PETS2009 and Winter-PETS 2009 results: a combined evaluation

This paper presents the results of the crowd image analysis challenge of the Winter PETS 2009 workshop. The evaluation is carried out using a selection of the metrics developed in the Video Analysis and Content Extraction (VACE) program and the CLassification of Events, Activities, and Relationships (CLEAR) consortium [13]. The evaluation highlights the detection and tracking performance of the authors’systems in areas such as precision, accuracy and robustness. The performance is also compared to the PETS 2009 submitted results.

PETS2010 and PETS2009 evaluation of results using individual ground truthed single views

This paper presents the results of the crowd image analysis challenge of the PETS2010 workshop. The evaluation was carried out using a selection of the metrics developed in the Video Analysis and Content Extraction (VACE) program and the CLassification of Events, Activities, and Relationships (CLEAR) consortium. The PETS 2010 evaluation was performed using new ground truthing create from each independant two dimensional view. In addition, the performance of the submissions to the PETS 2009 and Winter-PETS 2009 were evaluated and included in the results. The evaluation highlights the detection and tracking performance of the authors’ systems in areas such as precision, accuracy and robustness.

Final report on research project PS2010, proof of concept of automated mapping of weeds in arable fields

Many weeds occur in patches but farmers frequently spray whole fields to control the weeds in these patches. Given a geo-referenced weed map, technology exists to confine spraying to these patches. Adoption of patch spraying by arable farmers has, however, been negligible partly due to the difficulty of constructing weed maps. Building on previous DEFRA and HGCA projects, this proposal aims to develop and evaluate a machine vision system to automate the weed mapping process. The project thereby addresses the principal technical stumbling block to widespread adoption of site specific weed management (SSWM). The accuracy of weed identification by machine vision based on a single field survey may be inadequate to create herbicide application maps. We therefore propose to test the hypothesis that sufficiently accurate weed maps can be constructed by integrating information from geo-referenced images captured automatically at different times of the year during normal field activities. Accuracy of identification will also be increased by utilising a priori knowledge of weeds present in fields. To prove this concept, images will be captured from arable fields on two farms and processed offline to identify and map the weeds, focussing especially on black-grass, wild oats, barren brome, couch grass and cleavers. As advocated by Lutman et al. (2002), the approach uncouples the weed mapping and treatment processes and builds on the observation that patches of these weeds are quite stable in arable fields. There are three main aspects to the project. 1) Machine vision hardware. Hardware component parts of the system are one or more cameras connected to a single board computer (Concurrent Solutions LLC) and interfaced with an accurate Global Positioning System (GPS) supplied by Patchwork Technology. The camera(s) will take separate measurements for each of the three primary colours of visible light (red, green and blue) in each pixel. The basic proof of concept can be achieved in principle using a single camera system, but in practice systems with more than one camera may need to be installed so that larger fractions of each field can be photographed. Hardware will be reviewed regularly during the project in response to feedback from other work packages and updated as required. 2) Image capture and weed identification software. The machine vision system will be attached to toolbars of farm machinery so that images can be collected during different field operations. Images will be captured at different ground speeds, in different directions and at different crop growth stages as well as in different crop backgrounds. Having captured geo-referenced images in the field, image analysis software will be developed to identify weed species by Murray State and Reading Universities with advice from The Arable Group. A wide range of pattern recognition and in particular Bayesian Networks will be used to advance the state of the art in machine vision-based weed identification and mapping. Weed identification algorithms used by others are inadequate for this project as we intend to collect and correlate images collected at different growth stages. Plants grown for this purpose by Herbiseed will be used in the first instance. In addition, our image capture and analysis system will include plant characteristics such as leaf shape, size, vein structure, colour and textural pattern, some of which are not detectable by other machine vision systems or are omitted by their algorithms. Using such a list of features observable using our machine vision system, we will determine those that can be used to distinguish weed species of interest. 3) Weed mapping. Geo-referenced maps of weeds in arable fields (Reading University and Syngenta) will be produced with advice from The Arable Group and Patchwork Technology. Natural infestations will be mapped in the fields but we will also introduce specimen plants in pots to facilitate more rigorous system evaluation and testing. Manual weed maps of the same fields will be generated by Reading University, Syngenta and Peter Lutman so that the accuracy of automated mapping can be assessed. The principal hypothesis and concept to be tested is that by combining maps from several surveys, a weed map with acceptable accuracy for endusers can be produced. If the concept is proved and can be commercialised, systems could be retrofitted at low cost onto existing farm machinery. The outputs of the weed mapping software would then link with the precision farming options already built into many commercial sprayers, allowing their use for targeted, site-specific herbicide applications. Immediate economic benefits would, therefore, arise directly from reducing herbicide costs. SSWM will also reduce the overall pesticide load on the crop and so may reduce pesticide residues in food and drinking water, and reduce adverse impacts of pesticides on non-target species and beneficials. Farmers may even choose to leave unsprayed some non-injurious, environmentally-beneficial, low density weed infestations. These benefits fit very well with the anticipated legislation emerging in the new EU Thematic Strategy for Pesticides which will encourage more targeted use of pesticides and greater uptake of Integrated Crop (Pest) Management approaches, and also with the requirements of the Water Framework Directive to reduce levels of pesticides in water bodies. The greater precision of weed management offered by SSWM is therefore a key element in preparing arable farming systems for the future, where policy makers and consumers want to minimise pesticide use and the carbon footprint of farming while maintaining food production and security. The mapping technology could also be used on organic farms to identify areas of fields needing mechanical weed control thereby reducing both carbon footprints and also damage to crops by, for example, spring tines. Objective i. To develop a prototype machine vision system for automated image capture during agricultural field operations; ii. To prove the concept that images captured by the machine vision system over a series of field operations can be processed to identify and geo-reference specific weeds in the field; iii. To generate weed maps from the geo-referenced, weed plants/patches identified in objective (ii).

Gene-chip technology and its applications

Gene Chips are finding extensive use in animal and plant science. Generally microarrays are of two kind, cDNA or oligonucleotide. cDNA microarrays were developed at Stanford University, whereas oligonucleotide were developed by Affymetrix. The construction of cDNA or oligonucleotide on a glass slide helps to compare the gene expression level of treated and control samples by labeling mRNA with green (Cy3) and red (Cy5) dyes. The hybridized gene chip emit fluorescence whose intensity and colour can be measured. RNA labeling can be done directly or indirectly. Indirect method involves amino allyle modified dUTP instead of pre-labelled nucleotide. Hybridization of gene chip generally occurs in a minimum volume possible and to ensure the hetroduplex formation, a ten fold more DNA is spotted on slide than in the solutions. A confocal or semi confocal laser technologies coupled with CCD camera are used for image acquisition. For standardization, house keeping genes are used or cDNA are spotted in gene chip that are not present in treated or control samples. Moreover, statistical analysis (image analysis) and cluster analysis softwares have been developed by Stanford University. The gene-chip technology has many applications like expression analysis, gene expression signatures (molecular phenotypes) and promoter regulatory element co-expression.

Root phenomics of crops: opportunities and challenges

Reliable techniques for screening large numbers of plants for root traits are still being developed, but include aeroponic, hydroponic and agar plate systems. Coupled with digital cameras and image analysis software, these systems permit the rapid measurement of root numbers, length and diameter in moderate ( typically <1000) numbers of plants. Usually such systems are employed with relatively small seedlings, and information is recorded in 2D. Recent developments in X-ray microtomography have facilitated 3D non-invasive measurement of small root systems grown in solid media, allowing angular distributions to be obtained in addition to numbers and length. However, because of the time taken to scan samples, only a small number can be screened (typically<10 per day, not including analysis time of the large spatial datasets generated) and, depending on sample size, limited resolution may mean that fine roots remain unresolved. Although agar plates allow differences between lines and genotypes to be discerned in young seedlings, the rank order may not be the same when the same materials are grown in solid media. For example, root length of dwarfing wheat ( Triticum aestivum L.) lines grown on agar plates was increased by similar to 40% relative to wild-type and semi-dwarfing lines, but in a sandy loam soil under well watered conditions it was decreased by 24-33%. Such differences in ranking suggest that significant soil environment-genotype interactions are occurring. Developments in instruments and software mean that a combination of high-throughput simple screens and more in-depth examination of root-soil interactions is becoming viable.

Sparse shape representation using the Laplace-Beltrami eigenfunctions and its application to modeling subcortical structures

We present a new sparse shape modeling framework on the Laplace-Beltrami (LB) eigenfunctions. Traditionally, the LB-eigenfunctions are used as a basis for intrinsically representing surface shapes by forming a Fourier series expansion. To reduce high frequency noise, only the first few terms are used in the expansion and higher frequency terms are simply thrown away. However, some lower frequency terms may not necessarily contribute significantly in reconstructing the surfaces. Motivated by this idea, we propose to filter out only the significant eigenfunctions by imposing l1-penalty. The new sparse framework can further avoid additional surface-based smoothing often used in the field. The proposed approach is applied in investigating the influence of age (38-79 years) and gender on amygdala and hippocampus shapes in the normal population. In addition, we show how the emotional response is related to the anatomy of the subcortical structures.

Estimating root–soil contact from 3D X-ray microtomographs

Adequate contact with the soil is essential for water and nutrient adsorption by plant roots, but the determination of root–soil contact is a challenging task because it is difficult to visualize roots in situ and quantify their interactions with the soil at the scale of micrometres. A method to determine root–soil contact using X-ray microtomography was developed. Contact areas were determined from 3D volumetric images using segmentation and iso-surface determination tools. The accuracy of the method was tested with physical model systems of contact between two objects (phantoms). Volumes, surface areas and contact areas calculated from the measured phantoms were compared with those estimated from image analysis. The volume was accurate to within 0.3%, the surface area to within 2–4%, and the contact area to within 2.5%. Maize and lupin roots were grown in soil (<2 mm) and vermiculite at matric potentials of −0.03 and −1.6 MPa and in aggregate fractions of 4–2, 2–1, 1–0.5 and < 0.5 mm at a matric potential of −0.03 MPa. The contact of the roots with their growth medium was determined from 3D volumetric images. Macroporosity (>70 µm) of the soil sieved to different aggregate fractions was calculated from binarized data. Root-soil contact was greater in soil than in vermiculite and increased with decreasing aggregate or particle size. The differences in root–soil contact could not be explained solely by the decrease in porosity with decreasing aggregate size but may also result from changes in particle and aggregate packing around the root.

Expression of cyclooxygenase-2 in intestine of pigs of different ages and hygiene status

Prostaglandins (PG) are bioactive lipids derived from the metabolism of membrane polyunsaturated fatty acids (PUFA), and play important roles in a number of biological processes including cell division, immune responses and wound healing. Cyclooxygenase (COX) is the key enzyme in PG synthesis from arachidonic acid. The hypothesis of the present study was that expression of COX-2 in porcine intestine was dependent on the microbial load and the age of piglets. Piglets were obtained from sows raised either on outdoor free-range farms or on indoor commercial farms, and littermates were divided into three treatments: One group of piglets suckled the sow, a second group was put into an isolator and fed a milk formula, and a third group was put into the isolator fed milk formula and injected with broad spectrum antibiotics. Samples were collected from the 75% level of the small intestine at day 5, 28 and 56 of age. Tissue section from four piglets from each of these six treatment groups was analysed by immunofluorescence for COX-2 and type-IV collagen (basement membrane, defining lamina propria (LP)). Image analysis was used to determine the number of positive pixels expressing LP and epithelial COX-2. COX-2 expressing cells were observed in LP and epithelium in all porcine intestinal samples. When analysing images obtained on day 28, injection of antibiotics seemed to reduce the COX-2 expression in intestinal samples of piglets when compared to other treatments (P=0.053). No significant effect of farm, treatments or age of piglets was observed on COX-2 expressing data when analysing all data of images obtained at day 28 and 56. By double-labelling experiments, COX-2 was found not to be expressed on cell co-expressing CD45, CD16, CD163 or CD2, thus indicating that mucosal leukocytes, including dendritic cells, macrophages and NK cells did not express COX-2. Future research should investigate the role of COX-2 expression in the digestive tract in relation to pig health.

Understanding the spatial mass transfer behaviour of a pulsating jet HMV system: vortex generation and characterisation

The flow patterns generated by a pulsating jet used to study hydrodynamic modulated voltammetry (HMV) are investigated. It is shown that the pronounced edge effect reported previously is the result of the generation of a vortex ring from the pulsating jet. This vortex behaviour of the pulsating jet system is imaged using a number of visualisation techniques. These include a dye system and an electrochemically generated bubble stream. In each case a toroidal vortex ring was observed. Image analysis revealed that the velocity of this motion was of the order of 250 mm s−1 with a corresponding Reynolds number of the order of 1200. This motion, in conjunction with the electrode structure, is used to explain the strong ‘ring and halo’ features detected by electrochemical mapping of the system reported previously.

Rainfastness of poly(vinyl alcohol) deposits on Vicia faba leaf surfaces: from laboratory-scale washing to simulated rain

Rainfastness is the ability of agrochemical deposits to resist wash-off by rain and other related environmental phenomena. This work reports laboratory-scale and raintower studies of the rainfastness of fluorescently labeled poly(vinyl alcohol) (PVA) using fluorescent microscopy combined with image analysis. Samples of hydrolyzed PVA exhibit improved rainfastness over a threshold molecular weight, which correlates with PVA film dissolution, swelling, and crystalline properties. It was also established that the rainfastness of PVA scaled with the molecular weight over this threshold. These PVA samples were further characterized in order to determine the effect of the crystallinity on rainfastness. The quantification of rainfastness is of great interest to the field of agrochemical formulation development in order to improve the efficacy of pesticides and their adjuvants.

Differential regulation of FGF-2 in neurons and reactive astrocytes of axotomized rat hypoglossal nucleus. A possible therapeutic target for neuroprotection in peripheral nerve pathology

Despite the favorable treatment of cranial nerve neuropathology in adulthood, some cases are resistant to therapy leading to permanent functional impairments In many cases, suitable treatment is problematic as the therapeutic target remains unknown Basic fibroblast growth factor (bFGF, FGF 2) is involved in neuronal maintenance and wound repair following nervous system lesions It is one of few neurotrophic molecules acting in autocrine, paracrine and intracrine fashions depending upon specific circumstances Peripheral cranial somatic motor neurons, i e hypoglossal (XII) neurons, may offer a unique opportunity to study cellular FGF 2 mechanisms as the molecule is present in the cytoplasm of neurons and in the nuclei of astrocytes of the central nervous system FGF-2 may trigger differential actions during development, maintenance and lesion of XII neurons because axotomy of those cells leads to cell death during neonatal ages, but not in adult life Moreover, the modulatory effects of astroglial FGF 2 and the Ca+2 binding protein S100 beta have been postulated in paracrine mechanisms after neuronal lesions In our study, adult Wistar rats received a unilateral crush or transection (with amputation of stumps) of XII nerve, and were sacrificed after 72 h or 11 days Brains were processed for immunohistochemical localization of neurofilaments (NF), with or without counterstaining for Nissl substance, ghat fibrillary acidic protein (GFAP, as a marker of astrocytes), S100 beta and FGF-2 The number of Nissl positive neurons of axotomized XII nucleus did not differ from controls The NF immunoreactivity increased in the perikarya and decreased in the neuropil of axotomized XII neurons 11 days after nerve crush or transection An astrocytic reaction was seen in the ipsilateral XII nucleus of the crushed or transected animals 72 h and 11 days after the surgery The nerve lesions did not change the number of FGF-2 neurons in the ipsilateral XII nucleus, however, the nerve transection increased the number of FGF-2 ghat profiles by 72 h and 11 days Microdensitometric image analysis revealed a short lasting decrease in the intensity of FGF 2 immunoreactivity in axotomized XII neurons by 72 h after nerve crush or transection and also an elevation of FGF-2 in the ipsilateral of ghat nuclei by 72h and 11 days after the two lesions S100 beta decreased in astrocytes of 11-day transected XII nucleus The two-color immunoperoxidase for the simultaneous detection of the GFAP/FGF-2 indicated FGF-2 upregulation in the nuclei of reactive astrocytes of the lesioned XII nucleus Astroglial FGF-2 may exert paracrine trophic actions in mature axotomized XII neurons and might represent a therapeutic target for neuroprotection in peripheral nerve pathology (C) 2009 Elsevier GmbH All rights reserved

Tyrosine hydroxylase immunoreactivity as indicator of sympathetic activity: simultaneous evaluation in different tissues of hypertensive rats

Burgi K, Cavalleri MT, Alves AS, Britto LRG, Antunes VR, Michelini LC. Tyrosine hydroxylase immunoreactivity as indicator of sympathetic activity: simultaneous evaluation in different tissues of hypertensive rats. Am J Physiol Regul Integr Comp Physiol 300: R264-R271, 2011. First published December 9, 2010; doi: 10.1152/ajpregu.00687.2009.-Vasomotor control by the sympathetic nervous system presents substantial heterogeneity within different tissues, providing appropriate homeostatic responses to maintain basal/stimulated cardiovascular function both at normal and pathological conditions. The availability of a reproducible technique for simultaneous measurement of sympathetic drive to different tissues is of great interest to uncover regional patterns of sympathetic nerve activity (SNA). We propose the association of tyrosine hydroxylase immunoreactivity (THir) with image analysis to quantify norepinephrine (NE) content within nerve terminals in arteries/arterioles as a good index for regional sympathetic outflow. THir was measured in fixed arterioles of kidney, heart, and skeletal muscle of WistarKyoto rats (WKY) and spontaneously hypertensive rats (SHR) (123 +/- 2 and 181 +/- 4 mmHg, 300 +/- 8 and 352 +/- 8 beats/min, respectively). There was a differential THir distribution in both groups: higher THir was observed in the kidney and skeletal muscle (similar to 3-4-fold vs. heart arterioles) of WKY; in SHR, THir was increased in the kidney and heart (2.4- and 5.3-fold vs. WKY, respectively) with no change in the skeletal muscle arterioles. Observed THir changes were confirmed by either: 1) determination of NE content (high-performance liquid chromatography) in fresh tissues (SHR vs. WKY): +34% and +17% in kidney and heart, respectively, with no change in the skeletal muscle; 2) direct recording of renal (RSNA) and lumbar SNA (LSNA) in anesthetized rats, showing increased RSNA but unchanged LSNA in SHR vs. WKY. THir in skeletal muscle arterioles, NE content in femoral artery, and LSNA were simultaneously reduced by exercise training in the WKY group. Results indicate that THir is a valuable technique to simultaneously evaluate regional patterns of sympathetic activity.

Neurodegeneration and Increased Production of Nitrotyrosine, Nitric Oxide Synthase, IFN-gamma and S100 beta Protein in the Spinal Cord of IL-12p40-Deficient Mice Infected with Trypanosoma cruzi

Background/Aim: Chagas` disease is caused by Trypanosoma cruzi and occurs in most Latin American countries. The protozoan may colonize the central nervous system (CNS) of immune-compromised human hosts, thus causing neuronal disorders. Systemic control of the intracellular forms of the parasite greatly depends on the establishment of a TH1 response and subsequent nitric oxide (NO) release. At the CNS, it is known that low concentrations of NO promote neuronal survival and growth, while high concentrations exert toxic effects and neuron death. Accounting for NO production by astrocytes is the glia-derived factor S100 beta, which is overproduced in some neurodegenerative diseases. In the current work, we studied the expression of NO, interferon (IFN)-gamma and S100 beta in the spinal cord tissue of IL-12p40KO mice infected with T. cruzi, a model of neurodegenerative process. Methods: IL-12p40KO and wild-type (WT) female mice infected with T. cruzi Sylvio X10/4 (10(5) trypomastigotes, intraperitoneally) were euthanized when IL-12p40KO individuals presented limb paralysis. Spinal cord sections were submitted to immunohistochemical procedures for localization of neurofilament, laminin, nitrotyrosine, NO synthases (NOS), IFN-gamma and S100 beta. The total number of neurons was estimated by stereological analysis and the area and intensity of immunoreactivities were assessed by microdensitometric/morphometric image analysis. Results: No lesion was found in the spinal cord sections of WT mice, while morphological disarrangements, many inflammatory foci, enlarged vessels, amastigote nests and dying neurons were seen at various levels of IL-12p40KO spinal cord. Compared to WT mice, IL-12p40KO mice presented a decrement on total number of neurons (46.4%, p<0.05) and showed increased values of immunoreactive area for nitrotyrosine (239%, p<0.01) and NOS (544%, p<0.001). Moreover, the intensity of nitrotyrosine (16%, p<0.01), NOS (38%, p<0.05) and S100 beta (21%, p<0.001) immunoreactivities were also augmented. No IFN-gamma labeled cells were seen in WT spinal cord tissue, contrary to IL-12p40KO tissue that displayed inflammatory infiltrating cells and also some parenchymal cells positively labeled.Conclusion: We suggest that overproduction of NO may account for neuronal death at the spinal cord of T. cruzi-infected IL-12p40KO mice and that IFN-gamma and S100 beta may contribute to NOS activation in the absence of IL-12. Copyright (C) 2009 S. Karger AG, Basel

Chaotic phase synchronization and desynchronization in an oscillator network for object selection

Object selection refers to the mechanism of extracting objects of interest while ignoring other objects and background in a given visual scene. It is a fundamental issue for many computer vision and image analysis techniques and it is still a challenging task to artificial Visual systems. Chaotic phase synchronization takes place in cases involving almost identical dynamical systems and it means that the phase difference between the systems is kept bounded over the time, while their amplitudes remain chaotic and may be uncorrelated. Instead of complete synchronization, phase synchronization is believed to be a mechanism for neural integration in brain. In this paper, an object selection model is proposed. Oscillators in the network representing the salient object in a given scene are phase synchronized, while no phase synchronization occurs for background objects. In this way, the salient object can be extracted. In this model, a shift mechanism is also introduced to change attention from one object to another. Computer simulations show that the model produces some results similar to those observed in natural vision systems.

Objective Detection and Delineation of Oral Neoplasia Using Autofluorescence Imaging

Although the oral cavity is easily accessible to inspection, patients with oral cancer most often present at a late stage, leading to high morbidity and mortality. Autofluorescence imaging has emerged as a promising technology to aid clinicians in screening for oral neoplasia and as an aid to resection, but current approaches rely on subjective interpretation. We present a new method to objectively delineate neoplastic oral mucosa using autofluorescence imaging. Autofluorescence images were obtained from 56 patients with oral lesions and 11 normal volunteers. From these images, 276 measurements from 159 unique regions of interest (ROI) sites corresponding to normal and confirmed neoplastic areas were identified. Data from ROIs in the first 46 subjects were used to develop a simple classification algorithm based on the ratio of red-to-green fluorescence; performance of this algorithm was then validated using data from the ROIs in the last 21 subjects. This algorithm was applied to patient images to create visual disease probability maps across the field of view. Histologic sections of resected tissue were used to validate the disease probability maps. The best discrimination between neoplastic and nonneoplastic areas was obtained at 405 nm excitation; normal tissue could be discriminated from dysplasia and invasive cancer with a 95.9% sensitivity and 96.2% specificity in the training set, and with a 100% sensitivity and 91.4% specificity in the validation set. Disease probability maps qualitatively agreed with both clinical impression and histology. Autofluorescence imaging coupled with objective image analysis provided a sensitive and noninvasive tool for the detection of oral neoplasia.