Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs

Differentiation of radicular cysts and radicular granulomas via texture analysis of multi-slice computed tomography images

OBJECTIVES

This study aimed to establish a method for differentiating radicular cysts from granulomas via texture analysis (TA) of multi-slice computed tomography (CT) images.

METHODS

A total of 222 lesions with multi-slice computed tomography images acquired at our hospital between 2013 and 2022 that were pathologically diagnosed were included in this study. Cases of contrast-enhanced images, severe metallic artefacts, and lesions that were not sufficiently large to be analysed were excluded. The images were chronologically divided into a training group and a validation group. The radiological characteristics were determined. Subsequently, a TA was performed. Pyradiomics software was used for the TA of three-dimensionally segmented volumes extracted from 2 mm slice thickness images with a soft-tissue algorithm. Features that differed significantly between the two lesions in the training group were extracted and used to create machine-learning models. The discriminative ability of these models was evaluated in the validation group using receiver operating characteristic curve analysis.

RESULTS

A total of 131 lesions, comprising 28 radicular cysts and 103 granulomas, were analysed. Forty-three texture features that exhibited significant variations were extracted. A support vector machine and decision tree model, with areas under the curves of 0.829 and 0.803, respectively, were created. These models showed high discriminative abilities, even for the validation group, with areas under the curve of 0.727 and 0.701, respectively. Both models showed superior performance compared with that of the models based on radiographic findings.

CONCLUSION

Discriminatory models were established for the TA of radicular cysts and granulomas using CT images.

Advances in Musculoskeletal Imaging and Their Applications

Modern medical imaging systems provide ever-more information about the patient's health condition [...].

Radiomics in bone pathology of the jaws

OBJECTIVE

To define which are and how the radiomics features of jawbone pathologies are extracted for diagnosis, predicting prognosis and therapeutic response.

METHODS

A comprehensive literature search was conducted using eight databases and gray literature. Two independent observers rated these articles according to exclusion and inclusion criteria. 23 papers were included to assess the radiomics features related to jawbone pathologies. Included studies were evaluated by using JBI Critical Appraisal Checklist for Analytical Cross-Sectional Studies.

RESULTS

Agnostic features were mined from periapical, dental panoramic radiographs, cone beam CT, CT and MRI images of six different jawbone alterations. The most frequent features mined were texture-, shape- and intensity-based features. Only 13 studies described the machine learning step, and the best results were obtained with Support Vector Machine and random forest classifier. For osteoporosis diagnosis and classification, filtering, shape-based and Tamura texture features showed the best performance. For temporomandibular joint pathology, gray-level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), first-order statistics analysis and shape-based analysis showed the best results. Considering odontogenic and non-odontogenic cysts and tumors, contourlet and SPHARM features, first-order statistical features, GLRLM, GLCM had better indexes. For odontogenic cysts and granulomas, first-order statistical analysis showed better classification results.

CONCLUSIONS

GLCM was the most frequent feature, followed by first-order statistics, and GLRLM features. No study reported predicting response, prognosis or therapeutic response, but instead diseases diagnosis or classification. Although the lack of standardization in the radiomics workflow of the included studies, texture analysis showed potential to contribute to radiologists' reports, decreasing the subjectivity and leading to personalized healthcare.

Exploring the Importance of Corticalization Occurring in Alveolar Bone Surrounding a Dental Implant

Several measures describing the transformation of trabecular bone to cortical bone on the basis of analysis of intraoral radiographs are known (including bone index or corticalization index, CI). At the same time, it has been noted that after functional loading of dental implants such transformations occur in the bone directly adjacent to the fixture. Intuitively, it seems that this is a process conducive to the long-term maintenance of dental implants and certainly necessary when immediate loading is applied. The authors examined the relationship of implant design features to marginal bone loss (MBL) and the intensity of corticalization over a 10-year period of functional loading. This study is a general description of the phenomenon of peri-implant bone corticalization and an attempt to interpret this phenomenon to achieve success of implant treatment in the long term. Corticalization significantly increased over the first 5-year functional loading (CI from 200 ± 146 initially to 282 ± 182, p < 0.001) and maintained a high level (CI = 261 ± 168) in the 10-year study relative to the reference bone (149 ± 178). MBL significantly increased throughout the follow-up period—5 years: 0.83 ± 1.26 mm (p < 0.001), 10 years: 1.48 ± 2.01 mm (p < 0.001). MBL and radiographic bone structure (CI) were evaluated in relation to intraosseous implant design features and prosthetic work performed. In the scope of the study, it can be concluded that the phenomenon of peri-implant jawbone corticalization seems an unfavorable condition for the future fate of bone-anchored implants, but it requires further research to fully explain the significance of this phenomenon.

Measures of Corticalization

After the insertion of dental implants into living bone, the condition of the peri-implant bone changes with time. Implant-loading phenomena can induce bone remodeling in the form of the corticalization of the trabecular bone. The aim of this study was to see how bone index (BI) values behave in areas of bone loss (radiographically translucent non-trabecular areas) and to propose other indices specifically dedicated to detecting corticalization in living bone. Eight measures of corticalization in clinical standardized intraoral radiographs were studied: mean optical density, entropy, differential entropy, long-run emphasis moment, BI, corticalization index ver. 1 and ver. 2 (CI v.1, CI v.2) and corticalization factor (CF). The analysis was conducted on 40 cortical bone image samples, 40 cancellous bone samples and 40 soft tissue samples. It was found that each measure distinguishes corticalization significantly (p < 0.001), but only CI v.1 and CI v.2 do so selectively. CF or the inverse of BI can serve as a measure of peri-implant bone corticalization. However, better measures are CIs as they are dedicated to detecting this phenomenon and allowing clear clinical deduction.

Sensors and Pattern Recognition Methods for Security and Industrial Applications

Contemporary cyberthreats continue to evolve, powering the neverending development arms race [...].

Selection of Image Texture Analysis and Color Model in the Advanced Image Processing of Thermal Images of Horses following Exercise

Simple Summary

Detecting horse state after exercise is critical for maximizing athletic performance. The horse’s response to fatigue includes exercise termination or exercise continuation at a lower intensity, which significantly limit the results achieved in races and equestrian competition. As conventional methods of detecting and quantifying exercise effort have shown some limitations, infrared thermography was proposed as a method of contactless detection of exercise effect. The promising correlation between body surface temperature and exercise-dependent blood biomarkers has been demonstrated. As the application of conventional thermography is limited by low specificity, advanced thermal image analysis was proposed here to visualize the link between blood biomarkers and texture of thermal images. Twelve horses underwent standardized exercise tests for six consecutive days, and both thermal images and blood samples were collected before and after each test. The images were analyzed using four color models (RGB, red-green-blue; YUV, brightness-UV-components; YIQ, brightness-IQ-components; HSB, hue-saturation-brightness) and eight texture-features approaches, including 88 features in total. In contrast to conventional temperature measures, as many as twelve texture features in two color models (RGB, YIQ) were linked with blood biomarker levels as part of the horse’s response to exercise.

Abstract

As the detection of horse state after exercise is constantly developing, a link between blood biomarkers and infrared thermography (IRT) was investigated using advanced image texture analysis. The aim of the study was to determine which combinations of RGB (red-green-blue), YUI (brightness-UV-components), YIQ (brightness-IQ-components), and HSB (hue-saturation-brightness) color models, components, and texture features are related to the blood biomarkers of exercise effect. Twelve Polish warmblood horses underwent standardized exercise tests for six consecutive days. Both thermal images and blood samples were collected before and after each test. All 144 obtained IRT images were analyzed independently for 12 color components in four color models using eight texture-feature approaches, including 88 features. The similarity between blood biomarker levels and texture features was determined using linear regression models. In the horses’ thoracolumbar region, 12 texture features (nine in RGB, one in YIQ, and two in HSB) were related to blood biomarkers. Variance, sum of squares, and sum of variance in the RGB were highly repeatable between image processing protocols. The combination of two approaches of image texture (histogram statistics and gray-level co-occurrence matrix) and two color models (RGB, YIQ), should be considered in the application of digital image processing of equine IRT.

The Effect of Rider:Horse Bodyweight Ratio on the Superficial Body Temperature of Horse's Thoracolumbar Region Evaluated by Advanced Thermal Image Processing

Appropriate matching of rider-horse sizes is becoming an increasingly important issue of riding horses' care, as the human population becomes heavier. Recently, infrared thermography (IRT) was considered to be effective in differing the effect of 10.6% and 21.3% of the rider:horse bodyweight ratio, but not 10.1% and 15.3%. As IRT images contain many pixels reflecting the complexity of the body's surface, the pixel relations were assessed by image texture analysis using histogram statistics (HS), gray-level run-length matrix (GLRLM), and gray level co-occurrence matrix (GLCM) approaches. The study aimed to determine differences in texture features of thermal images under the impact of 10-12%, >12 ≤15%, >15 <18% rider:horse bodyweight ratios, respectively. Twelve horses were ridden by each of six riders assigned to light (L), moderate (M), and heavy (H) groups. Thermal images were taken pre- and post-standard exercise and underwent conventional and texture analysis. Texture analysis required image decomposition into red, green, and blue components. Among 372 returned features, 95 HS features, 48 GLRLM features, and 96 GLCH features differed dependent on exercise; whereas 29 HS features, 16 GLRLM features, and 30 GLCH features differed dependent on bodyweight ratio. Contrary to conventional thermal features, the texture heterogeneity measures, InvDefMom, SumEntrp, Entropy, DifVarnc, and DifEntrp, expressed consistent measurable differences when the red component was considered.