Objective: To assess the influence of field of view (FOV) size, scanning position within the FOV and scanning mode on the detection of root fracture and artifact perception. Methods: Forty single-rooted premolars restored with NiCr and AgPd posts were divided into two groups: fractured and sound. All teeth were scanned using four CBCT scanning protocols varying FOV sizes (80 × 80 mm and 50 × 55 mm) and scanning modes (Standard and High Definition). The sample was positioned within the FOV in two pre-set positions (central and lateral) and in four positions established by the operator (quadrants). Detection of root fracture and artifact perception were assessed by two observers using 5-point and 4-point scales. Sensitivity, specificity, accuracy, and AUC values were calculated and compared by ANOVA two-way and Tukey’s test. Chi-square and Fisher’s exact test were used to assess artifact perception. The level of significance was set at p < 0.05. Results : The central position within the FOV presented higher sensitivity, specificity, accuracy, and AUC values and differed from the lateral position within the FOV for the studied metal posts (p<0.05). Quadrant 2 presented the best sensitivity, accuracy, and AUC values (p<0.05). The lateral position within the FOV, AgPd posts, quadrants 1 and 3 and protocols 1 (SM, 80 × 80) and 2 (HD, 80× 80) presented higher frequency of artifacts classified as “severe”. Conclusion: Positioning the object in the center or closer to the anterior periphery of the FOV while using a small FOV improved the detection of root fracture and decreased artifact perception.
Considering Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network approaches have shown promising image classification performance, the aim of this study was to compare the performance of novel Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) architectures with a classic CNN for classification of panoramic radiographs with inflammatory periapical lesions. A dataset of 356 panoramic radiographs with periapical lesions and 769 control images were retrospectively collected and divided into training, validation, and testing sets. Next, four different models were constructed: a classic CNN, a classic LSTM, a cascaded CNN-LSTM, and parallel CNN-LSTM architecture. In each model the CNN took the full panoramic radiograph as input while the LSTM network ran on the images divided into 6 sequential patches. Sensitivity, specificity, and Area Under the Receiver-Operating Curve (AUC) were calculated. McNemar's test compared the sensitivity and specificity between the classic CNN and the other models. Parallel CNN-LSTM had a significantly higher sensitivity than classic CNN for detecting periapical lesions (95% vs. 81%, 95% confidence interval for the difference = 6 - 22 %, P = 0.002), while also exhibiting the best overall performance of the four models [AUC = 96% vs. 90% (classic CNN), 92% (classic LSTM), and 94% (cascaded CNN-LSTM)]. The parallel CNN-LSTM architecture outperformed the classic CNN for classification of panoramic radiographs with inflammatory periapical lesions. Combining CNN and LSTM models improves the classification of panoramic radiographs with and without inflammatory periapical lesions.
Objectives: To assess the dynamic range and enhancement ability of radiographs acquired with contemporary digital systems. Methods: Five repeated periapical radiographs of human mandibles with an aluminium step-wedge were acquired using two sensor-based and three photostimulable phosphor plate-based systems and an X-ray unit at ten exposure times 0.020, 0.032, 0.063, 0.080, 0.100, 0.200, 0.320, 0.400, 0.500, and 0.630 s. All images had their brightness and contrast enhanced by two experienced oral and maxillofacial radiologists in consensus and were exported as both the original and enhanced file formats. Mean grey values were obtained from the aluminium steps and tabulated with their corresponding thicknesses for each exposure time, digital radiographic system, and file format. Images with saturated steps were excluded and the mean grey values from the remaining images were averaged to assess image brightness and the angular coefficient of the linear trendlines was generated from the relationship between mean grey values and their corresponding aluminium thicknesses to assess image contrast. Brightness and contrast values were compared using two-way ANOVA with post-hoc Tukey (α = 0.05). Results: Photostimulable phosphor plate-based digital radiographic systems had a broader dynamic range. Longer exposure times produced original images with lower brightness and variable contrast (p < 0.05). Subjective enhancement significantly increased or reduced brightness and/or contrast in some systems (p < 0.05). Conclusions: Contemporary digital radiographic systems present different dynamic ranges and exposure-related brightness and contrast. Image enhancement may be a valuable tool at slightly suboptimal exposure times.
9 August 2024 in Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
Objective: To assess the subjective image quality of original and manually enhanced radiographs acquired at different X-ray exposure times and using different digital systems. Methods: A total of 500 radiographs obtained under 10 exposure times, 5 digital systems, and 2 enhancement conditions were assessed by 5 observers, who were asked to categorize each radiograph into acceptable or unacceptable. A radiograph was considered to be acceptable when at least four out of five observers found it acceptable. Descriptive analysis was used to summarize the outcomes and compare the subjective image quality of original and manually enhanced digital radiographs among different X-ray exposure times and digital systems. Results: Express had six exposure times producing acceptable original images within a range from 0.063 to 0.4 s, followed by Digora Toto, which had five within a range from 0.063 to 0.32 s, Digora Optime, which had four within a range from 0.063 to 0.2 s,and SnapShot and VistaScan, which had 2 (0.2 and 0.32 s) and 1 (0.63 s), respectively. Image enhancement turned unacceptable images into acceptable ones in four digital systems: SnapShot at three exposure times, Digora Toto at two exposure times, Express at one exposure time, and VistaScan at four exposure times. Conclusion: Image enhancement based on brightness and/or contrast adjustments may be necessary to reveal the useful dynamic range of some digital radiographic systems and PSP-based systems may not necessarily have a wider range than sensor-based systems.
12 January 2024 in Journal of Imaging Informatics in Medicine