Image Analysis Criteria Research Articles

Energy-efficient and fast IMPLY-based approximate full adder applying NAND gates for image processing

Today’s processing applications require frequent and energy-consuming data transfers between memory and processing elements. Reducing the dimensions of Metal Oxide Semiconductor Field Effect Transistors (MOSFETs) brings essential problems. Therefore, applying emerging technologies should be considered as a solution. As a crossbar array compatible technology, memristors can play the computing and memory device roles. Therefore, it is suitable for In-Memory Computing (IMC). The issue of changing the computation method to achieve higher efficiency can also be considered. Today, approximate computing is of great interest for error-tolerant applications. These two concepts are applied, and an approximate serial full adder based on the Material Implication (IMPLY) method is introduced. The proposed Serial Approximate Full Adder using NAND gates (SAFAN) reduces the number of steps and energy consumption by up to 30% and 26% compared to approximate ones, 70% and 68% compared to exact ones, respectively. The error analysis results show that the accuracy decreases to a reasonable level by applying the SAFAN to the least significant bits (LSBs) of an approximate 8-bit adder. Image analysis criteria evaluated the functionality of the SAFAN in image processing applications, and the results showed the suitable performance of the SAFAN in error-tolerant applications.

Correlation between clinical symptoms and cone beam computed tomography finding in temporomandibular disorders patients

Background: Abnormalities of temporomandibular joint, masticatory muscles, and/or related structural abnormalities are known as temporomandibular disorders. The use of cone beam computed tomography for temporomandibular imaging is becoming more prevalent. Aim: This study was carried out to analyse correlation between clinical symptoms and cone beam computed tomography finding in temporomandibular disorders patients. Methods and materials: This study looked at cone beam computed tomography pictures and clinical records of 40 patients with temporomandibular joint issues who sought treatment in Sangli district of Maharashtra between 2016 and 2018. The type of condylar bony change was classified based on the cone beam computed tomography images using both Koyama et al's classification and Ahmad et al's image analysis criteria. An orofacial pain specialist took a complete history and did a clinical assessment on all of the participants. The average pain intensity level self-reported in the previous week was graded on a 0 to 10 verbal rating scale, with "0" indicating no pain and "10" indicating the worst pain possible. Results: The greatest condyle bony change and verbal pain rating had a poor association. There was no statistically significant link between maximum condyle alteration and maximum openness.

Web-based educational programme for temporomandibular joint assessment with cone-beam computed tomography.

To develop and evaluate an educational web-based programme for temporomandibular joint (TMJ) assessment using cone-beam computed tomography (CBCT). A web-based educational programme was designed for TMJ assessment using CBCT images. Fifteen CBCT cases of the TMJ (three-dimensional reconstructed volumes) and an assessment module based on image analysis criteria in the Diagnostic Criteria for Temporomandibular Disorders (DC/TMD) were added to the programme. Thirty-six undergraduate dental students were invited to test the programme by assessing all cases twice: before and after 2months of training. Participants submitted written subjective evaluations of the programme. The web-based programme can be accessed on Malmö University webpage (www.cbct-tmj.mau.se). Despite limited CBCT learning in their undergraduate training and not using the programme in the 2-month interval, the students were able to correctly diagnose 80% of the cases at the second assessment. Their diagnoses, however, did not differ significantly from the first assessment. Overall, the students were satisfied with the programme and considered it user-friendly. The web-based educational programme that was developed in the present study and tested by dental students could be a useful educational tool for TMJ assessment using CBCT.

Automated Detection of TMJ Osteoarthritis Based on Artificial Intelligence

The purpose of this study was to develop a diagnostic tool to automatically detect temporomandibular joint osteoarthritis (TMJOA) from cone beam computed tomography (CBCT) images with artificial intelligence. CBCT images of patients diagnosed with temporomandibular disorder were included for image preparation. Single-shot detection, an object detection model, was trained with 3,514 sagittal CBCT images of the temporomandibular joint that showed signs of osseous changes in the mandibular condyle. The region of interest (condylar head) was defined and classified into 2 categories—indeterminate for TMJOA and TMJOA—according to image analysis criteria for the diagnosis of temporomandibular disorder. The model was tested with 2 sets of 300 images in total. The average accuracy, precision, recall, and F1 score over the 2 test sets were 0.86, 0.85, 0.84, and 0.84, respectively. Automated detection of TMJOA from sagittal CBCT images is possible by using a deep neural networks model. It may be used to support clinicians with diagnosis and decision making for treatments of TMJOA.

Anatomical region segmentation method from dermoscopic images of pigmented skin lesions

AbstractMelanoma tumor can cause a serious life threatening problem in humans, if left untreated for a long time without early diagnosis. For early diagnosis of melanoma, it is more significant to develop novel methods based on biophysics analyses, molecular targets recognitions, and new image analysis criteria. In this article, anatomical region segmentation and diameter identification is proposed to detect melanoma from dermoscopic images. Four main steps of the proposed system are as follows: In the first step, the preprocessing is performed to smooth the melanoma extraction process. The region segmentation is done in the second step using watershed segmentation and Sobel operator. In the third step, the postprocessing procedures like as morphological open, canny edge detection also applied to improve the region of interest. Finally, the melanoma region is identified using color symmetry features. The proposed method is tested with two data sets to prove the performance proposed method. The proposed method achieved an accuracy of 95.31% and specificity of 98.3%, which is better than other methods. Experimental results show that the effectiveness of the proposed method and illustrate viability of real‐time clinical applications.

Magnetic resonance enterography in inflammatory small bowel disease. image analysis criteria

Today magnetic resonance enterography is one of the most informative and safe methods of identification of the manifistations and complications of Crohn’s disease among children and adults. Receipt of the high-informaitive MR-enterograms directly depends on the right preparation of the patient and the competent research. The article deals with semiotics of the small bowel lesions in Crohn’s disease. The qualitative and quantitative analysis of the images are also represented.

Incidental findings of temporomandibular joint osteoarthritis and its variability based on age and sex.

PurposeThis study investigated the prevalence of temporomandibular joint osteoarthritis (TMJ-OA) using the Research Diagnostic Criteria for Temporomandibular Disorders image analysis criteria, assessed the severity of incidental osteoarthritic changes affecting the TMJ, and evaluated the correlations of sex and age with the prevalence and severity of TMJ-OA.Materials and MethodsThis retrospective study assessed 145 randomly selected cone-beam computed tomography scans (261 TMJs) from the authors' institutional maxillofacial radiology archive following the application of inclusion and exclusion criteria. The criteria described by Ahmad et al. were used to determine whether each TMJ was affected by OA, and the severity of the osteoarthritic changes was scored for each joint based on the method described by Alexiou et al. The chi-square, McNemar, Bhapkar chi-square, and Stuart-Maxwell chi-square tests were applied to evaluate the significance of the relationships between variables (age and sex).ResultsSixteen TMJs (6.1%) had no OA, 74 (28.6%) were indeterminate for OA, and 171 (65.5%) had OA. Flattening and sclerosis were observed in 86.6% and 12.3% of cases, respectively, while resorption was observed in 7.3% of the joints. Only 21 (8.1%) of the examined TMJs had subchondral cysts. Erosion of the articular eminence was observed in 58 (22.1%) cases, while sclerosis and resorption were found in 68 (25.9%) and 16 (6.1%) TMJs, respectively.ConclusionFemale patients had a higher prevalence and severity of TMJ-OA than male patients. The prevalence and severity of TMJ-OA increased with age, with peaks in the fifth and seventh decades of life.

CBCT characteristics and interpretation challenges of temporomandibular joint osteoarthritis in a hand osteoarthritis cohort.

To characterise osteoarthritis (OA) in the temporomandibular joints (TMJs) by means of cone beam CT in a hand OA population, and identify interpretation challenges. The TMJs of 54 individuals (mean age 71.3) recruited from the "The Oslo hand OA cohort", independently of TMJ-related symptoms, were examined with cone beam CT (ProMax MidCBCT). Images were analysed for bone change characteristics and each joint was diagnosed with either OA, no OA or as indeterminate for OA. The image analysis criteria developed for the Research Diagnostic Criteria for Temporomandibular Disorders were used. Frequencies of bone changes, joint diagnoses and severity grades (1-2) were calculated, as well as κ values for observer agreement. In the OA joints, the most frequent bone changes occurred in the condyle: flattening (79%), osteophyte (72%) and subcortical sclerosis (70%). The most frequent changes in the fossa/eminence were flattening (57%), erosion (49%) and subcortical sclerosis (47%). 53 (49%) of the 108 joints were diagnosed with TMJ OA (68 % Grade 2), 29 joints (27%) with no OA, and 26 joints (24%) were indeterminate for OA. Inter- and intraobserver agreement showed mean κ values of 0.67 and 0.62, respectively. TMJ changes were common in elderly with hand OA and characterised by bone productive changes. The radiologic features indicated a late stage TMJ OA. Interpretation challenges related to subtle changes were identified and are reflected by the rather low observer agreement. The diagnosis of TMJ OA should be based on evident and clear abnormalities only.

Images in biology: are instructional criteria used in textbook image design?

ABSTRACTThis paper analyses the extent to which textbook images are designed using the Instructional Criteria for Image Analysis (ICIA) model in textbooks. The ICIA proposed that learning through images involves interaction between the learner, the image, and the activities with images proposed to the student. Images from the main text and activity section of eleven primary and secondary school textbooks on the human body were analysed regarding the extent to which they fit the proposed criteria. Images in the main text were analysed according to size and type, presence of visual elements (graphical elements, colour, enlarged details), verbal elements (caption, labels) and reference to the image within the text, while images in the activity sections were analysed according to learning involved (task type, procedure, processing level). Results show unequal presence of these criteria in both primary and secondary school textbooks. There are some differences between primary and secondary levels (predominant image type, degree of image contextualisation and processing level required). Images should not be considered self-evident. Images should be designed based less on aesthetic and decorative criteria and more on instructional criteria such as ICIA proposed in order to support image-based learning processes and increase the potential value of images as learning tools.

Quantitative Analysis of High-Resolution Microendoscopic Images for Diagnosis of Esophageal Squamous Cell Carcinoma

High-resolution microendoscopy is an optical imaging technique with the potential to improve the accuracy of endoscopic screening for esophageal squamous neoplasia. Although these microscopic images can be interpreted readily by trained personnel, quantitative image analysis software could facilitate the use of this technology in low-resource settings. In this study, we developed and evaluated quantitative image analysis criteria for the evaluation of neoplastic and non-neoplastic squamous esophageal mucosa. We performed an image analysis of 177 patients undergoing standard upper endoscopy for screening or surveillance of esophageal squamous neoplasia, using high-resolution microendoscopy, at 2 hospitals in China and at 1 hospital in the United States from May 2010 to October 2012. Biopsy specimens were collected from imaged sites (n= 375), and a consensus diagnosis was provided by 2 expert gastrointestinal pathologists and used as the standard. Quantitative information from the high-resolution images was used to develop an algorithm to identify high-grade squamous dysplasia or invasive squamous cell cancer, based on histopathology findings. Optimal performance was obtained using the mean nuclear area as the basis for classification, resulting in sensitivities and specificities of 93% and 92% in the training set, 87% and 97% in the test set, and 84% and 95% in an independent validation set, respectively. High-resolution microendoscopy with quantitative image analysis can aid in the identification of esophageal squamous neoplasia. Use of software-based image guides may overcome issues of training and expertise in low-resource settings, allowing for widespread use of these optical biopsy technologies.

Evidence Based Approach for the Diagnosis of Temporomandibular Joint Disorders (TMD).

Evidence Based Approach for the Diagnosis of Temporomandibular Joint Disorders (TMD).

Temporomandibular joint diagnosis: striking a balance between the sufficiency of clinical assessment and the need for imaging

Temporomandibular joint diagnosis: striking a balance between the sufficiency of clinical assessment and the need for imaging

Quantificação de atributos micromorfológicos (microfábrica) de depósito de encosta por meio de classificação de imagem

Apresenta-se uma aplicação de classificação de imagens digitais capturadas em lâminas micromorfológicas na caracterização da freqüência relativa dos constituintes e das microfeições identificadas em depósito de encosta. Ao todo foram capturadas 26 imagens em lâmina representativa da base de uma seqüência de três unidades coluvionares, no Planalto Basáltico – SW PR. Para classificar as imagens utilizou-se funções do software SPRING 5.0, com as quais se produziu três padrões de classificação por imagem capturada: i) distribuição relativa dos constituintes – DRC (esqueleto, plasma e poros); ii) distribuição relativa das microfeições – DRMf (esqueleto, poros, hipocutãs de depleção de poros, microfeições de depleção, microfeições de impregnação, preenchimentos finos, preenchimentos densos e cutãs; e iii) distribuição relativa das microfeições agrupadas por processos micromorfológicos – DRMP (esqueleto, poros, microfeições de impregnação, microfeições de depleção e acumulações plásmicas intrusivas. A quantificação do resultado dessa classificação de imagens se deu pelo cálculo de área por classe temática e da área total da imagem. Estabeleceu-se percentuais das classes temáticas com base no cálculo de área e se aplicou parâmetros de tendência central para os dados individuais (média aritmética, desvio padrão, coeficiente de variância) e para os dados agrupados em classes (média aritmética e moda). Como resultado obteve-se em média 2% de esqueleto, 95% de plasma e 3% de poros. As microfeições plásmicas são em cerca de 5% de hipocutãs de depleção de poro, 32% de microfeições de depleção, 50% de microfeições de impregnação, 5% de preenchimento fino, 3% de preenchimento denso e menos de 1% de cutãs. Agrupadas por processos micromorfológicos registrou-se em média 34% de depleção, 53% de impregnação e 9,5% de acumulações plásmicas intrusivas. Enfim, os critérios de análise de imagem utilizados neste trabalho podem ser aplicados para análises similares em coberturas pedológicas.

Correlating cone beam CT results with temporomandibular joint pain of osteoarthritic origin

The purpose of this study was to determine whether bony changes in temporomandibular joint (TMJ) osteoarthritis (OA) is correlated with pain and other clinical signs and symptoms. Clinical data and cone beam CT (CBCT) images of 30 patients with TMJ OA were analysed. The criteria of Koyama et al (Koyama J, Nishiyama H, Hayashi T. Follow-up study of condylar bony changes using helical computed tomography in patients with temporomandibular disorder. Dentomaxillofac Radiol 2007; 36: 472-477.) and Ahmad et al [Ahmad M, Hollender L, Anderson Q, Kartha K, Ohrbach R, Truelove EL, et al. Research diagnostic criteria for temporomandibular disorders (RDC/TMD): development of image analysis criteria and examiner reliability for image analysis. Oral Surg Oral Med Oral Pathol Oral Radiol Endod 2009; 107: 844-860.] were used to classify the condyles observed on the CBCT. Clinical measures included self-reported pain, mandibular range of motion, TMJ sound, pain on palpation of the TMJ and masticatory muscles, and pain on jaw function. Generalized linear modelling was used to correlate the clinical and radiographic findings and Spearman's rho was used to correlate the two classification systems. There was poor correlation between the maximum condyle change and pain rating (Koyama: r² = 0.1443, p = 0.3995; Ahmad: r² = 0.0273, p = 0.9490), maximum mouth opening (Koyama: r² = 0.2910, p = 0.0629; Ahmad: r² = 0.2626, p = 0.0951), protrusion (Koyama: r² = 0.0875, p = 0.7001; Ahmad: r² = 0.1658, p = 0.3612), right lateral motion (Koyama: r² = 0.0394, p = 0.9093; Ahmad: r² = 0.0866, p = 0.6877) and left lateral motion (Koyama: r² = 0.0943, p = 0.6494; Ahmad: r² = 0.1704, p = 0.3236). Strong correlation was observed between Koyama et al's and Ahmad et al's classifications for average (r = 0.9216, p < 0.001) and maximum (r = 0.7694; p < 0.0001) bony change. There was poor correlation between condylar changes (as observed on CBCT images), pain and other clinical signs and symptoms in TMJ OA.

Evaluation of quantitative image analysis criteria for the high-resolution microendoscopic detection of neoplasia in Barrett’s esophagus

Early detection of neoplasia in patients with Barrett's esophagus is essential to improve outcomes. The aim of this ex vivo study was to evaluate the ability of high-resolution microendoscopic imaging and quantitative image analysis to identify neoplastic lesions in patients with Barrett's esophagus. Nine patients with pathologically confirmed Barrett's esophagus underwent endoscopic examination with biopsies or endoscopic mucosal resection. Resected fresh tissue was imaged with fiber bundle microendoscopy; images were analyzed by visual interpretation or by quantitative image analysis to predict whether the imaged sites were non-neoplastic or neoplastic. The best performing pair of quantitative features were chosen based on their ability to correctly classify the data into the two groups. Predictions were compared to the gold standard of histopathology. Subjective analysis of the images by expert clinicians achieved average sensitivity and specificity of 87% and 61%, respectively. The best performing quantitative classification algorithm relied on two image textural features and achieved a sensitivity and specificity of 87% and 85%, respectively. This ex vivo pilot trial demonstrates that quantitative analysis of images obtained with a simple microendoscope system can distinguish neoplasia in Barrett's esophagus with good sensitivity and specificity when compared to histopathology and to subjective image interpretation.

Research diagnostic criteria for temporomandibular disorders (RDC/TMD): development of image analysis criteria and examiner reliability for image analysis

As part of the Multisite Research Diagnostic Criteria For Temporomandibular Disorders (RDC/TMD) Validation Project, comprehensive temporomandibular joint diagnostic criteria were developed for image analysis using panoramic radiography, magnetic resonance imaging (MRI), and computerized tomography (CT). Interexaminer reliability was estimated using the kappa (kappa) statistic, and agreement between rater pairs was characterized by overall, positive, and negative percent agreement. Computerized tomography was the reference standard for assessing validity of other imaging modalities for detecting osteoarthritis (OA). For the radiologic diagnosis of OA, reliability of the 3 examiners was poor for panoramic radiography (kappa = 0.16), fair for MRI (kappa = 0.46), and close to the threshold for excellent for CT (kappa = 0.71). Using MRI, reliability was excellent for diagnosing disc displacements (DD) with reduction (kappa = 0.78) and for DD without reduction (kappa = 0.94) and good for effusion (kappa = 0.64). Overall percent agreement for pairwise ratings was >or=82% for all conditions. Positive percent agreement for diagnosing OA was 19% for panoramic radiography, 59% for MRI, and 84% for CT. Using MRI, positive percent agreement for diagnoses of any DD was 95% and of effusion was 81%. Negative percent agreement was >or=88% for all conditions. Compared with CT, panoramic radiography and MRI had poor and marginal sensitivity, respectively, but excellent specificity in detecting OA. Comprehensive image analysis criteria for the RDC/TMD Validation Project were developed, which can reliably be used for assessing OA using CT and for disc position and effusion using MRI.

Precise CCD image analysis for planar laser-induced fluorescence experiments

The goal of this paper is to describe essential criteria for image analysis of planar laser-induced fluorescence (PLIF) signals. A new image file conversion method is introduced and some typical illustrative examples showing the potential applications of the method in PLIF experiments are presented. Analysis of row, column, and total pixel counts, and the dark noise related to an image are discussed. Image segmentation, averaging and background correction can be easily done by the reported method. In our analysis it is straightforward to inspect the pixel counts and check for saturation of the camera sensors. It is also feasible to obtain a particular row or column for interpretation and it offers an easy way to check the validity of the captured images. Furthermore, the method offers a sensitive technique to check pulse-to-pulse variation of the excitation laser by using frame-to-frame fluorescence image data comparison, which is more illustrative than power checking by other means. The overall results show that the developed conversion method reported here can be effectively used to obtain more in-depth and quantitative information out of the raw data for the PLIF experiments.

Computer-assisted cell morphometry and ploidy analysis in the assessment of thyroid follicular neoplasms.

Conventional cytology cannot discriminate between benign and malignant follicular neoplasms. Our study evaluated the diagnostic role of computer-assisted image analysis in the presurgical assessment of thyroid follicular neoplasms. Fifty-eight patients (14 males, 44 females, age range, 45-75 years) who underwent surgery for cytologic diagnosis of thyroid follicular neoplasm were studied. All patients were first evaluated on clinical grounds and assigned a high/low suspicion of malignancy on the basis of gender, age, and nodule size. Cell image analysis was subsequently performed using a Cytometrica BYK Gulden microscope image processor on Feulgen-stained thyroid cytologic smears. A different population of 50 benign and 50 malignant, histologically evaluated nodules was studied in order to establish image analysis criteria suggestive of thyroid malignancy. Ploidy histogram, proliferation index (PI), nuclear area coefficient of variation (NACV), and anisocariosis ratio (AR) were studied. Thyroid cancer was diagnosed in 16 of 58 follicular neoplasms. Only 7 of these lesions were clinically suspicious (43.7%), whereas 14 of 16 (87.5%) malignant tumors were identified by image analysis. Positive and negative predictive values of image analysis versus clinical evaluation were 46.6% versus 30.4% and 92.8% versus 74.3%, respectively. The distribution of ploidy pattern was different in benign versus malignant follicular neoplasms (chi2 8.25, p = 0.016), malignant lesions showing an increased frequency of heteroclonal aneuploid DNA content (37.5% vs. 7.1%). Increased PI (mean +/- standard deviation (SD) = 11.3 +/- 5.7 vs. 7.1 +/- 6.1; p < 0.01) and NACV (mean +/- SD = 25.28 +/- 1.89 vs. 20.14 0.91; p < 0.01) levels were also observed in malignant follicular neoplasms. In conclusion, computer-assisted image analysis may profitably support clinical evaluation in the assessment of thyroid follicular neoplasms.