Semi-supervised remote sensing image classification with cluster kernels

A semisupervised support vector machine is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictions.

High b-value diffusion-weighted imaging: A sensitive method to reveal white matter differences in schizophrenia.

Over the last 10 years, diffusion-weighted imaging (DWI) has become an important tool to investigate white matter (WM) anomalies in schizophrenia. Despite technological improvement and the exponential use of this technique, discrepancies remain and little is known about optimal parameters to apply for diffusion weighting during image acquisition. Specifically, high b-value diffusion-weighted imaging known to be more sensitive to slow diffusion is not widely used, even though subtle myelin alterations as thought to happen in schizophrenia are likely to affect slow-diffusing protons. Schizophrenia patients and healthy controls were scanned with a high b-value (4000s/mm(2)) protocol. Apparent diffusion coefficient (ADC) measures turned out to be very sensitive in detecting differences between schizophrenia patients and healthy volunteers even in a relatively small sample. We speculate that this is related to the sensitivity of high b-value imaging to the slow-diffusing compartment believed to reflect mainly the intra-axonal and myelin bound water pool. We also compared these results to a low b-value imaging experiment performed on the same population in the same scanning session. Even though the acquisition protocols are not strictly comparable, we noticed important differences in sensitivities in the favor of high b-value imaging, warranting further exploration.

The prognostic value of semi-quantitative i-123 mibg scintigraphy at diagnosis in high risk neuroblastoma: validation of the siopen score method

Purpose: SIOPEN scoring of 123I mIBG imaging has been shown to predict response to induction chemotherapy and outcome at diagnosis in children with HRN.Method: Patterns of skeletal 123I mIBG uptake were assigned numerical scores (Mscore) ranging from 0 (no metastasis) to 72 (diffuse metastases) within 12 body areas as described previously. 271 anonymised, paired image data sets acquired at diagnosis and on completion of Rapid COJEC induction chemotherapy were reviewed, constituting a representative sample of 1602 children treated prospectively within the HR-NBL1/SIOPEN trial. Pre-and post-treatment Mscores were compared with bone marrow cytology (BM) and 3 year event free survival (EFS).Results: Results 224/271 patients showed skeletal MIBG-uptake at diagnosis and were evaluable forMIBG-response. Complete response (CR) on MIBG to Rapid COJEC induction was achieved by 66%, 34% and 15% of patients who had pre-treatment Mscores of <18 (n¼65, 29%), 18-44 (n¼95,42%) and Y ´ 45 (n¼64, 28.5%) respectively (chi squared test p<.0001). Mscore at diagnosis and on completion of Rapid COJEC correlated strongly with BM involvement (p<0.0001). The correlation of pre score with post scores and response was highly significant (p<0.001). Most importantly, the 3 year EFS in 47 children with Mscore 0 at diagnosis was 0.68 (A ` 0.07), by comparison with 0.42 (A` 0.06), 0.35 (A` 0.05) and 0.25 (A` 0.06) for patients in pre-treatment score groups <18, 18-44 and Y ´ 45, respectively (p<0.001). AnMscore threshold ofY ´ 45 at diagnosis was associated with significantly worse outcome by comparison with all other Mscore groups (p¼0.029). The 3 year EFS of 0.53 (A` 0.07) of patients in metastatic CR (mIBG and BM) after Rapid Cojec (33%) is clearly superior to patients not achieving metastatic CR (0.24 (A ` 0.04), p¼0.005).Conclusion: SIOPEN scoring of 123I mIBG imaging has been shown to predict response to induction chemotherapy and outcome at diagnosis in children with HRN.

Public-domain software for root image analysis

In the search for high efficiency in root studies, computational systems have been developed to analyze digital images. ImageJ and Safira are public-domain systems that may be used for image analysis of washed roots. However, differences in root properties measured using ImageJ and Safira are supposed. This study compared values of root length and surface area obtained with public-domain systems with values obtained by a reference method. Root samples were collected in a banana plantation in an area of a shallower Typic Carbonatic Haplic Cambisol (CXk), and an area of a deeper Typic Haplic Ta Eutrophic Cambisol (CXve), at six depths in five replications. Root images were digitized and the systems ImageJ and Safira used to determine root length and surface area. The line-intersect method modified by Tennant was used as reference; values of root length and surface area measured with the different systems were analyzed by Pearson's correlation coefficient and compared by the confidence interval and t-test. Both systems ImageJ and Safira had positive correlation coefficients with the reference method for root length and surface area data in CXk and CXve. The correlation coefficient ranged from 0.54 to 0.80, with lowest value observed for ImageJ in the measurement of surface area of roots sampled in CXve. The IC (95 %) revealed that root length measurements with Safira did not differ from that with the reference method in CXk (-77.3 to 244.0 mm). Regarding surface area measurements, Safira did not differ from the reference method for samples collected in CXk (-530.6 to 565.8 mm²) as well as in CXve (-4231 to 612.1 mm²). However, measurements with ImageJ were different from those obtained by the reference method, underestimating length and surface area in samples collected in CXk and CXve. Both ImageJ and Safira allow an identification of increases or decreases in root length and surface area. However, Safira results for root length and surface area are closer to the results obtained with the reference method.

Classification of urban multi-angular image sequences by aligning their manifolds

When dealing with multi-angular image sequences, problems of reflectance changes due either to illumination and acquisition geometry, or to interactions with the atmosphere, naturally arise. These phenomena interplay with the scene and lead to a modification of the measured radiance: for example, according to the angle of acquisition, tall objects may be seen from top or from the side and different light scatterings may affect the surfaces. This results in shifts in the acquired radiance, that make the problem of multi-angular classification harder and might lead to catastrophic results, since surfaces with the same reflectance return significantly different signals. In this paper, rather than performing atmospheric or bi-directional reflection distribution function (BRDF) correction, a non-linear manifold learning approach is used to align data structures. This method maximizes the similarity between the different acquisitions by deforming their manifold, thus enhancing the transferability of classification models among the images of the sequence.

Objective assessment of image quality in conventional and digital mammography taking into account dynamic range.

The goal of this work is to develop a method to objectively compare the performance of a digital and a screen-film mammography system in terms of image quality. The method takes into account the dynamic range of the image detector, the detection of high and low contrast structures, the visualisation of the images and the observer response. A test object, designed to represent a compressed breast, was constructed from various tissue equivalent materials ranging from purely adipose to purely glandular composition. Different areas within the test object permitted the evaluation of low and high contrast detection, spatial resolution and image noise. All the images (digital and conventional) were captured using a CCD camera to include the visualisation process in the image quality assessment. A mathematical model observer (non-prewhitening matched filter), that calculates the detectability of high and low contrast structures using spatial resolution, noise and contrast, was used to compare the two technologies. Our results show that for a given patient dose, the detection of high and low contrast structures is significantly better for the digital system than for the conventional screen-film system studied. The method of using a test object with a large tissue composition range combined with a camera to compare conventional and digital imaging modalities can be applied to other radiological imaging techniques. In particular it could be used to optimise the process of radiographic reading of soft copy images.

An active contour-based atlas registration model applied to automatic subthalamic nucleus targeting on MRI: method and validation.

This paper presents a new non parametric atlas registration framework, derived from the optical flow model and the active contour theory, applied to automatic subthalamic nucleus (STN) targeting in deep brain stimulation (DBS) surgery. In a previous work, we demonstrated that the STN position can be predicted based on the position of surrounding visible structures, namely the lateral and third ventricles. A STN targeting process can thus be obtained by registering these structures of interest between a brain atlas and the patient image. Here we aim to improve the results of the state of the art targeting methods and at the same time to reduce the computational time. Our simultaneous segmentation and registration model shows mean STN localization errors statistically similar to the most performing registration algorithms tested so far and to the targeting expert's variability. Moreover, the computational time of our registration method is much lower, which is a worthwhile improvement from a clinical point of view.

Fast Geodesic Active Fields for Image Registration Based on Splitting and Augmented Lagrangian Approaches.

In this paper, we present an efficient numerical scheme for the recently introduced geodesic active fields (GAF) framework for geometric image registration. This framework considers the registration task as a weighted minimal surface problem. Hence, the data-term and the regularization-term are combined through multiplication in a single, parametrization invariant and geometric cost functional. The multiplicative coupling provides an intrinsic, spatially varying and data-dependent tuning of the regularization strength, and the parametrization invariance allows working with images of nonflat geometry, generally defined on any smoothly parametrizable manifold. The resulting energy-minimizing flow, however, has poor numerical properties. Here, we provide an efficient numerical scheme that uses a splitting approach; data and regularity terms are optimized over two distinct deformation fields that are constrained to be equal via an augmented Lagrangian approach. Our approach is more flexible than standard Gaussian regularization, since one can interpolate freely between isotropic Gaussian and anisotropic TV-like smoothing. In this paper, we compare the geodesic active fields method with the popular Demons method and three more recent state-of-the-art algorithms: NL-optical flow, MRF image registration, and landmark-enhanced large displacement optical flow. Thus, we can show the advantages of the proposed FastGAF method. It compares favorably against Demons, both in terms of registration speed and quality. Over the range of example applications, it also consistently produces results not far from more dedicated state-of-the-art methods, illustrating the flexibility of the proposed framework.

High b-value Diffusion-weighted Imaging: A Sensitive Method to Reveal White Matter Changes in Schizophrenia

Background: b-value is the parameter characterizing the intensity of the diffusion weighting during image acquisition. Data acquisition is usually performed with low b value (b~1000 s/mm2). Evidence shows that high b-values (b>2000 s/mm2) are more sensitive to the slow diffusion compartment (SDC) and maybe more sensitive in detecting white matter (WM) anomalies in schizophrenia.Methods: 12 male patients with schizophrenia (mean age 35 +/-3 years) and 16 healthy male controls matched for age were scanned with a low b-value (1000 s/mm2) and a high b-value (4000 s/mm2) protocol. Apparent diffusion coefficient (ADC) is a measure of the average diffusion distance of water molecules per time unit (mm2/s). ADC maps were generated for all individuals. 8 region of interests (frontal and parietal region bilaterally, centrum semi-ovale bilaterally and anterior and posterior corpus callosum) were manually traced blind to diagnosis.Results: ADC measures acquired with high b-value imaging were more sensitive in detecting differences between schizophrenia patients and healthy controls than low b-value imaging with a gain in significance by a factor of 20- 100 times despite the lower image Signal-to-noise ratio (SNR). Increased ADC was identified in patient's WM (p=0.00015) with major contributions from left and right centrum semi-ovale and to a lesser extent right parietal region.Conclusions: Our results may be related to the sensitivity of high b-value imaging to the SDC believed to reflect mainly the intra-axonal and myelin bound water pool. High b-value imaging might be more sensitive and specific to WM anomalies in schizophrenia than low b-value imaging

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.

Iterative statistical reconstruction method: A new way to reduce dose in pediatric cardiac CT

Purpose: Although several approaches have been already used to reduce radiation dose, CT doses are still among the high doses in radio-diagnostic. Recently, General Electric introduced a new imaging reconstruction technique, adaptive statistical iterative reconstruction (ASIR), allows to taking into account the statistical fluctuation of noise. The benefits of ASIR method were assessed through classic metrics and the evaluations of cardiac structures by radiologists. Methods and materials: A 64-row CT (MDCT) was employed. Catphan600 phantom acquisitions and 10 routine-dose CT examinations performed at 80 kVp were reconstructed with FBP and with 50% of ASIR. Six radiologists then assessed the visibility of main cardiac structures using the visual grading analysis (VGA) method. Results: On phantoms, for a constant value of SD (25 HU), CTDIvol is divided by 2 (8 mGy to 4 mGy) when 50% of ASIR is used. At constant CTDIvol, MTF medium frequencies were also significantly improved. First results indicated that clinical images reconstructed with ASIR had a better overall image quality compared with conventional reconstruction. This means that at constant image quality the radiation dose can be strongly reduced. Conclusion: The first results of this study shown that the ASIR method improves the image quality on phantoms by decreasing noise and improving resolution with respect to the classical one. Moreover, the benefit obtained is higher at lower doses. In clinical environment, a dose reduction can still be expected on 80 kVp low dose pediatric protocols using 50% of iterative reconstruction. Best ASIR percentage as a function of cardiac structures and detailed protocols will be presented for cardiac examinations.

Image Analysis for Evaluating Air Void Parameters of Concrete, HR-396, 1998

This research project investigated the use of image analysis to measure the air void parameters of concrete specimens produced under standard laboratory conditions. The results obtained from the image analysis technique were compared to results obtained from plastic air content tests, Danish air meter tests (also referred to as Air Void Analyzer tests), high-pressure air content tests on hardened concrete, and linear traverse tests (as per ASTM C-457). Hardened concrete specimens were sent to three different laboratories for the linear traverse tests. The samples that were circulated to the three labs consisted of specimens that needed different levels of surface preparation. The first set consisted of approximately 18 specimens that had been sectioned from a 4 in. by 4 in. by 18 in. (10 cm by 10 cm by 46 cm) beam using a saw equipped with a diamond blade. These specimens were subjected to the normal sample preparation techniques that were commonly employed by the three different labs (each lab practiced slightly different specimen preparation techniques). The second set of samples consisted of eight specimens that had been ground and polished at a single laboratory. The companion labs were only supposed to retouch the sample surfaces if they exhibited major flaws. In general, the study indicated that the image analysis test results for entrained air content exhibited good to strong correlation to the average values determined via the linear traverse technique. Specimens ground and polished in a single laboratory and then circulated to the other participating laboratories for the air content determinations exhibited the strongest correlation between the image analysis and linear traverse techniques (coefficient of determination, r-squared = 0.96, for n=8). Specimens ground and polished at each of the individual laboratories exhibited considerably more scatter (coefficient of determination, r-squared = 0.78, for n=16). The image analysis technique tended to produce low estimates of the specific surface of the voids when compared to the results from the linear traverse method. This caused the image analysis spacing factor calculations to produce larger values than those obtained from the linear traverse tests. The image analysis spacing factors were still successful at distinguishing between the frost-prone test specimens and the other (more durable) test specimens that were studied in this research project.

Comparison of microscopic method and computational program for pesticide deposition evaluation of spraying

The main objective of this work was to compare two methods to estimate the deposition of pesticide applied by aerial spraying. Hundred and fifty pieces of water sensitive paper were distributed over an area of 50 m length by 75 m width for sampling droplets sprayed by an aircraft calibrated to apply a spray volume of 32 L/ha. The samples were analysed by visual microscopic method using NG 2 Porton graticule and by an image analyser computer program. The results reached by visual microscopic method were the following: volume median diameter, 398±62 mum; number median diameter, 159±22 mum; droplet density, 22.5±7.0 droplets/cm² and estimated deposited volume, 22.2±9.4 L/ha. The respective ones reached with the computer program were: 402±58 mum, 161±32 mum, 21.9±7.5 droplets/cm² and 21.9±9.2 L/ha. Graphs of the spatial distribution of droplet density and deposited spray volume on the area were produced by the computer program.

Model-based iterative reconstruction in pediatric chest CT: assessment of image quality in a prospective study of children with cystic fibrosis.

BACKGROUND: The potential effects of ionizing radiation are of particular concern in children. The model-based iterative reconstruction VEO(TM) is a technique commercialized to improve image quality and reduce noise compared with the filtered back-projection (FBP) method. OBJECTIVE: To evaluate the potential of VEO(TM) on diagnostic image quality and dose reduction in pediatric chest CT examinations. MATERIALS AND METHODS: Twenty children (mean 11.4 years) with cystic fibrosis underwent either a standard CT or a moderately reduced-dose CT plus a minimum-dose CT performed at 100 kVp. Reduced-dose CT examinations consisted of two consecutive acquisitions: one moderately reduced-dose CT with increased noise index (NI = 70) and one minimum-dose CT at CTDIvol 0.14 mGy. Standard CTs were reconstructed using the FBP method while low-dose CTs were reconstructed using FBP and VEO. Two senior radiologists evaluated diagnostic image quality independently by scoring anatomical structures using a four-point scale (1 = excellent, 2 = clear, 3 = diminished, 4 = non-diagnostic). Standard deviation (SD) and signal-to-noise ratio (SNR) were also computed. RESULTS: At moderately reduced doses, VEO images had significantly lower SD (P < 0.001) and higher SNR (P < 0.05) in comparison to filtered back-projection images. Further improvements were obtained at minimum-dose CT. The best diagnostic image quality was obtained with VEO at minimum-dose CT for the small structures (subpleural vessels and lung fissures) (P < 0.001). The potential for dose reduction was dependent on the diagnostic task because of the modification of the image texture produced by this reconstruction. CONCLUSIONS: At minimum-dose CT, VEO enables important dose reduction depending on the clinical indication and makes visible certain small structures that were not perceptible with filtered back-projection.

Image quality assessment in digital mammography: part II. NPWE as a validated alternative for contrast detail analysis.

Assessment of image quality for digital x-ray mammography systems used in European screening programs relies mainly on contrast-detail CDMAM phantom scoring and requires the acquisition and analysis of many images in order to reduce variability in threshold detectability. Part II of this study proposes an alternative method based on the detectability index (d') calculated for a non-prewhitened model observer with an eye filter (NPWE). The detectability index was calculated from the normalized noise power spectrum and image contrast, both measured from an image of a 5 cm poly(methyl methacrylate) phantom containing a 0.2 mm thick aluminium square, and the pre-sampling modulation transfer function. This was performed as a function of air kerma at the detector for 11 different digital mammography systems. These calculated d' values were compared against threshold gold thickness (T) results measured with the CDMAM test object and against derived theoretical relationships. A simple relationship was found between T and d', as a function of detector air kerma; a linear relationship was found between d' and contrast-to-noise ratio. The values of threshold thickness used to specify acceptable performance in the European Guidelines for 0.10 and 0.25 mm diameter discs were equivalent to threshold calculated detectability indices of 1.05 and 6.30, respectively. The NPWE method is a validated alternative to CDMAM scoring for use in the image quality specification, quality control and optimization of digital x-ray systems for screening mammography.