Development and evaluation of digital subtraction radiography computer program

Development and validation of intraoral periapical radiography-based machine learning model for periodontal defect diagnosis

Radiographic determination of the bone level is useful in the diagnosis and determination of the severity of the periodontal disease. Various two- and three-dimensional imaging modalities offer choices for imaging pathologic processes that affect the periodontium. In recent years, innovative computer techniques, especially artificial intelligence (AI), have begun to be used in many areas of dentistry and are helping increase treatment and diagnostic performance. This study was aimed at developing a machine-learning (ML) model and assessing the extent to which it was capable of classifying periodontal defects on 2D periapical images. Eighty-seven periapical images were examined as part of this research. The existence or absence of periodontal defects in the aforementioned images were evaluated by a human observer. The evaluations were subsequently repeated using a radiomics platform. A comparison was made of all data acquired through human observation and ML techniques by SVM analysis. According to the study findings the ability of human observers and the ML model to detect periodontal defects was significantly different in comparison to the gold standard. However, ML and human observers performed similarly for the detection of periodontal defects without a significant difference. This study reveals that the prediction of periodontal defects can be achieved by combining particular radiomic features with image variables. The proposed machine leaning model can be utilized for supporting clinical practitioners and eventually substitute evaluations conducted by human observers while enhancing future levels of performance.

A New Method of Measuring the Volumetric Change of Alveolar Bone Around Dental Implants Using Computed Tomography

This study proposes a method for measuring the volumetric change of alveolar bone after dental implant surgery using computed tomography (CT). A total of 40 implants in 20 patients (15 males and 5 females) were selected. The types of implants used were group 1: 24 CMI IS-II Active implants (Neobiotech Co., Seoul, Republic of Korea) and group 2: 16 SLActive Bone Level implants (Institut Straumann AG, Basel, Switzerland). The OnDemand3D software (CyberMed, Seoul, Korea) was used for analysis. The volumetric change of the alveolar bone around an implant fixture is measured as follows: (1) Establish two cylinders: the main cylinder with the implant axis as the central axis (radius of implant + 3 mm) and the error correction cylinder (radius of implant + 1 mm). (2) The height of the cylinder extended from the top of the fixture to a 3 mm coronal portion. (3) Calculate the volumetric change of the alveolar bone (Vd) by subtracting the volume of the error correction cylinder from the main cylinder between CT images taken immediately after the implant placement and 12 months later. After a one-year installation, the volumetric change of alveolar bone, ΔV (cc) had increased in both groups (group 1: −0.011 ± 0.015 cc, group 2: −0.012 ± 0.017 cc) with statistical significance (p < 0.05), and the difference between the groups was not statistically significant (p > 0.05). This three-dimensional assessment method would be a useful clinical reference for the assessment of marginal bone change after implant surgery.

Assessment of three methods of geometric image reconstruction for digital subtraction radiography

OBJECTIVES

To evaluate three methods of geometric image reconstruction for digital subtraction radiography (DSR).

METHODS

Digital periapical radiographs were acquired of 24 teeth with the X-ray tube at 6 different geometric configurations of vertical (V) and horizontal (H) angles: V0°H0°, V0°H10°, V10°H0°, V10°H10°, V20°H0° and V20°H10°. All 144 images were registered in pairs (Group V0°H0° + 1 of the 6 groups) 3 times by using the Emago(®) (Oral Diagnostic Systems, Amsterdam, Netherlands) with manual selection and Regeemy with manual and automatic selections. After geometric reconstruction on the two software applications under different modes of selection, all images were subtracted and the standard deviation of grey values was obtained as a measure of image noise. All measurements were repeated after 15 days to evaluate the method error. Values of image noise were statistically analyzed by one-way ANOVA for differences between methods and between projection angles, followed by Tukey's test at a level of significance of 5%.

RESULTS

Significant differences were found between most of the projection angles for the three reconstruction methods. Image subtraction after manual selection-based reconstruction on Regeemy presented the lowest values of image noise, except on group V0°H0°. The groups V10°H0° and V20°H0° were not significantly different between the manual selection-based reconstruction in Regeemy and automatic selection-based reconstruction in Regeemy methods.

CONCLUSIONS

The Regeemy software on manual mode revealed better quality of geometric image reconstruction for DSR than the Regeemy on automatic mode and the Emago on manual mode, when the radiographic images were obtained at V and H angles used in the present investigation.

A retrospective study of digital subtraction technique to detect sclerotic changes in alveolar bone on intraoral radiographs of bisphosphonate-treated patients

OBJECTIVES

Several reports have suggested that sclerotic changes in cancellous bone of the jaw and thickening of the lamina dura are characteristic radiographic changes of an early silent stage of bisphosphonate (BP)-related osteonecrosis of the jaw. No quantitative evaluation has been reported to support this hypothesis. Emago(®) software (Oral Diagnostic Systems, Amsterdam, Netherlands) can perform digital subtraction on intraoral radiographs even if they were obtained by non-standardized radiography, provided the dimensional error is within a certain limit. The purpose of this study was to evaluate whether sclerotic changes of alveolar bone or thickening of lamina dura in patients using BP can be detected using the subtraction function of Emago.

METHODS

The authors selected 46 pairs of intraoral radiographs of the mandibular molar area in dental patients. All radiographs were obtained at intervals of 6 months or more. Among the 46 pairs, 7 pairs were from patients who were being treated with BP (study subjects), and 39 pairs were from patients who had not been using BP (controls). All pairs of radiographs underwent digital subtraction by Emago. The number of pixels of the sclerotic areas was counted and compared between subjects and controls.

RESULTS

The sclerotic changes were significantly distinguishable in two of the seven subjects (28.6%) using BP.

CONCLUSIONS

Digital subtraction function of Emago was able to detect sclerotic changes in alveolar bone. Therefore, it is suggested that the subtraction function of Emago is a useful tool for quantitatively detecting sclerotic changes that are observed at an early, silent stage of BP-related osteonecrosis of the jaw.

Development of a novel digital subtraction technique for detecting subtle changes in jawbone density

The objective of this paper is to develop a novel digital subtraction technique for serial intra-oral radiography, which would allow the detection of subtle variations in grey values. Digital images of the maxilla of a dried human skull and of a fresh pig mandible were acquired using intra-oral photostimulable phosphor plates (Digora FMX, Soredex, Helsinki) with an aluminium calibration stepwedge incorporated in the filmholder. Exposures were made with an X-ray tube for intra-oral radiography (Prostyle Intra, Planmeca, Helsinki). During pilot testing, parameter settings were adapted to reach an optimal contrast. Exposures were repeated within a 1-week interval to determine the test-retest reliability of the development. After in vitro and in vivo testing, the exposure technique and software development were used to evaluate its applicability in a pilot clinical case. Although parameter settings remained stable during the in vitro studies, the clinical exposures yielded non-linear digital images, thus, not readily suitable for data acquisition and comparison of the regions of interest. To allow further analysis, image processing was carried out using self-developed software for semi-automated linearisation and optimised contrast normalisation. This processing significantly increased the precise quantisation of jawbone density and the assessment of subtle bone density changes in arbitrarily selected regions of interest of in vivo exposures. The clinical applicability of the technique is demonstrated in a pilot case. It was demonstrated that minute densitometric deviations could be detected. The present technique and image processing may allow the quantification of jawbone density.