Infrared Image Analysis Research Articles

Research on Potential Pathological Knee Diagnosis for Undergraduates by Infrared Image Analysis

Research on Potential Pathological Knee Diagnosis for Undergraduates by Infrared Image Analysis

Classification of fresh and frozen-thawed pork muscles using visible and near infrared hyperspectral imaging and textural analysis

The potential of visible and near infrared hyperspectral imaging was investigated as a rapid and nondestructive technique for classifying fresh and frozen-thawed meats by integrating critical spectral and image features extracted from hyperspectral images in the region of 400–1000nm. Six feature wavelengths (400, 446, 477, 516, 592 and 686nm) were identified using uninformative variable elimination and successive projections algorithm. Image textural features of the principal component images from hyperspectral images were obtained using histogram statistics (HS), gray level co-occurrence matrix (GLCM) and gray level-gradient co-occurrence matrix (GLGCM). By these spectral and textural features, probabilistic neural network (PNN) models for classification of fresh and frozen-thawed pork meats were established. Compared with the models using the optimum wavelengths only, optimum wavelengths with HS image features, and optimum wavelengths with GLCM image features, the model integrating optimum wavelengths with GLGCM gave the highest classification rate of 93.14% and 90.91% for calibration and validation sets, respectively. Results indicated that the classification accuracy can be improved by combining spectral features with textural features and the fusion of critical spectral and textural features had better potential than single spectral extraction in classifying fresh and frozen-thawed pork meat.

Wavelet-based multifractal analysis of dynamic infrared thermograms to assist in early breast cancer diagnosis.

Breast cancer is the most common type of cancer among women and despite recent advances in the medical field, there are still some inherent limitations in the currently used screening techniques. The radiological interpretation of screening X-ray mammograms often leads to over-diagnosis and, as a consequence, to unnecessary traumatic and painful biopsies. Here we propose a computer-aided multifractal analysis of dynamic infrared (IR) imaging as an efficient method for identifying women with risk of breast cancer. Using a wavelet-based multi-scale method to analyze the temporal fluctuations of breast skin temperature collected from a panel of patients with diagnosed breast cancer and some female volunteers with healthy breasts, we show that the multifractal complexity of temperature fluctuations observed in healthy breasts is lost in mammary glands with malignant tumor. Besides potential clinical impact, these results open new perspectives in the investigation of physiological changes that may precede anatomical alterations in breast cancer development.

Procedure to diagnose onychomycosis through changes in emissivity on infrared images

A noninvasive, quick, reliable, and relatively cheap procedure for the diagnosis of onychomycosis is put forward. It is known that a nail may show an abnormal appearance, although only 50% of all the nails having such an appearance may owe it to the presence of onychomycosis; hence, adequate diagnosis of nail disease is needed for appropriate prescription of medication and treatment of the nail. In order to contribute to the process of improvement in the diagnosis, a procedure based on the analysis of medium-range infrared images is presented in which it is possible to observe energy changes mostly due to the changes in emissivity of the nail. As a nail is more affected by onychomycosis, such changes become more intense. Also, it was found that a nail without onychomycosis has a lower temperature than toe skin, but has a higher emission of energy. Fifty percent of the ailments that may a cause a fingernail or toenail to have an abnormal appearance are not considered in the present work.

Improving prediction accuracy of thermal analysis for weld-based additive manufacturing by calibrating input parameters using IR imaging

In experiments, it is usually difficult to accurately determine simulation input parameters such as heat source parameters, material properties at high temperature, etc. The uncertainty of such input parameters is responsible for the large error of thermal simulation for weld-based additive manufacturing. In this paper, a new approach is presented to calibrate uncertain input parameters. The approach is based on the solution of the inverse heat conduction problem of small-scale five-layer deposition and the application of the infrared (IR) imaging technique. The calibration of heat source parameters involves a multivariate optimization search using the pattern search method, whereas the calibration of the combined radiation and convection model includes a number of one-dimensional searches using the Fibonacci search method. Based on an in-depth analysis of IR images, thermal characteristics such as mean layer temperature and cooling rate are selected as the comparison results and included in cost functions. Lastly, the validity of the approach is demonstrated by a simulation case of 15-layer deposition with calibrated input parameters. The comparison between the simulated and experimental results verifies the improved prediction accuracy.

Accuracy of two forms of infrared image analysis of the masticatory muscles in the diagnosis of myogenous temporomandibular disorder

The aim of the present study was to assess the accuracy of two forms of infrared image analysis (area and extension) of the masseter and anterior temporalis muscles in the diagnosis of myogenous temporomandibular disorder (TMD). A cross-sectional study was carried out involving 104 female volunteers from the university community. Following the application of the Research Diagnostic Criteria for Temporomandibular Disorders, the volunteers were divided into a TMD group (n = 52) and control group (n = 52), and evaluated using infrared thermography. The area and extension of the masseter and anterior temporalis muscles were measured on the images. The receiver operating characteristic (ROC) curve was used to determine diagnostic accuracy (area under the curve), best cutoff point, sensitivity and specificity. A significant difference in skin temperature between groups was only found in the measurement of the area of the left anterior temporalis muscle (p = 0.011). The area under the ROC curve was less than the reference values for all muscles evaluated in the analyses of area and extension. Thus, neither method of infrared thermography tested for the quantification of the masseter and anterior temporalis muscles (analysis of area and extension) is consistent with the RDC/TMD for the diagnosis of myogenous TMD in women.

Accuracy and Reliability of Infrared Thermography in the Diagnosis of Arthralgia in Women With Temporomandibular Disorder

ObjectiveThe purpose of this study was to determine the accuracy and reliability of infrared thermography in the diagnosis of arthralgia in women with temporomandibular disorder. MethodsThirty women aged between 18 and 40 years were recruited for the study. The Research Diagnostic Criteria for Temporomandibular Disorders was used to allocate the volunteers to the control group (n = 15) and arthralgia group (n = 15). Both groups were submitted to infrared thermography of the temporomandibular joint (TMJ), followed by a punctual analysis of the images. The Mann-Whitney U test was used for the comparison of skin surface temperature between groups. The intraclass correlation coefficient was calculated to determine the reliability of the infrared image analysis. The receiver operating characteristic curve was used to determine the accuracy of the diagnosis. ResultsSkin temperature was significantly greater over the left (P = .004) and right (P = .012) TMJ in the arthralgia group. The intraclass correlation coefficient ranged from 0.841 to 0.874. The area under the receiver operating characteristic curve ranged from 0.598 to 0.675. ConclusionExcellent intrarater and interrater reliability was found in the analysis of the infrared images of the TMJ. However, infrared thermography demonstrated a low accuracy in the diagnosis of arthralgia in women with temporomandibular disorder.

Intra and inter-rater reliability of infrared image analysis of masticatory and upper trapezius muscles in women with and without temporomandibular disorder

Infrared thermography is an aid tool that can be used to evaluate several pathologies given its efficiency in analyzing the distribution of skin surface temperature. To propose two forms of infrared image analysis of the masticatory and upper trapezius muscles, and to determine the intra and inter-rater reliability of both forms of analysis. Infrared images of masticatory and upper trapezius muscles of 64 female volunteers with and without temporomandibular disorder (TMD) were collected. Two raters performed the infrared image analysis, which occurred in two ways: temperature measurement of the muscle length and in central portion of the muscle. The Intraclass Correlation Coefficient (ICC) was used to determine the intra and inter-rater reliability. The ICC showed excellent intra and inter-rater values for both measurements: temperature measurement of the muscle length (TMD group, intra-rater, ICC ranged from 0.996 to 0.999, inter-rater, ICC ranged from 0.992 to 0.999; control group, intra-rater, ICC ranged from 0.993 to 0.998, inter-rater, ICC ranged from 0.990 to 0.998), and temperature measurement of the central portion of the muscle (TMD group, intra-rater, ICC ranged from 0.981 to 0.998, inter-rater, ICC ranged from 0.971 to 0.998; control group, intra-rater, ICC ranged from 0.887 to 0.996, inter-rater, ICC ranged from 0.852 to 0.996). The results indicated that temperature measurements of the masticatory and upper trapezius muscles carried out by the analysis of the muscle length and central portion yielded excellent intra and inter-rater reliability.

Fourier transform infrared imaging analysis in discrimination studies of bladder cancer

Bladder carcinoma represents more than 4% of all cancer diseases in Austria. The histomorphological evaluation is invasive and remains a subjective and time consuming technique. On account of this it is necessary to find novel non-invasive approaches which support the pathologists for histological recognition to identify malignancy at an early stage. In the present study, Fourier transform infrared (FTIR) microscopic imaging was combined with univariate and multivariate data analysis methods to study bladder carcinoma tissue sections in detail. The possibility to collect IR spectra of bladder carcinoma tissue sections employing an optimized analytical protocol is demonstrated. The correlation between FTIR microscopic imaging and the morphological tissue features obtained by histological staining of the sections demonstrated that many histomorphological tissue patterns can be visualized in the colour images. The routine generation of high quality imaging data is enabled because of the combination of FTIR technology and optimized sample preparation techniques. This opens a new quality of spectroscopic analyses of cancerous tissue, allowing exploration of molecular changes associated with the histopathological morphology.

Fourier transform infrared imaging analysis in discrimination studies of St. John's wort (Hypericum perforatum)

In the present study, Fourier transform infrared (FTIR) imaging and data analysis methods were combined to study morphological and molecular patterns of St. John's wort (Hypericum perforatum) in detail. For interpretation, FTIR imaging results were correlated with histological information gained from light microscopy (LM). Additionally, we tested several evaluation processes and optimized the methodology for use of complex FTIR microscopic images to monitor molecular patterns. It is demonstrated that the combination of the used spectroscopic method with LM enables a more distinct picture, concerning morphology and distribution of active ingredients, to be gained. We were able to obtain high-quality FTIR microscopic imaging results and to distinguish different tissue types with their chemical ingredients.

Real-Time Infrared Image Analysis for Deformation Heat of Precast Defected PVC Sheet Based on MATLAB

In a deformation progress of a polyvinyl chloride sheet, the coupled deforming heat is recorded by a thermal infrared imager. In order to have a real-time study for the variation regularity of the deforming temperature field distribution, all infrared images are imported into MATLAB software as digital data through a dynamic link routine compiled based on MATLAB and Windows. By utilizing a gradient-based transition region extraction algorithm and an interpolation algorithm, the high-resolution recognized and reconstructed infrared images are obtained from original blurring images recorded in thermal infrared imager. The variations of temperature distribution are studied combining with the test data based on MATLAB.

Improved Image Target Detection Based on Component Analysis

Image target detection and tracking is an important research field of image processing for its great potential in Military and Civil applications. This paper proposes improved image target detection based on component analysis. At first, it explains the concept about image connected region. Then, it introduces the component analysis algorithm to extract connected components, and uses support vector machine to classify the target region. It is very useful to Forward Looking Infra-Red image processing and analysis. The experiments performed on Forward Looking Infra-Red images, and the results show that the proposed algorithm is effective.

Thermal infrared anomalies as a precursor of strong earthquakes in the distant future

Satellite thermal infrared images contain valuable earthquake precursor information. Past studies concluded that such information appeared only a few days or dozens of days before an earthquake would occur. In our study, though, we observed that the time intervals between the thermal infrared precursor and an earthquake’s occurrence can be up to 10 years. An infrared image can also synchronously indicate the locations of additional future earthquakes with different epicenters within a region. The shape, area, intensity, and movement of thermal infrared anomaly areas are a combination of all the future strong earthquakes within a region. These distant future earthquakes are generally located near the edges, endpoints, or corners of the main structure, fine structures or periphery structures of a thermal infrared anomaly area and play a role in confining the anomaly area. There have not been any exceptions among the strong earthquakes we analyzed, which have included the 2011 Japan Mw 9 event, the 2010 Yushu MS 7.1 event, the 2008 Wenchuan MS 8 event, and many other strong events following the 2004 Sumatra MS 9 event. Surprisingly, some of the earthquakes can outline an area of elevated temperature observed many months ago. If we can roughly locate these potential epicenters through the analysis of thermal infrared images and combining the analysis with other information, and then dynamically monitor them, it may be easier to observe the precursor of an earthquake and predict its occurrence.

Critical evaluation of methods for end-point determination in pharmaceutical blending processes

This paper compares existing approaches to the monitoring of pharmaceutical blending processes and the detection of their end-point by use of near infrared spectroscopy (NIRS). To this end, we examined homogenization in a pharmaceutical mixture containing a relatively low concentration (<4%) of an API that exhibits low absorption in the NIR region and is difficult to blend with excipients. The end-point of the process (viz. where a uniform distribution of the API in the mixture was reached) was determined by using various qualitative and quantitative spectral treatments for comparison. The results revealed the capabilities of different spectral treatments for establishing blend homogeneity, which can be especially useful with a view to optimizing their industrial use. API distribution uniformity in the final blend was confirmed by near infrared chemical imaging (NIR-CI) analysis.

Near Infrared Image Analysis for Online Identification and Separation of Wood Chips with Elevated Levels of Extractives

Forest-based biorefinery feedstocks are usually broken up into wood chips prior to any form of processing. These wood chips have a complex and highly variable composition, although they may look identical to an inexperienced observer. Some chips have high contents of valuable extractives. Therefore, it would be desirable to separate such chips that are rich in extractives. Various fractions of pine and spruce wood were used to acquire near infrared (1000–2498 nm) hyperspectral images in order to explore the usefulness of multivariate image analysis for detection and separation purposes. Multivariate modelling by image principal component analysis detected large variations in extractive content among wood chips of different biomass types, for example, sapwood, heartwood and knotwood. The extractive parts could be classified in the images and their content could be reasonably well predicted. Partial least squares (PLS) regression models could be made between collected spectra and measured extractive contents. These worked better for milled and homogenised bulk samples than for average image spectra. Regression coefficients showed that the C–H bonds in the spectra were responsible for the validity of the models. The average image PLS models could be used to make prediction images showing the location of the regions with high extractive content in knotwood. The results indicate that extremely rapid spectral-based fractionation could be used to separate tailored biomass streams of wood chips.

Hyperspectral near Infrared Image Analysis of a Phenol Formaldehyde Resin Curing Reaction

In the production of sandpaper, a phenol formaldehyde polymer bonds the abrasive material to a backing material made of paper or a textile. The reaction takes place at elevated temperatures (90–120°C) for a long time (at least eight hours) and is thereby a very energy-demanding process step. A possible future application would be to use near infrared (NIR) hyperspectral imaging (1000–2498 nm) for (1) monitoring the curing reaction and determining an end point for it and (2) for identifying in homogeneous regions with low adhesion in the final product. A feasibility study was carried out on four series of resin-coated backing materials without abrasives. These were imaged at half hour intervals for eight hours of curing using a NIR line scan imager. In order to analyse the influence of the backing material on the net NIR signal from resin-coated samples, spectra of the backing material (paper, textile) were also collected using a moving grating NIR spectrometer (1100–2498 nm). Results from principal components analysis of the hyperspectral images indicated that the reaction was stabilised after five to six hours, although it continued slowly for at least 16 more hours. A relevant question was when to finish the heating (curing) and still obtain a final product of high quality. Partial least squares regression models for predicting the curing time were thus also evaluated. A calibration made on image mean spectra was used for predicting the curing time of each pixel in the full set of hyperspectral images. The predicted images showed the curing progress, in homogeneous regions where the reaction had progressed to a slower extent and other physical abnormalities (for example air bubbles). Pixel prediction distribution analysis of the images was found useful for determining the significant number of components of the proposed regression models.

Fourier transform infrared imaging analysis in discrimination studies of squamous cell carcinoma

Oral squamous cell carcinoma (OSCC) of the oral cavity and oropharynx represents more than 95% of all malignant neoplasms in the oral cavity. Histomorphological evaluation of this cancer type is invasive and remains a time consuming and subjective technique. Therefore, novel approaches for histological recognition are necessary to identify malignancy at an early stage. Fourier transform infrared (FTIR) imaging has become an essential tool for the detection and characterization of the molecular components of biological processes, such as those responsible for the dynamic properties of tumor progression. FTIR imaging is a modern analytical technique enabling molecular imaging of a complex biological sample and is based on the absorption of IR radiation by vibrational transitions in covalent bonds. One major advantage of this technique is the acquisition of local molecular expression profiles, while maintaining the topographic integrity of the tissue and avoiding time-consuming extraction, purification, and separation steps. With this imaging technique, it is possible to obtain unique images of the spatial distribution of proteins, lipids, carbohydrates, cholesterols, nucleic acids, phospholipids, and small molecules with high spatial resolution. Analysis and visualization of FTIR imaging datasets are challenging and the use of chemometric tools is crucial in order to take advantage of the full measurement. Therefore, methodologies for this task based on the novel developed algorithm for multivariate image analysis (MIA) are often necessary. In the present study, FTIR imaging and data analysis methods were combined to optimize the tissue measurement mode after deparaffinization and subsequent data evaluation (univariate analysis and MIAs). We demonstrate that it is possible to collect excellent IR spectra from formalin-fixed paraffin-embedded (FFPE) tissue microarrays (TMAs) of OSCC tissue sections employing an optimised analytical protocol. The correlation of FTIR imaging to the morphological tissue features obtained by histological staining of the sections demonstrated that many histomorphological tissue patterns can be visualized in the colour images. The different algorithms used for MIAs of FTIR imaging data dramatically increased the information content of the IR images from squamous cell tissue sections. These findings indicate that intra-operative and surgical specimens of squamous cell carcinoma tissue can be characterized by FTIR imaging.

Two-Stage Automated Defect Recognition Algorithm for the Analysis of Infrared Images

In this article an algorithm for the analysis of raw thermal infrared images is proposed. The images are obtained by using the nondestructive evaluation method of the laser-spot thermography and aim at detecting the presence of surface defects. A laser is used to scan a test specimen through the generation of single pulses. The temperature distribution produced by this thermoelastic source is measured by an infrared camera and processed with a two-stage algorithm. In the first stage, simple mathematical and statistical parameters are used to flag the presence of damage. Then, once damage is detected, the thermal image's first and second spatial derivative and two spatial filters are computed to enhance contrast, and to locate and size the defect. Some of the advantages of the proposed method with respect to existing approaches include automation in the defect detection process and better defective area isolation through increased contrast. The algorithm is first proven by analyzing simulated thermal images, and then it is experimentally validated by scanning the surface of a CFRP composite plate with induced defects.

Ice Detection Based on Near Infrared Image Analysis

In order to detect the ice on aircraft wings, a method based on near infrared image processing is proposed. According to the variety of near-infrared reflectivity, four images of one object are obtained under different detection wavelengths. Water and ice can be distinguished by the different variation trends of near infrared images. In this paper, 1.10μm, 1.16μm, 1.26μm and 1.28μm are selected to be the detection wavelengths. The images of Carbon Fiber Composite material aircraft wings partially covered by water or ice are obtained and analyzed. Parameter D can reflect the variation trend of relative near-infrared reflectivity, so that Parameter D also can be the distinguish basis. The results of the experiment show that the method proposed in this paper is available for ice detection.

Real-Time Monitoring of Weld Pool during GTAW using Infra-Red Thermography and analysis of Infra-Red thermal images

Real-time monitoring of the weld pool using infra-red (IR) thermography during gas tungsten arc (GTA) welding is gaining importance due to the requirements for on-line monitoring and control of the welding process. To facilitate real-time monitoring of the weld pool, a computer-controlled GTA welding machine with sensing of the weld pool using IR camera has been developed. The IR camera, mounted on the torch assembly, monitors the molten pool and the surface temperature distribution surrounding the weld pool during GTA welding. Temperature profiles were measured on the plates using thermocouples in combination with IR thermography to determine the emissivity of the plate surface. GTA welding was carried out on 3 mm-thick 316LN stainless steel (SS) plates under different welding conditions. IR thermal images were acquired on-line and analysed. A linear relationship was obtained between the thermal bead width, determined by line-scan analysis technique, and the actual bead width, measured by cross-sectional optical microscopy. The computed macroscopic temperature gradient and the actual of weld bead depth of penetration showed an inverse relationship. Full-frame analysis was carried out to estimate the surface temperature distribution for square-butt weld joints. For 1316LN SS weld joints, IR thermal signatures were acquired for various weld defects, such as lack of fusion, lack of penetration and tungsten inclusions, for use as reference signatures for on-line monitoring during GTA welding.