Visual Color Assessment Research Articles

Deep Learning for Differentiation of Breast Masses Detected by Screening Ultrasound Elastography.

Recently, deep learning using convolutional neural networks (CNNs) has yielded consistent results in image-pattern recognition. This study was aimed at investigating the effectiveness of deep learning using CNNs to differentiate benign and malignant breast masses identified by elastography on ultrasound screening. A data set of the elastography images of 245 breast masses (146 benign, 99 malignant) in 239 consecutive patients was retrospectively obtained. The data set was randomly split into training (55%), validation (25%) and test (20%) cohorts. A deep learning model predicting the probability of malignancy was constructed using GoogLeNet architectures (pre-trained by ImageNet) with 50 epochs. The model was then applied to the test data, and the results were compared with those obtained by evaluating the fat-to-lesion ratio (FLR) and by a 5-point visual color assessment (elasticity score). The receiver operating characteristic (ROC) curve was calculated to evaluate the performance of the model. The DeLong test was used to compare the areas under the ROC curve (AUCs). The CNN, FLR and elasticity score had a sensitivity of 0.800, 0.800 and 0.350; specificity of 0.966, 0.586 and 0.931; accuracy of 0.898, 0.673 and 0.694; positive predictive value of 0.941, 0.571 and 0.778; negative predictive value of 0.875, 0.810 and 0.675; and AUC of 0.895, 0.693 and 0.641, respectively. The AUC of the CNN was significantly higher than that of the FLR or elasticity score (p < 0.001). A CNN-based deep learning model for predicting benign or malignant breast masses revealed better diagnostic performance than did FLR or elasticity score-based estimations on ultrasound elastography. The CNN-based model also increased the positive predictive value from 57%-78% to 94%. Therefore, this model may reduce unnecessary biopsy recommendations for masses detected on breast ultrasound screening.

Two birds with one stone: Visual colorful assessment of dipicolinic acid and Cu2+ by Ln-MOF hybrid attapulgite nano-probe

The poor solubility of Ln-MOF fluorescent nano-probe in water significantly limited their practical application. At the same time, the determination of target analytes is mostly carried out in buffer solution, but the preparation of buffer solution and pH calibration often bring inconvenience to the test. In this work, a bifunctional fluorescent nano-probe (ATP@Eu:Tb-MOF) was constructed at room temperature through one-step method using inorganic nanoclays ATP and Ln-MOF, which recognized anthrax biomarker DPA and Cu2+ in commercially pure drinking water. This nano-probe achieved visual detection of DPA with ultra-high sensitivity (LOD-DPA = 8.82 nM), excellent selectivity to DPA isomers and high reliability in the detection of DPA released by Bacillus subtilis. In addition, the probe can also selectively detect Cu2+ through the “turn-off” pathway with a high sensitivity (LOD-Cu2+ = 6.94 nM). Intelligent visual monitoring was realized by fast reading and analyzing the RGB values of the color changing images of the paper-based nano-probe using smartphone color scanning APP. Furthermore, thin-film-based luminescent nanoprobe can also make excellent visual color assessment of DPA and Cu2+, and advanced logic gate circuit analytical devices were also designed.

COTTON MEDIUM FIBRE COLOUR ASSESSMENT

The Uster HVI system evaluates the colour of medium staple cotton fibre based on the international universal standard and replaces the subjective visual colour assessment of Uzbek cotton fibre determined by the classifier with an objective instrumental measurement.

Visual and photographic assessment of wine color

AbstractThis article presents a color chart explicitly designed for the visual color assessment of wines as a part of more comprehensive hedonistic or analytical tasting systems. The chart is based on visual, colorimetric, and in situ evaluations of existent wine color and the techniques for its assessment in wine sensory evaluation. The system is specified in Munsell coordinates and corresponding sRGB values. Its derivation and use is described and a photographic system for measurement‐based implementation of the system is introduced.

New insights in the reproducibility of visual and electronic tooth color assessment for dental practice

BackgroundThe aim of the study was to compare a 2D and 3D color system concerning a variety of statistical and graphical methods to assess validity and reliability of color measurements, and provide guidance on when to use which system and how to interpret color distance measures, including ΔE and d(0M1).MethodsThe color of teeth 14 to 24 of 35 patients undergoing regular bleaching treatment was visually assessed and electronically measured with the spectrophotometer Shade Inspector™. Tooth color was recorded before bleaching treatment, after 14 days, and again after 6 months. VITAPAN® Classical (2D) and VITA-3D-Master® (3D) served as reference systems.ResultsConcerning repeated measurements, the 2D system was superior to the 3D system, both visually and electronically in terms of ΔE and d(OM1), for statistics of agreement and reliability. All four methods showed strong patterns in Bland-Altman plots. In the 3D system, hue was less reliable than lightness and chroma, which was more pronounced visually than electronically. The smallest detectable color difference varied among the four methods used, and was most favorable in the electronic 2D system. Comparing the methods, the agreement between the 2D and 3D system in terms of ΔE was not good. The reliability of the visual and electronic method was essentially the same in the 2D and 3D systems; this comparability is fair to good.Clinical relevanceThe 3D system may confuse human raters and even electronic devices. The 2D system is the simple and best choice.

Retraction: Influence of lighting and noise on visual color assessment in textiles (IOP Conf. Series: Materials Science and Engineering 872 012033)

Published 15 September 2020This article, and others within this volume, has been retracted by IOP Publishing following clear evidence of plagiarism and citation manipulation.This work was originally published in Spanish (1) and has been translated and published without permission or acknowledgement to the original authors. IOP Publishing Limited has discovered other papers within this volume that have been subjected to the same treatment. This is scientific misconduct.Misconduct investigations are ongoing at the author’s institutions. IOP Publishing Limited will update this notice if required once those investigations have concluded.IOP Publishing Limited request any citations to this article be redirected to the original work (1).Anyone with any information regarding these papers is requested to contact conferenceseries@ioppublishing.org.

Classification of Breast Masses on Ultrasound Shear Wave Elastography using Convolutional Neural Networks.

We aimed to use deep learning with convolutional neural networks (CNNs) to discriminate images of benign and malignant breast masses on ultrasound shear wave elastography (SWE). We retrospectively gathered 158 images of benign masses and 146 images of malignant masses as training data for SWE. A deep learning model was constructed using several CNN architectures (Xception, InceptionV3, InceptionResNetV2, DenseNet121, DenseNet169, and NASNetMobile) with 50, 100, and 200 epochs. We analyzed SWE images of 38 benign masses and 35 malignant masses as test data. Two radiologists interpreted these test data through a consensus reading using a 5-point visual color assessment (SWEc) and the mean elasticity value (in kPa) (SWEe). Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. The best CNN model (which was DenseNet169 with 100 epochs), SWEc, and SWEe had a sensitivity of 0.857, 0.829, and 0.914 and a specificity of 0.789, 0.737, and 0.763 respectively. The CNNs exhibited a mean AUC of 0.870 (range, 0.844-0.898), and SWEc and SWEe had an AUC of 0.821 and 0.855. The CNNs had an equal or better diagnostic performance compared with radiologist readings. DenseNet169 with 100 epochs, Xception with 50 epochs, and Xception with 100 epochs had a better diagnostic performance compared with SWEc (P = 0.018-0.037). Deep learning with CNNs exhibited equal or higher AUC compared with radiologists when discriminating benign from malignant breast masses on ultrasound SWE.

Influence of lighting and noise on visual color assessment in textiles

Color is a human perception of the light reflected by an object. It is an appreciation that depends on the way the human’s eyes detect the reflected light and the way the brain processes it. However, for industry, it is an attribute of product appearance and its observation allows the detection of certain anomalies and defects [1]. Therefore, color is a characteristic that allows to judge an object by creating conditions for its acceptance or rejection [2]. In this research, a laboratory experiment was carried out to analyze different factors involved in visual color evaluations in textiles. A complete factorial experiment design was carried out in which the analyzed factors were lighting, noise, color and participants.

Prediction of Orchard Soils Degradation using Munsell Soil Color

The soil organic carbon content played an important role in reducing soil fertility, then fruit yield and quality. Several studies in Mekong Delta, Vietnam area showed that soil of orchards was degraded after longtime constructed. The prediction of soil organic carbon in the fields at wider regions requires a large number of samples that are costly to analyze. The objective of this study found out the correlation between Munsell soil colour with the content of organic matter of the different orchard soils to predict the content of organic carbon from 52 orchard soil samples of the different ages of construction as soil degraded. A case study in Hau Giang province, Vietnam. The results showed that there was a complicated relation to soil properties. Soil colour has the same Munsell Hue, but there is different between Munsell Value and Chroma when the soil has at the same humidity. Organic Carbon content ranged from 1,32 to 5,6%. There was negative significant correlation between organic C content and Munsell soil color properties, such as with Munsell Value (r = -0,75** air-dry, r = -0,74** moist); Munsell Chroma (r= -0,55** air-dry, r = -0,66** moist). Since, Visual soil colour assessment is useful predictors of organic C content, especially for topsoil layers to predict the degradation of orchard soils. This study indicates that soil organic content can be predicted by using Munsell soil colours for visual field measurements on the old raised bed at the moist condition, which can be used for field soil fertility degradation recommendation. However, more study of pedotransfer function on other soils condition must be correlated for further recommendation.

Effect of plant growth regulators on visual quality of turfgrass

Plant growth regulators (PGRs) are used on turfgrass to slow vertical growth and reduce mowing intensity. However, turfgrasses sometimes exhibit some leaf discolouration after PGR applications. The objective of this study was to determine the effect of different rates of PGRs on turfgrass quality with a special focus on colour characteristics. Three cultivars of perennial ryegrass (Lolium perenne L.) were used in an experiment. Six PGRs were used, namely, Trinexapac Ethyl, Paclobutrazol, Flurprimidol, Mefluidide, Ethephon and Gibberellic Acid, at five different rates. A control without the addition of PGRs was also tested simultaneously. The measurement of leaf colour was performed using a portable spectrophotometer and is presented in CIELab colour space. The turfgrass quality was assessed by a visual score.The results showed that the turfgrass quality was significantly different regarding the perennial ryegrass cultivar, treated with different PGRs rates. The changes owing to different PGRs rates appeared in the wavelengths ranging from 540 to 650 nm. PGRs application significantly affected L, b and a colour components. Gibberellic Acid application resulted lighter leaves with higher yellow hue and in a lower score of overall appearance and turf colour assessment. Paclobutrazol and Trinexapac Ethyl, had a beneficial influence on colour characteristics and turf quality. Flurprimidol and Melfuidide had no effect on turfgrass colour and quality after PGR treatment. The changes in colour of turf of perennial ryegrass correlated with PGR rates. Higher rates resulted in increased intensity of discolouration. The results of the spectrophotometric analysis of leaf colour corresponded with visual turf colour assessment. However, visually scored turfgrass did not show differences between PGR rates.

Diamonds Colour Measurements

As a rule, evaluation of diamond colour is carrying out visually, because creation of the measuring devices is a complex problem due to influence of defects in diamonds (irregularity of coloration, cracks and graphite inclusions). And elimination of this influence is a very difficult task. In this work, an analysis of visual diamond colour evaluation methods and assessment of known devices for objective diamond colour measurements is carried out. As a result, an installation for measuring diamond colour is offered, which as much as possible meets the visual evaluation conditions.

A cheap protocol for colour measure and for diagnostic in planning a cultural heritage restoration. Case study: main façade of Palazzo Governi (Cagliari, Sardinia, Italy).

Due to the bad state of conservation, "Palazzo Governi", a seventeenth-century building located in the old town district of "Stampace" in Cagliari (Sardinia, Italy), was subjected to restoration. Thus, according to the Italian Law n. 1089, the main façade colour must be reproduced, and therefore, its identification was required. The available samples looked fairly degraded, in particular as an easy plaster to crumble; so, some other analyses able to identify the degradation cause were performed. Two different approaches were adopted to attain the first goal, the visual colour assessment by a sensory panel (subjective) and the instrumental measurement by colorimetry (objective). Ion chromatography and inductively coupled plasma-optical emission spectroscopy analyses, as well as conductivity and pH measurements, were performed to evaluate the presence of water-soluble salts inside the plaster, as possible cause of degradation; the binder/aggregate ratio was also evaluated. A full mineralogical and petrographic characterisation of the materials constituting the samples, as well as the identification of their stratigraphy and some other morphologic and structural features suitable to highlight eventual forms of degradation, were performed by optical microscopy. Scanning electron microscopy coupled to X-ray microanalysis was been also used in order to confirm and/or to integrate data obtained by optical microscopy. The samples have been compared with two samples coming from two other buildings, also located in Sardinia, that looked in good conservation state. The results evidenced that the causes of degradation come from a high salt (especially sulphate) content and a scarce presence of binder in the plaster that can be imputed to a wrong initial composition and/ or to a leaching by acidic rain.

Cellulose Fibre Identification through Color Vectors of Stained Fibre

Simple, rapid staining analytical methods with visual color assessment are the most used in practice, but they involve problems including subjective error, low accuracy, qualitative results, and the necessity of using many kinds of stains and a great deal of morphology information for correct identification. A method of objective fiber identification using color vectors of a microscan from stained fibre digital photography is described in this report. A model set of cellulose fibres was prepared: groundwood; sulphate pulp; Whatman paper; and rag fibres. The objective micro-colorimetric method, using RGB (red, green, blue) vectors with discriminatory analysis, reduced the number of stains to 1; requires no morphological information; and the discriminatory power (dp,) of this approach is up to 95 to 100% of correctly identified unknown samples with one color vector R or B. A dp value of 100% was achieved when using 2-P or 3-P combinations of R, G, and B.

Measurement of water-holding capacity in raw and freeze-dried broiler breast meat with visible and near-infrared spectroscopy

The feasibility of using visible/near-infrared spectroscopy (vis/NIR) to segregate broiler breast fillets by water-holding capacity (WHC) was determined. Broiler breast fillets (n = 72) were selected from a commercial deboning line based on visual color assessment. Meat color (L*a*b*), pH (2 and 24 h), drip loss, and salt-induced water uptake were measured. Reflectance measurements were recorded from 400 to 2,500 nm in both raw and freeze-dried breast meat samples. Raw and freeze-dried samples had similar spectra in the visible region (400–750 nm), but the freeze-dried samples exhibited numerous bands in the NIR region (750–2,500 nm) corresponding to muscle proteins and lipids that were not observed in the NIR spectra of the raw samples. Linear discriminate analyses were used to classify fillets as high-WHC or low-WHC according to predicted meat quality characteristics. Using the visible spectra (400–750 nm), fillets could be correctly classified into high-WHC and low-WHC groups based on drip loss and salt-induced water uptake with 88 to 92% accuracy in raw samples and 79 to 86% accuracy in freeze-dried samples. Using the NIR spectra (750–2,500 nm), fillets could be correctly classified into high-WHC and low-WHC groups with 74 to 76% accuracy in raw samples and 85 to 86% accuracy in freeze-dried samples. Thus, freeze-drying enhanced the accuracy of WHC classification using the NIR portion of the spectra. Data from this study demonstrate the potential for utilizing vis/NIR spectroscopy as a method for classifying broiler breast meat according to WHC.

Gray and grayness—its complexities in color appearance of surface colors

Complexities on the roles of reference color gray and grayness are reviewed. They are essential in color appearance, but gray is an implicit color. Although “grayness” is not explicitly used in visual color assessment of surface colors or color order systems, gray can be combined with any colors having six primary‐color components using the term “grayish,” for example, grayish red and grayish yellow. However, the existing region of grayness is limited in a part of color‐appearance space. Illuminance dependency of gray perception is also clarified. Existence of two kinds of psychometric quantities are suggested: one is the attribute of grayness based on its psychological amount in a grayish color under study, and the other is the attribute of brightness of the grayish color under a specified illuminance, psychophysical quantity. The Nayatani‐Theoretical color order system, which uses three opponent‐colors axes, can clarify the above complexities of gray and grayness. Its importance is the same as six primary colors, red–green, yellow–blue, and white–black. © 2012 Wiley Periodicals, Inc. Col Res Appl, 39, 37–44, 2014

A comparison between a new visual method of colour matching by intraoral camera and conventional visual and spectrometric methods

ObjectivesThe objective of this study was to evaluate the new colour-matching Sopro Shade concept of the Sopro 717® intraoral camera (assisted visual evaluation method) by comparing it with the Vita 3DMaster® shade guide under the True Shade® lamp and the Vita Easyshade® spectrophotometric method. MethodsThe basic colour of the maxillary right central incisor and canine of 38 participants was determined by three examiners then repeated the next day using the three evaluation methods. Two examiners were experienced clinicians and one was a Sopro intraoral camera engineer. The Vita 3D-Master shade guide was used with all three colour-matching methods. Kendall's tau-b correlation coefficients between the different series of tooth-colour evaluations were computed and two-tailed t-tests for paired samples were applied. ResultsRegardless of the tooth examined, significant intra-examiner agreement (p<0.05) occurred between the visual and the assisted visual methods. Inter-examiner reliability was higher for canines than for central incisors, for all three methods. When comparing the two visual assessments with the spectrophotometric one, Kendall's tau-b correlation coefficients were lower. When comparing the two visual methods, significant agreement (p<0.05) was found for both canines and central incisors. ConclusionsWithin the limitations of this study, the Sopro Shade concept of the Sopro 717 intraoral camera is a reliable assistance to visual colour assessment compared with conventional visual methods. The reproducibility and reliability of all methods and examiners’ measurements for canines were generally higher than those for central incisors. The possible clinical impact of the lower level of agreement between the two visual methods (conventional and assisted) compared with spectrophotometry should be studied further.

Experimental investigations into visual and electronic tooth color measurement

The present study aimed to examine the validity of the visual color assessment and an electronic tooth color measurement system by means of Shade Inspector™ in comparison with a gold standard. Additionally, reproducibility of electronic measurements was demonstrated by means of two reference systems. Ceramic specimens of two thicknesses (h=1.6 mm, h=2.6 mm) were used. Three experienced dental technicians using the VITAPAN Classical(®) color scale carried out all visual tests. Validity of the visual assessment and the electronic measurements was confirmed separately for both thicknesses by means of lightness and hue of the VITAPAN Classical(®) color scale. Reproducibility of electronic measurements was confirmed by means of the VITAPAN Classical(®) and 3D-Master(®). The 3D-Master(®) data were calculated according to lightness, hue and chroma. Intraclass correlation coefficient (ICC) was used in assessing validity/reproducibility for lightness and chroma, Kappa statistics were used for hue. A level ≥0.75 was pre-established for ICC and ≥0.60 for the Kappa index. RESULTS OF VISUAL COLOR ASSESSMENT: Validity for lightness was good for both thicknesses; agreement rates for hue were inconsistent. ELECTRONIC MEASUREMENT: Validity for lightness was fair to good, hue values were below 0.60. Reproducibility of lightness was good to very good for both reference systems. Hue values (VITAPAN Classical(®)) for 1.6 mm test specimens were upside, for 2.6 mm below 0.60, Kappa values for 3D-Master(®) were ≥0.60 for all measurements, reproducibility of chroma was very good. Validity was better for visual than for electronic color assessment. Reproducibility of the electronic device by means of the Shade Inspector™ was given for the VITAPAN Classical(®) and 3D-Master(®) systems.

Stability of Vancomycin 25 mg/mL in Ora-Sweet and Water in Unit-Dose Cups and Plastic Bottles at 4°C and 25°C

Solutions of vancomycin for oral administration are not available commercially in Canada or the United States but are needed for patients who cannot swallow capsules. To evaluate the stability of vancomycin solutions stored in unit-dose cups and plastic bottles under refrigeration (4°C) and at room temperature (25°C) for up to 75 days. Vancomycin 25 mg/mL in Ora-Sweet vehicle and water (1:1 ratio by volume) was dispensed into opaque blue polyethylene unit-dose cups with aluminum seal (14 replicates) or amber plastic prescription bottles (6 replicates). Seven cups and 3 bottles were refrigerated (4°C), and the remainder of the containers were stored at room temperature (25°C). At the time of preparation and at 15, 30, 40, 50, 63, and 75 days, 3 aliquots were collected from one of the cups and from every bottle and were stored frozen (-85°C) until the time of analysis. Physical characteristics were evaluated at each time point, including measurement of pH and visual assessment of colour and precipitation. After thawing, the samples were analyzed in triplicate by a validated stability-indicating high-performance liquid chromatography method. A solution was considered stable if 90% of the initial concentration of vancomycin was maintained. No notable changes in colour, taste, or pH were observed in vancomycin solutions stored in the unit-dose cups at 4°C or 25°C or in the plastic bottles stored at 4°C over the 75-day study period. Starting on day 63, a white precipitate was observed in the solutions stored in plastic bottles at 25°C, but there were no notable changes in taste or pH during the 75-day period. The 95% confidence interval of the slope of the curve relating concentration to time, determined by linear regression, indicated that vancomycin solutions stored in cups or bottles at 4°C would maintain at least 93.6% of the initial vancomycin concentration for 75 days and that solutions stored at 25°C would maintain at least 90.0% of the initial concentration for 30 days (cups) or 26 days (bottles), with 95% confidence. Vancomycin 25 mg/mL stored in unit-dose cups or plastic bottles at 4°C was stable for at least 75 days, whereas solutions stored in cups or bottles at 25°C are expected to be stable for 30 or 26 days, respectively.

The linear shade guide design of Vita 3D‐master performs as well as the original design of the Vita 3D‐master

Visual tooth colour assessment by use of the Vita 3D-Master(®) (3D; Vita Zahnfabrik, Bad Säckingen, Germany) is well documented. To improve handling, a new linear arrangement of the shade tabs has been introduced (LG; Linearguide 3D-Master(®) ). The purpose of this study was to investigate whether the linear design has an effect on shade matching. Fifty-six students underwent identical, theoretical and practical training, by use of an Internet learning module [Toothguide Training Software(®) (TT)] and a standardised training programme [Toothguide Training Box(®) (TTB)]. Each student then matched 30 randomly chosen shade tabs presented in an intra-oral setting by a standardised device [Toothguide Check Box(®) (TCB)]; 15 matches were made using the 3D and 15 using the LG shade guide system, under a daylight lamp (840 matches for each guide). It was recorded to what extent the presented and selected shade tabs, or the lightness group of the tabs, matched, also the needed time for colour matching. The results showed that 35% of perfect matches were observed for the 3D and 32% for the LG. The lightness group was correct in 59% of cases for 3D and 56% for LG. Mean time needed for matching of tabs and lightness group was no different between groups (no significant difference for any assessment). Within the limitations of the study design, the colour assessment with regard to performance and time needed in shade matching was not different with the LG or the 3D. Therefore, the user should choose which shade tab arrangement is more applicable.

Combined effects of thymol, carvacrol and grapefruit seed extract on lipid oxidation and colour stability of poultry meat preparations

SummaryThe combined effects of thymol, carvacrol and grapefruit seed extract (GFSE) on lipid oxidation and colour stability of poultry meat preparations packaged in air or modified atmospheres (MAP: 5% O2; 30% CO2; 65% N2) were investigated using a simplex centroid mixture design. Lipid oxidation was evaluated through measurement of secondary oxidation products (malonaldehyde, MDA) and general appearance with visual assessment and instrumental measurement of colour. Thymol and carvacrol, as individual antioxidants, retarded the oxidation process by maintaining MDA values below 2 mg kg−1 meat. The effect of GFSE was less than thymol and carvacrol. Redness (a*) decreased in all treatments during storage but this reduction was more evident in the control and in samples containing GFSE than in thymol and carvacrol. Although colour acceptability decreased with time, all meat preparations packaged in air maintained desirable appearance better than samples in MAP. Also, off‐odours developed faster in the samples packaged in MAP than in aerobically packaged samples.