Red Channel Images Research Articles

Development of a three-dimensional dose evaluation method for computed tomography.

During a single scan using computed tomography, an X-ray tube orbits along a 360°-circular path around the patient. A scan obtained using the half-cylindrical type phantoms with a radiochromic film sandwiched in between reveals a pixel value map illustrating the two-dimensional (2D) dose distribution. A three-dimensional (3D) dose distribution can be obtained with a 360° rotation of the 2D dose map. This study evaluates the concept and methodology of creating a 3D dose map to develop a phantom with a radiochromic film for obtaining the 3D dose distribution. The coronal and axial plane dose distributions were also evaluated. A single scan computed tomography image obtained using a half-cylindrical type of acrylic phantom with a sandwiched radiochromic film was studied. The diameters of the phantoms were 10 and 16cm, and their lengths were 30cm. A 2D image of the XR-QA2 film was obtained using an image scanner and image processing software. A red channel image was used to obtain the 3D dose distribution using a computing platform. A pseudo color was applied to the red channel image from which cross-sectional color images were obtained. Half of the cross-sectional pixel data were rotated by 360° to generate the data for each axial plane. The image created was saved, and a 3D pixel value map was constructed. The dose measurement procedure for the 3D dose distribution was developed using half-cylindrical acrylic phantoms with a radiochromic film.

Retinal haemorrhages on ultra-widefield red channel images and perfusion status in central retinal vein occlusion.

To evaluate the relationship between retinal haemorrhages detected on Ultra-widefield (UWF) red channel images and perfusion status in eyes with acute central retinal vein occlusion (CRVO). UWF fundus images were split into green and red channels using ImageJ software. The retinal haemorrhages were calculated quantitatively with both the green and red channel images, resulting in green channel haemorrhages (GCH) and red channel haemorrhages (RCH). The nonperfusion area (NPA) was also calculated from fluorescein angiography in each eye. The relationships between both the GCH and RCH with the NPA were investigated. Thirty-two eyes of 32 patients with acute CRVO (18 men, 14 women) were included. The mean GCH and RCH values were 10.4% ± 8.2% and 1.7% ± 1.7%, respectively. The mean NPA was 39.2% ± 28.8%. Significant correlations were seen between the GCH and NPA (r = 0.38; P = 0.022) and RCH and NPA (r = 0.44; P = 0.010, linear regression analysis). Multivariate analysis suggested that only the RCHs were correlated significantly with the NPA. Retinal haemorrhages detected by UWF red channel imaging were less compared to green channel imaging and associated closely with retinal NPAs in eyes with acute CRVO. UWF red channel imaging allowed us to identify ischaemia-related haemorrhage.

TOPSIS aided ensemble of CNN models for screening COVID-19 in chest X-ray images

The novel coronavirus (COVID-19), has undoubtedly imprinted our lives with its deadly impact. Early testing with isolation of the individual is the best possible way to curb the spread of this deadly virus. Computer aided diagnosis (CAD) provides an alternative and cheap option for screening of the said virus. In this paper, we propose a convolution neural network (CNN)-based CAD method for COVID-19 and pneumonia detection from chest X-ray images. We consider three input types for three identical base classifiers. To capture maximum possible complementary features, we consider the original RGB image, Red channel image and the original image stacked with Robert's edge information. After that we develop an ensemble strategy based on the technique for order preference by similarity to an ideal solution (TOPSIS) to aggregate the outcomes of base classifiers. The overall framework, called TOPCONet, is very light in comparison with standard CNN models in terms of the number of trainable parameters required. TOPCONet achieves state-of-the-art results when evaluated on the three publicly available datasets: (1) IEEE COVID-19 dataset + Kaggle Pneumonia Dataset, (2) Kaggle Radiography dataset and (3) COVIDx.

Ordered iterative colour channel selection enhances segmentation of brain slice image neurons of the sham fetal sheep model

• We propose a novel segmentation model to extract the densely populated overlapping cortical neurons from the background image, which is essential to rapidly qualify and quantify the brain cortical neurons from brain slice images of in utero fetal sheep model . • The ordered iterative colour channel selection (OICCS) segmentation model enhances the performance of the marker controlled watershed (MCW) K-means segmentation technique. • The OICCS model involves the iterative application of the MCW K-means segmentation method in the three colour channels (red, green, and blue) of an RGB image in a selective order. • The segmentation model is significant as it is the essential first step to accelerate the histological analysis process over the currently employed manual assessment. Hypoxic Ischemia (HI) accounts for 23% of annual worldwide neonatal death, brain damage and long-term disability. Histopathological studies of infants with HI are rare, so the assessment of neuronal survival in HI animal models compared to the neuronal survival of their sham control, such as the term in utero fetal sheep model, is pivotal to increasing our understanding of HI at the cellular level and for the development of novel therapeutics and treatments. Histopathological studies of the in utero fetal sheep model rely heavily on the manual identification of neurons in histological brain slice images. However, manual identification is prone to being highly subjective, costly and time-consuming. Thus, there is an urgent need to automate the segmentation process, which is complicated by the existence of densely populated overlapping cells with no prior information of shape or size, resulting in images of high complexity. In this article, we propose an ‘Ordered Iterative Colour Channel Selection (OICCS) method. Such that, when applied to the standard ‘Marker Controlled Watershed k-means segmentation’ (MCW k-means) method, serves to effectively segment cortical neurons from the background in brain slice images of the term equivalent sham control in utero fetal sheep model. Thus, tackling the over-segmentation issue that was encountered by MCW k-means alone. In the OICCS model, we determine that by iteratively applying MCW k-means segmentation: firstly, to the blue channel image; then again on the green channel image for cortical neurons that remained unsegmented from the blue channel segmentation; and finally again on the red channel image for cortical neurons that remained unsegmented from the green channel segmentation that optimal performance results could be achieved of 97.98% ± 0.97% over 90.65 ± 3.32% achieved by the standard MCW k-means applied to the R, G, B channel alone or other permutations of the colour channels. The new OICCS enhanced MCW k-means segmentation method presented here is a significant step in automating the segmentation process of cortical brain cells from brain slice images of the sham control fetal sheep model. This will serve to accelerate the histological segmentation process over the manually intensive identification process that is currently employed.

Crack Detection of Eggshell using Image Processing and Computer Vision

This article presents an eggshell crack inspection using image processing techniques. This approach uses the concept of industrial 4.0 to reduce manual coordination in the egg industry’s manufacturing process. The method started with receiving images from a webcam camera. Then, we rescaled the image to 1147 x 633 for faster computation. Next, divide the image into the red and green channels. The red channel image was converted to grayscale using a Gaussian blur filter with a kernel filter 11 x 11 to reduce noise, followed by turning the image to binary. After that, multiply the binary image with the grayscale of the green channel to remove the background. By that time, a morphological operation was used to enhance the quality of the image. Finally, use the contour matrix to find the area of the object and then build the condition to detect the crack in the eggshell. These techniques of image processing are used to inspect the eggshell crack with a high accuracy of more than 98% as well as the high performance of computing.

Using ultra-widefield red channel images to improve the detection of ischemic central retinal vein occlusion.

To examine the usefulness of red channel fundus imaging to detect the ischemic status in eyes with central retinal vein occlusion (CRVO). Ultra-widefield (UWF) fundus images were obtained from 42 eyes with CRVO. Twenty-one eyes were ischemic, and 21 eyes were non-ischemic. Rubeosis was found in 11 ischemic eyes. UWF images were split into red and green channels using ImageJ software. Both the color and red channel images were used to predict the presence or absence of ischemia when examined by masked graders. The sensitivity and specificity of UWF imagings for the detection of ischemia were calculated in Group A (total 42 eyes), Group B (32 eyes excluding non-rubeotic ischemic CRVO) and Group C (31 eyes excluding rubeotic ischemic CRVO), respectively. Moreover, a linear mixed model was conducted to investigate the relationship between the type of images and the accuracy of prediction in each group. No significant difference in the sensitivity of color fundus imaging was seen between Group A and Group B. By contrast, a significant difference in the sensitivity of red channel imaging was seen between Group A and Group B (p = 0.031). The accuracies of the predictions were not associated with the type of image in Group A and Group B, but were significantly associated in Group C (p = 0.026). UWF red channel imaging enabled more accurate detection of the ischemic status, compared with color fundus images, especially in non-rubeotic CRVO eyes.

Potential- and Color-Resolved Electrochemiluminescence of Polymer Dots for Array Imaging of Multiplex MicroRNAs.

The development of electrochemiluminescence (ECL) emitters remains a great research interest in ECL analysis. Herein, luminol-doped polymer dots (L-Pdots) and diethylamine-coupled Pdots (N-Pdots) were synthesized to design a both potential- and color-resolved ECL strategy. L-Pdots showed the maximum ECL emission at 450 nm in the presence of hydrogen peroxide at +0.6 V, while the maximum emission of N-Pdots was at 675 nm under +1.0 V. This strategy was conveniently used to construct a novel ECL array imaging method for high-throughput detection of two microRNAs (miRNAs). The array was prepared with the mixture of L-Pdots and N-Pdots that were covalently modified with quencher-labeled DNAs, respectively, to recognize the corresponding miRNAs. Upon the addition of duplex-specific nuclease, the DNAs hybridized with miRNAs were digested to release the quenchers and miRNAs, which led to the ECL recovery of Pdots and target-cyclic signal amplification. By imaging the array at +0.6 and +1.0 V and using miRNA-21 and miRNA-205 as the analytes, the blue and red channel images could be extracted to quantify these miRNAs with detection limits of 2.5 and 3.1 pM, respectively. This work provides a new family member of potential- or color-resolved ECL emitters and successfully realizes the simultaneous and high-throughput sensing of multiplex miRNAs.

Stomach 3D Reconstruction Using Virtual Chromoendoscopic Images.

Gastric endoscopy is a golden standard in the clinical process that enables medical practitioners to diagnose various lesions inside a patient’s stomach. If a lesion is found, a success in identifying the location of the found lesion relative to the global view of the stomach will lead to better decision making for the next clinical treatment. Our previous research showed that the lesion localization could be achieved by reconstructing the whole stomach shape from chromoendoscopic indigo carmine (IC) dye-sprayed images using a structure-from-motion (SfM) pipeline. However, spraying the IC dye to the whole stomach requires additional time, which is not desirable for both patients and practitioners. Our objective is to propose an alternative way to achieve whole stomach 3D reconstruction without the need of the IC dye. We generate virtual IC-sprayed (VIC) images based on image-to-image style translation trained on unpaired real no-IC and IC-sprayed images, where we have investigated the effect of input and output color channel selection for generating the VIC images. We validate our reconstruction results by comparing them with the results using real IC-sprayed images and confirm that the obtained stomach 3D structures are comparable to each other. We also propose a local reconstruction technique to obtain a more detailed surface and texture around an interesting region. The proposed method achieves the whole stomach reconstruction without the need of real IC dye using SfM. We have found that translating no-IC green-channel images to IC-sprayed red-channel images gives the best SfM reconstruction result. Clinical impact We offer a method of the frame localization and local 3D reconstruction of a found gastric lesion using standard endoscopy images, leading to better clinical decision.

Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation.

Gastric endoscopy is a standard clinical process that enables medical practitioners to diagnose various lesions inside a patient's stomach. If any lesion is found, it is very important to perceive the location of the lesion relative to the global view of the stomach. Our previous research showed that this could be addressed by reconstructing the whole stomach shape from chromoendoscopic images using a structure-from-motion (SfM) pipeline, in which indigo carmine (IC) blue dye-sprayed images were used to increase feature matches for SfM by enhancing stomach surface's textures. However, spraying the IC dye to the whole stomach requires additional time, labor, and cost, which is not desirable for patients and practitioners. In this paper, we propose an alternative way to achieve whole stomach 3D reconstruction without the need of the IC dye by generating virtual IC-sprayed (VIC) images based on image-to-image style translation trained on unpaired real no-IC and IC-sprayed images. We have specifically investigated the effect of input and output color channel selection for generating the VIC images and found that translating no-IC green-channel images to IC-sprayed red-channel images gives the best SfM reconstruction result.

A Fully Automated Gridding Technique for Real Composite cDNA Microarray Images

Genome-wide screening using microarrays of DNA will be of great use in the early diagnosis of diseases such as cancer and HIV. It also makes use of gene discovery, pharmacogenomics, toxicogenomics, and nutrigenomics for other applications. A DNA microarray image lays out an orderly arranged specific gene regions called spots. Microarray image analysis consists primarily of preprocessing, spot area gridding, spot segmentation, and intensity extraction. The first two phases are focused on this work: preprocessing and gridding. The experiment is conducted on real composite cDNA microarray images. A composite microarray image is formed by suitably stacking a red channel image and a green channel image acquired from a microarray experiment either in the RGB domain or in the GRB domain. The blue channel is kept as zero. In order to reduce the challenging problems of microarray images, an efficient preprocessing algorithm is proposed here for these composite images. We have developed a fully automated gridding algorithm integrating global subgrid gridding and local gridding of spots. This technique extracts the structural information namely inter-subgrid spacing, inter-spot spacing and spot center position to achieve efficient gridding. The traits of a microarray image are evaluated using three parameters namely Mean square error, Naturalness quality image evaluator and degree of contrast. The accuracy of the experimental results indicates that this combined preprocessing and gridding technique performs better than existing competitive methods in SIB, GEO, SMD and DeRisi datasets which are most commonly used by the research community for microarray image analysis techniques.

3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion.

Gastric endoscopy is a common clinical practice that enables medical doctors to diagnose the stomach inside a body. In order to identify a gastric lesion's location such as early gastric cancer within the stomach, this work addressed to reconstruct the 3D shape of a whole stomach with color texture information generated from a standard monocular endoscope video. Previous works have tried to reconstruct the 3D structures of various organs from endoscope images. However, they are mainly focused on a partial surface. In this work, we investigated how to enable structure-from-motion (SfM) to reconstruct the whole shape of a stomach from a standard endoscope video. We specifically investigated the combined effect of chromo-endoscopy and color channel selection on SfM. Our study found that 3D reconstruction of the whole stomach can be achieved by using red channel images captured under chromo-endoscopy by spreading indigo carmine (IC) dye on the stomach surface.

Validation of Alternative Methods for Detecting Meibomian Gland Dropout Without an Infrared Light System: Red Filter for Simple and Effective Meibography.

To evaluate the validity and reliability of alternative methods for evaluating meibomian gland (MG) dropout without using an infrared light system: red-filtered or isolated red-channel images (RCIs) of the everted eyelid. We evaluated MG dropout in the everted upper and lower eyelids of 125 eyes of 64 patients with good-quality infrared meibography images (IMIs) and color digital photographs with and without a red filter. Red-filtered images (RFIs) were converted to black and white and adjusted for contrast/brightness [adjusted red-filtered images (aRFIs)]. RCIs were computationally isolated from color digital photographs obtained without a red filter. After randomization, the total meiboscore (0-6) was evaluated by 2 independent evaluators (interobserver reliability) masked to the image origin, and again after a 30-day interval (intraobserver reliability). The meiboscores evaluated using the RFI, aRFI, and RCI were strongly positively correlated with those evaluated using the IMI (RFI: ρ = 0.788; aRFI: ρ = 0.735; RCI: ρ = 0.630; all P < 0.001, Spearman correlation analysis). Linear-weighted κ-values (κw) showed substantial agreement between the RFI and IMI (κw = 0.676, 95% CI = 0.594-0.759). The RFI had substantial intraobserver reliability (κw = 0.735, 95% CI = 0.685-0.785) and moderate interobserver reliability (κw = 0.467, 95% CI = 0.371-0.563). Computational adjustment of RFIs did not enhance the validity or reliability, and RCIs had limitations in some cases. MGs were successfully visualized using a red filter on a slit lamp and showed substantial agreement with visualization using the standard infrared method. Although interobserver reliability was only moderate, this alternative technique may be useful for evaluating MG dropout when an infrared meibography device is not available.

Whole Stomach 3D Reconstruction and Frame Localization From Monocular Endoscope Video.

Gastric endoscopy is a common clinical practice that enables medical doctors to diagnose various lesions inside a stomach. In order to identify the location of a gastric lesion such as early cancer and a peptic ulcer within the stomach, this work addresses to reconstruct the color-textured 3D model of a whole stomach from a standard monocular endoscope video and localize any selected video frame to the 3D model. We examine how to enable structure-from-motion (SfM) to reconstruct the whole shape of a stomach from endoscope images, which is a challenging task due to the texture-less nature of the stomach surface. We specifically investigate the combined effect of chromo-endoscopy and color channel selection on SfM to increase the number of feature points. We also design a plane fitting-based algorithm for 3D point outliers removal to improve the 3D model quality. We show that whole stomach 3D reconstruction can be achieved (more than 90% of the frames can be reconstructed) by using red channel images captured under chromo-endoscopy by spreading indigo carmine (IC) dye on the stomach surface. In experimental results, we demonstrate the reconstructed 3D models for seven subjects and the application of lesion localization and reconstruction. The methodology and results presented in this paper could offer some valuable reference to other researchers and also could be an excellent tool for gastric surgeons in various computer-aided diagnosis applications.

Analysis of Soil and Vegetation Cover from Satellite Imagery to Assess its Relation to Lark Habitats (Alaudidae, Aves) in the Trans-Volga Semi-Desert

Abstract—This work was carried out in the Dzhanibek and Bokey Orda districts of the West Kazakhstan region of the Republic of Kazakhstan in two key areas. The possibility to study the relationship between the distribution of the abundance of various lark species and their nesting habitats detected using high-resolution satellite images, ground geobotanical descriptions, and bird counts on routes with a variable width of the accounting band was evaluated. The image heterogeneity in a snapshot was analyzed by cluster analysis in the ILWIS software (Heckbert quantization algorithm) using three rasters as variables: infrared and red channel images and NDVI. The correlation between the number of some lark species and the share of some plant associations in the band of accounting routes was established using correlation analysis and approximation of empirical distributions by theoretical ones. A reliable relationship was established between the distribution of three lark species living in the Trans-Volga semi-desert of the Caspian lowland with certain plant associations which they prefer to use as nesting stations.

Full-frame, high-speed 3D shape and deformation measurements using stereo-digital image correlation and a single color high-speed camera

Full-frame, high-speed 3D shape and deformation measurement using stereo-digital image correlation (stereo-DIC) technique and a single high-speed color camera is proposed. With the aid of a skillfully designed pseudo stereo-imaging apparatus, color images of a test object surface, composed of blue and red channel images from two different optical paths, are recorded by a high-speed color CMOS camera. The recorded color images can be separated into red and blue channel sub-images using a simple but effective color crosstalk correction method. These separated blue and red channel sub-images are processed by regular stereo-DIC method to retrieve full-field 3D shape and deformation on the test object surface. Compared with existing two-camera high-speed stereo-DIC or four-mirror-adapter-assisted singe-camera high-speed stereo-DIC, the proposed single-camera high-speed stereo-DIC technique offers prominent advantages of full-frame measurements using a single high-speed camera but without sacrificing its spatial resolution. Two real experiments, including shape measurement of a curved surface and vibration measurement of a Chinese double-side drum, demonstrated the effectiveness and accuracy of the proposed technique.

Grid patterns, spatial inter-scan variations and scanning reading repeatability in radiochromic film dosimetry

When comparing different scans of the same radiochromic film, several patterns can be observed. These patterns are caused by different sources of uncertainty, which affect the repeatability of the scanner. The purpose of this work was to study these uncertainties. The variance of the scanner noise, as a function of the pixel position, was studied for different resolutions. The inter-scan variability of the scanner response was analyzed taking into account spatial discrepancies. Finally, the distance between the position of the same point in different scans was examined. The variance of noise follows periodical patterns in both axes, causing the grid patterns. These patterns were identified for resolutions of 50, 72 and 96dpi, but not for 150dpi. Specially recognizable is the sinusoidal shape with a period of 8.5mm that is produced with 72dpi. Inter-scan variations of the response caused systematic relative dose deviations larger than 1% in 5% of the red channel images, 9% of the green and 51% of the blue. No systematic deviation larger than 1% was found after applying response corrections. The initial positioning and the speed of the scanner lamp vary between scans. Three new sources of uncertainty, which influence radiochromic film dosimetry with flatbed scanners, have been identified and analyzed in this work: grid patterns, spatial inter-scan variations and scanning reading repeatability. A novel correction method is proposed, which mitigates spatial inter-scan variations caused by deviations in the autocalibration of the individual Charge Coupled Device detectors.

Automatic CME front edge detection from STEREO white‐light coronagraph images

AbstractThe coronagraph images captured by a Solar Terrestrial Relations Observatory (STEREO) Ahead/Behind (A/B) spacecraft allow tracking of a coronal mass ejection (CME) from two different viewpoints and reconstructing its propagation in three‐dimensional space. The reconstruction can be done using a triangulation technique that requires a CME front edge location. There are currently no robust automatic CME front edge detection methods that can be integrated with the triangulation technique. In this paper, we propose a novel automatic method to detect the front edge of the CME using STEREO coronagraph 2 red‐colored Red, Green, Blue color model images. Our method consists of two modules: preprocessing and classification. The preprocessing module decomposes each coronagraph image into its three channels and uses only the red channel image for CME segmentation. The output of the preprocessing module is a set of segmented running‐difference binary images which is fed into the classification module. These images are then transformed into polar coordinates followed by CME front edge detection based on the distance that CME travels in the field of view. The proposed method was validated against a manual method using total 56 CME events, 28 from STEREO A and 28 from STEREO B, captured in the period from 1 January 2008 to 16 August 2009. The results show that the proposed method is effective for CME front edge detection. The proposed method is useful in quantitative CME processing and analysis and will be immediately applicable to assist automatic triangulation method for real‐time space weather forecasting.

Peau d'orange and angioid streaks: manifestations of Bruch membrane pathology.

The aim of this study was to characterize peau d'orange and angioid streaks, characteristic findings in eyes of patients with pseudoxanthoma elasticum, by examining fundus photography and optical coherence tomography imaging. Color photographs were evaluated directly as were the component red and green channels. Optical coherence tomography images were evaluated for reflectivity pattern of the band corresponding to the retinal pigment epithelium-Bruch membrane complex. Eighteen eyes of 9 patients with a mean age of 48.7 years (range, 31-61 years) were examined; 7 of them were women. Color photographs showed areas of yellowish opacification that obscured visualization of the underlying choroid. At the outer edges of this confluent area, opacification were nonconfluent changes with similar appearance and these regions were typical peau d'orange. Angioid streaks occurred within and extended up to the outer border of the confluent opacification. Underlying choroidal details could be seen through the regions of peau d'orange and through the gaps in angioid streaks. The red channel image showed increased reflectivity from the confluent deposit and improved visualization of the choroidal vasculature, except where the confluent opacification was located. Optical coherence tomography imaging showed increased reflectivity from the outer border of the retinal pigment epithelium-Bruch membrane complex. The findings suggest that the confluent region is the relevant lesion, not the subconfluent zone known as peau d'orange. Imaging characteristics of the confluent area of opacity are consistent with diffuse infiltration with calcium, a chief histologic abnormality of pseudoxanthoma elasticum. The name coquille d'oeuf was suggested for the confluent area of opacity as a consequence.

SU‐FF‐T‐417: The Use Radichromic Film for Tomotherapy IMRT Dosimetric Verification

Purpose: To evaluate the adequacy of radiochromic_film/CCD‐flatbed scanner system as a tool for tomotherapy IMRT delivery verification. Methods and Materials: In this study, EBT Gafchromic film and Epson flatbed scanner were used. IMRT plans created using tomotherapy treatment planning were delivered to a phantom which incorporates the film and ion chamber. To obtain accurate and reproducible results a film protocol was setup. First the scanner was evaluated in terms of OD variations due to film position on the scanner, direction of film relative to the motion of CCD‐array, and temperature of the glass during read out. From preliminary findings, a simple protocol was developed in which each film was scanned pre/post irradiation in the same position and orientation. The time between exposure and scan was ⩾ 6 hrs. This protocol is applicable for doses ranging from 0–300 cGy. For scanning, 48‐bit RGB mode was employed and the resolution set to 72 dpi. From the resulting TIFF‐images, the red channel images were extracted, filtered, and analyzed using an in‐house film dosimetry software. Since the pre and post irradiation images were co‐registered, the background was subtracted point by point and the pixel value converted to OD. The measured dose distributions were compared with values calculated by tomotherapy at the location of the film. Comparison between measured and calculated dose distributions is expressed using the γ‐index. Results: The measured dose uncertainty with this protocol is +/− 2.0%. A 2D correction matrix was obtained to account for the nonuniformities of the film, light source, glass plates, and CCD array. For the distributions compared, the passing rates γ ⩽1.0 were larger than 90%. Conclusion: The use of Gafchromic film and an Epson scanner in conjunction with a proper scanning protocol provides an accurate and efficient tool for dosimetric verification of IMRT fields produced by serial tomotherapy.

Identification of Seeds by Colour Imaging: Comparison of Discriminant Analysis and Artificial Neural Network

This study describes the use of colour image analysis to identify four seed varieties. A wide range of kernel measurements was obtained from digitised colour images of whole seed samples of rumex, wild oat, lucerne and vetch. The combination size, shape (including kernel seven invariant moments) and texture parameters is the major element in this investigation. Two pattern recognition approaches were attempted in the classification: stepwise discriminant analysis, which is part of statistical pattern recognition techniques, and artificial neural network. The artificial neural network was found to outperform discriminant analysis. With only three inputs, a simple three-layer perception network exhibited performances exceeding 99% both in learning and test sets. It is shown that a mixture of features improved classification from 92% for size and shape parameters to 99% for size, shape and texture parameters. Two species, totally overlapped in the morphometrical space, were well separated by texture. The best characteristics are extracted from the red channel images. Limitations of neural computing concepts are discussed with respect to seed classification.