to estimate the legume contribution (% of DM): i) The development of a digital image analysis (DIA) procedure in order to estimate legume coverage (% of area). ii) The description of the relationship between legume coverage (% area) and legume contribution (% of DM) derived from digital analysis of legume coverage related to the green area in a digital image. iii) The estimation of the legume DM contribution with the findings of i) and ii). i) In order to evaluate the most suitable approach for the estimation of legume coverage by means of DIA different tools were tested. Morphological operators such as erode and dilate support the differentiation of objects of different shape by shrinking and dilating objects (Soille, 1999). When applied to digital images of legume-grass mixtures thin grass leaves were removed whereas rounder clover leaves were left. After this process legume leaves were identified by threshold segmentation. The segmentation of greyscale images turned out to be not applicable since the segmentation between legumes and bare soil failed. The advanced procedure comprising morphological operators and HSL colour information could determine bare soil areas in young and open swards very accurately. Also legume specific HSL thresholds allowed for precise estimations of legume coverage across a wide range from 11.8 - 72.4 %. Based on this legume specific DIA procedure estimated legume coverage showed good correlations with the measured values across the whole range of sward ages (R2 0.96, SE 4.7 %). A wide range of form parameters (i.e. size, breadth, rectangularity, and circularity of areas) was tested across all sward types, but none did improve prediction accuracy of legume coverage significantly. ii) Using measured reference data of legume coverage and contribution, in a first approach a common relationship based on all three legumes and sward ages of 35, 49 and 63 days was found with R2 0.90. This relationship was improved by a legume-specific approach of only 49- and 63-d old swards (R2 0.94, 0.96 and 0.97 for red clover, white clover, and lucerne, respectively) since differing structural attributes of the legume species influence the relationship between these two parameters. In a second approach biomass was included in the model in order to allow for different structures of swards of different ages. Hence, a model was developed, providing a close look on the relationship between legume coverage in binary legume-ryegrass communities and the legume contribution: At the same level of legume coverage, legume contribution decreased with increased total biomass. This phenomenon may be caused by more non-leguminous biomass covered by legume leaves at high levels of total biomass. Additionally, values of legume contribution and coverage were transformed to the logit-scale in order to avoid problems with heteroscedasticity and negative predictions. The resulting relationships between the measured legume contribution and the calculated legume contribution indicated a high model accuracy for all legume species (R2 0.93, 0.97, 0.98 with SE 4.81, 3.22, 3.07 % of DM for red clover, white clover, and lucerne swards, respectively). The validation of the model by using digital images collected over field grown swards with biomass ranges considering the scope of the model shows, that the model is able to predict legume contribution for most common legume-grass swards (Frame, 1992; Ledgard and Steele, 1992; Loges, 1998). iii) An advanced procedure for the determination of legume DM contribution by DIA is suggested, which comprises the inclusion of morphological operators and HSL colour information in the analysis of images and which applies an advanced function to predict legume DM contribution from legume coverage by considering total sward biomass. Low residuals between measured and calculated values of legume dry matter contribution were found for the separate legume species (R2 0.90, 0.94, 0.93 with SE 5.89, 4.31, 5.52 % of DM for red clover, white clover, and lucerne swards, respectively). The introduced DIA procedure provides a rapid and precise estimation of legume DM contribution for different legume species across a wide range of sward ages. Further research is needed in order to adapt the procedure to field scale, dealing with differing light effects and potentially higher swards. The integration of total biomass into the model for determining legume contribution does not necessarily reduce its applicability in practice as a combined estimation of total biomass and legume coverage by field spectroscopy (Biewer et al. 2009) and DIA, respectively, may allow for an accurate prediction of the legume contribution in legume-grass mixtures.

Statistical Models for Co-occurrence Data

Modeling and predicting co-occurrences of events is a fundamental problem of unsupervised learning. In this contribution we develop a statistical framework for analyzing co-occurrence data in a general setting where elementary observations are joint occurrences of pairs of abstract objects from two finite sets. The main challenge for statistical models in this context is to overcome the inherent data sparseness and to estimate the probabilities for pairs which were rarely observed or even unobserved in a given sample set. Moreover, it is often of considerable interest to extract grouping structure or to find a hierarchical data organization. A novel family of mixture models is proposed which explain the observed data by a finite number of shared aspects or clusters. This provides a common framework for statistical inference and structure discovery and also includes several recently proposed models as special cases. Adopting the maximum likelihood principle, EM algorithms are derived to fit the model parameters. We develop improved versions of EM which largely avoid overfitting problems and overcome the inherent locality of EM--based optimization. Among the broad variety of possible applications, e.g., in information retrieval, natural language processing, data mining, and computer vision, we have chosen document retrieval, the statistical analysis of noun/adjective co-occurrence and the unsupervised segmentation of textured images to test and evaluate the proposed algorithms.

Solução viscosa de um modelo de difusão não linear para processamento de imagens

Pós-graduação em Matemática - IBILCE

Estimação de densidades e aplicação em segmentação de imagens

The aim of this work is to study some of the density estimation tec- niques and to apply to the segmentation of medical images. Medical images are used to help the diagnostic of tumor diseases as well as to plan and deliver treatment. A computer image is an array of values representing colors in some scale. The smallest element of the image to which it is possible to assign a value is called pixel. Segmen- tation is the process of dividing the image in portions through the classi¯cation of each pixel. The simplest way of classi¯cation is by thresholding, given the number of portions and the threshold values. Another method is constructing a histogram of the pixel values and assign a portion to each pike. The threshold is the mean between two pikes. As the histogram does not form a smooth curve it is di±cult to discern between true pikes and random variation. Density estimation methods allow the estimation of a smooth curve. Image data can be considered as mixture of different densities. In this project parametric and nonparametric methods for density estimation will be addressed and some of them are applied to CT image data

Source localization methods

One of the most pressing demands on electrophysiology applied to the diagnosis of epilepsy is the non-invasive localization of the neuronal generators responsible for brain electrical and magnetic fields (the so-called inverse problem). These neuronal generators produce primary currents in the brain, which together with passive currents give rise to the EEG signal. Unfortunately, the signal we measure on the scalp surface doesn't directly indicate the location of the active neuronal assemblies. This is the expression of the ambiguity of the underlying static electromagnetic inverse problem, partly due to the relatively limited number of independent measures available. A given electric potential distribution recorded at the scalp can be explained by the activity of infinite different configurations of intracranial sources. In contrast, the forward problem, which consists of computing the potential field at the scalp from known source locations and strengths with known geometry and conductivity properties of the brain and its layers (CSF/meninges, skin and skull), i.e. the head model, has a unique solution. The head models vary from the computationally simpler spherical models (three or four concentric spheres) to the realistic models based on the segmentation of anatomical images obtained using magnetic resonance imaging (MRI). Realistic models – computationally intensive and difficult to implement – can separate different tissues of the head and account for the convoluted geometry of the brain and the significant inter-individual variability. In real-life applications, if the assumptions of the statistical, anatomical or functional properties of the signal and the volume in which it is generated are meaningful, a true three-dimensional tomographic representation of sources of brain electrical activity is possible in spite of the ‘ill-posed’ nature of the inverse problem (Michel et al., 2004). The techniques used to achieve this are now referred to as electrical source imaging (ESI) or magnetic source imaging (MSI). The first issue to influence reconstruction accuracy is spatial sampling, i.e. the number of EEG electrodes. It has been shown that this relationship is not linear, reaching a plateau at about 128 electrodes, provided spatial distribution is uniform. The second factor is related to the different properties of the source localization strategies used with respect to the hypothesized source configuration.

A review of atlas-based segmentation for magnetic resonance brain images.

Normal and abnormal brains can be segmented by registering the target image with an atlas. Here, an atlas is defined as the combination of an intensity image (template) and its segmented image (the atlas labels). After registering the atlas template and the target image, the atlas labels are propagated to the target image. We define this process as atlas-based segmentation. In recent years, researchers have investigated registration algorithms to match atlases to query subjects and also strategies for atlas construction. In this paper we present a review of the automated approaches for atlas-based segmentation of magnetic resonance brain images. We aim to point out the strengths and weaknesses of atlas-based methods and suggest new research directions. We use two different criteria to present the methods. First, we refer to the algorithms according to their atlas-based strategy: label propagation, multi-atlas methods, and probabilistic techniques. Subsequently, we classify the methods according to their medical target: the brain and its internal structures, tissue segmentation in healthy subjects, tissue segmentation in fetus, neonates and elderly subjects, and segmentation of damaged brains. A quantitative comparison of the results reported in the literature is also presented.

Automatic segmentation and classification of human intestinal parasites from microscopy images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis. © 2012 IEEE.

Segmentation and grid generation for numerical simulations of vad connections with patient-specific data

Objectives: We are interested in the numerical simulation of the anastomotic region comprised between outflow canula of LVAD and the aorta. Segmenta¬tion, geometry reconstruction and grid generation from patient-specific data remain an issue because of the variable quality of DICOM images, in particular CT-scan (e.g. metallic noise of the device, non-aortic contrast phase). We pro¬pose a general framework to overcome this problem and create suitable grids for numerical simulations.Methods: Preliminary treatment of images is performed by reducing the level window and enhancing the contrast of the greyscale image using contrast-limited adaptive histogram equalization. A gradient anisotropic diffusion filter is applied to reduce the noise. Then, watershed segmentation algorithms and mathematical morphology filters allow reconstructing the patient geometry. This is done using the InsightToolKit library (www.itk.org). Finally the Vascular Model¬ing ToolKit (www.vmtk.org) and gmsh (www.geuz.org/gmsh) are used to create the meshes for the fluid (blood) and structure (arterial wall, outflow canula) and to a priori identify the boundary layers. The method is tested on five different patients with left ventricular assistance and who underwent a CT-scan exam.Results: This method produced good results in four patients. The anastomosis area is recovered and the generated grids are suitable for numerical simulations. In one patient the method failed to produce a good segmentation because of the small dimension of the aortic arch with respect to the image resolution.Conclusions: The described framework allows the use of data that could not be otherwise segmented by standard automatic segmentation tools. In particular the computational grids that have been generated are suitable for simulations that take into account fluid-structure interactions. Finally the presented method features a good reproducibility and fast application.

Model-based Segmentation and Fusion of 3D Computed Tomography and 3D Ultrasound of the Eye for Radiotherapy Planning

Computed Tomography (CT) represents the standard imaging modality for tumor volume delineation for radiotherapy treatment planning of retinoblastoma despite some inherent limitations. CT scan is very useful in providing information on physical density for dose calculation and morphological volumetric information but presents a low sensitivity in assessing the tumor viability. On the other hand, 3D ultrasound (US) allows a highly accurate definition of the tumor volume thanks to its high spatial resolution but it is not currently integrated in the treatment planning but used only for diagnosis and follow-up. Our ultimate goal is an automatic segmentation of gross tumor volume (GTV) in the 3D US, the segmentation of the organs at risk (OAR) in the CT and the registration of both modalities. In this paper, we present some preliminary results in this direction. We present 3D active contour-based segmentation of the eye ball and the lens in CT images; the presented approach incorporates the prior knowledge of the anatomy by using a 3D geometrical eye model. The automated segmentation results are validated by comparing with manual segmentations. Then, we present two approaches for the fusion of 3D CT and US images: (i) landmark-based transformation, and (ii) object-based transformation that makes use of eye ball contour information on CT and US images.

Model-based Segmentation and Image Fusion of 3D Computed Tomography and 3D Ultrasound of the Eye for Radiotherapy Planning

For radiotherapy treatment planning of retinoblastoma inchildhood, Computed Tomography (CT) represents thestandard method for tumor volume delineation, despitesome inherent limitations. CT scan is very useful inproviding information on physical density for dosecalculation and morphological volumetric information butpresents a low sensitivity in assessing the tumorviability. On the other hand, 3D ultrasound (US) allows ahigh accurate definition of the tumor volume thanks toits high spatial resolution but it is not currentlyintegrated in the treatment planning but used only fordiagnosis and follow-up. Our ultimate goal is anautomatic segmentation of gross tumor volume (GTV) in the3D US, the segmentation of the organs at risk (OAR) inthe CT and the registration of both. In this paper, wepresent some preliminary results in this direction. Wepresent 3D active contour-based segmentation of the eyeball and the lens in CT images; the presented approachincorporates the prior knowledge of the anatomy by usinga 3D geometrical eye model. The automated segmentationresults are validated by comparing with manualsegmentations. Then, for the fusion of 3D CT and USimages, we present two approaches: (i) landmark-basedtransformation, and (ii) object-based transformation thatmakes use of eye ball contour information on CT and USimages.

Definition of linear color models in the RGB vector color space to detect red peaches in orchard images taken under natural illumination

This work proposes the detection of red peaches in orchard images based on the definition of different linear color models in the RGB vector color space. The classification and segmentation of the pixels of the image is then performed by comparing the color distance from each pixel to the different previously defined linear color models. The methodology proposed has been tested with images obtained in a real orchard under natural light. The peach variety in the orchard was the paraguayo (Prunus persica var. platycarpa) peach with red skin. The segmentation results showed that the area of the red peaches in the images was detected with an average error of 11.6%; 19.7% in the case of bright illumination; 8.2% in the case of low illumination; 8.6% for occlusion up to 33%; 12.2% in the case of occlusion between 34 and 66%; and 23% for occlusion above 66%. Finally, a methodology was proposed to estimate the diameter of the fruits based on an ellipsoidal fitting. A first diameter was obtained by using all the contour pixels and a second diameter was obtained by rejecting some pixels of the contour. This approach enables a rough estimate of the fruit occlusion percentage range by comparing the two diameter estimates.

Brain tissue segmentation using q-entropy in multiple sclerosis magnetic resonance images

The loss of brain volume has been used as a marker of tissue destruction and can be used as an index of the progression of neurodegenerative diseases, such as multiple sclerosis. In the present study, we tested a new method for tissue segmentation based on pixel intensity threshold using generalized Tsallis entropy to determine a statistical segmentation parameter for each single class of brain tissue. We compared the performance of this method using a range of different q parameters and found a different optimal q parameter for white matter, gray matter, and cerebrospinal fluid. Our results support the conclusion that the differences in structural correlations and scale invariant similarities present in each tissue class can be accessed by generalized Tsallis entropy, obtaining the intensity limits for these tissue class separations. In order to test this method, we used it for analysis of brain magnetic resonance images of 43 patients and 10 healthy controls matched for gender and age. The values found for the entropic q index were 0.2 for cerebrospinal fluid, 0.1 for white matter and 1.5 for gray matter. With this algorithm, we could detect an annual loss of 0.98% for the patients, in agreement with literature data. Thus, we can conclude that the entropy of Tsallis adds advantages to the process of automatic target segmentation of tissue classes, which had not been demonstrated previously.

Urban Detection From Hyperspectral Images Using Dimension-Reduction Model and Fusion of Multiple Segmentations Based on Stuctural and Textural Features

Ce mémoire de maîtrise présente une nouvelle approche non supervisée pour détecter et segmenter les régions urbaines dans les images hyperspectrales. La méthode proposée n ́ecessite trois étapes. Tout d’abord, afin de réduire le coût calculatoire de notre algorithme, une image couleur du contenu spectral est estimée. A cette fin, une étape de réduction de dimensionalité non-linéaire, basée sur deux critères complémentaires mais contradictoires de bonne visualisation; à savoir la précision et le contraste, est réalisée pour l’affichage couleur de chaque image hyperspectrale. Ensuite, pour discriminer les régions urbaines des régions non urbaines, la seconde étape consiste à extraire quelques caractéristiques discriminantes (et complémentaires) sur cette image hyperspectrale couleur. A cette fin, nous avons extrait une série de paramètres discriminants pour décrire les caractéristiques d’une zone urbaine, principalement composée d’objets manufacturés de formes simples g ́eométriques et régulières. Nous avons utilisé des caractéristiques texturales basées sur les niveaux de gris, la magnitude du gradient ou des paramètres issus de la matrice de co-occurrence combinés avec des caractéristiques structurelles basées sur l’orientation locale du gradient de l’image et la détection locale de segments de droites. Afin de réduire encore la complexité de calcul de notre approche et éviter le problème de la ”malédiction de la dimensionnalité” quand on décide de regrouper des données de dimensions élevées, nous avons décidé de classifier individuellement, dans la dernière étape, chaque caractéristique texturale ou structurelle avec une simple procédure de K-moyennes et ensuite de combiner ces segmentations grossières, obtenues à faible coût, avec un modèle efficace de fusion de cartes de segmentations. Les expérimentations données dans ce rapport montrent que cette stratégie est efficace visuellement et se compare favorablement aux autres méthodes de détection et segmentation de zones urbaines à partir d’images hyperspectrales.

A semi-automatic method for segmentation and 3D modeling of glioma tumors from brain MRI

This work presents an efficient method for volume rendering of glioma tumors from segmented 2D MRI Datasets with user interactive control, by replacing manual segmentation required in the state of art methods. The most common primary brain tumors are gliomas, evolving from the cerebral supportive cells. For clinical follow-up, the evaluation of the pre- operative tumor volume is essential. Tumor portions were automatically segmented from 2D MR images using morphological filtering techniques. These seg- mented tumor slices were propagated and modeled with the software package. The 3D modeled tumor consists of gray level values of the original image with exact tumor boundary. Axial slices of FLAIR and T2 weighted images were used for extracting tumors. Volumetric assessment of tumor volume with manual segmentation of its outlines is a time-consuming proc- ess and is prone to error. These defects are overcome in this method. Authors verified the performance of our method on several sets of MRI scans. The 3D modeling was also done using segmented 2D slices with the help of a medical software package called 3D DOCTOR for verification purposes. The results were validated with the ground truth models by the Radi- ologist.

Three-dimensional magnetic resonance reconstruction images before and after surgical therapy of spontaneous canine brain tumors

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)