Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study.

BACKGROUND: Deep learning model trained on a large image dataset, can be used to detect and discriminate targets with similar but not identical appearances. The aim of this study is to evaluate the post-training performance of the CNN-based YOLOv5x algorithm in the detection of white spot lesions in post-orthodontic oral photographs using the limited data available and to make a preliminary study for fully automated models that can be clinically integrated in the future. METHODS: A total of 435 images in JPG format were uploaded into the CranioCatch labeling software and labeled white spot lesions. The labeled images were resized to 640 × 320 while maintaining their aspect ratio before model training. The labeled images were randomly divided into three groups (Training:349 images (1589 labels), Validation:43 images (181 labels), Test:43 images (215 labels)). YOLOv5x algorithm was used to perform deep learning. The segmentation performance of the tested model was visualized and analyzed using ROC analysis and a confusion matrix. True Positive (TP), False Positive (FP), and False Negative (FN) values were determined. RESULTS: Among the test group images, there were 133 TPs, 36 FPs, and 82 FNs. The model's performance metrics include precision, recall, and F1 score values of detecting white spot lesions were 0.786, 0.618, and 0.692. The AUC value obtained from the ROC analysis was 0.712. The mAP value obtained from the Precision-Recall curve graph was 0.425. CONCLUSIONS: The model's accuracy and sensitivity in detecting white spot lesions remained lower than expected for practical application, but is a promising and acceptable detection rate compared to previous study. The current study provides a preliminary insight to further improved by increasing the dataset for training, and applying modifications to the deep learning algorithm. CLINICAL REVELANCE: Deep learning systems can help clinicians to distinguish white spot lesions that may be missed during visual inspection.

A Rare Case of Persistent Left Superior Vena Cava Coexisting With Valvulopathies and Complete Heart Block.

Persistent left superior vena cava (PLSVC) is a rare congenital vascular anomaly that is often detected incidentally during cardiovascular imaging or interventions. Coexisting PLSVC with mitral regurgitation (MR), aortic stenosis (AS), aortic regurgitation (AR), and complete heart block (CHB) are exceptionally rare and have not been reported in the literature to our knowledge. We present the case of a 50-year-old male with PLSVC coexisting with severe MR, mild AS/AR, and CHB who successfully underwent permanent pacemaker (PPM) implantation and mitral valve replacement. Comprehensive diagnostic evaluation and tailored management strategies are crucial for achieving significant improvement in the patient's symptoms. The presence of PLSVC adds complexity to diagnosis and management, necessitating multidisciplinary collaboration for optimal patient care.

Cholesterol Granuloma in the Maxillary Sinus: A Rare Presentation Associated With an Odontogenic Cyst.

Cholesterol granuloma is a histopathological finding characterized by a mass of connective tissue and granulation tissue. It is primarily observed in the middle ear, mastoid process, or paranasal sinuses, with rare occurrences in the dental odontogenic region. A dentigerous cyst encloses the crown of an unerupted tooth by expanding its follicle and attaches to the neck of the tooth. Here, we report a 63-year-old female who presented to the dental clinic complaining of an ill-fitted denture. A panoramic radiograph showed a well-defined radiolucent lesion in the upper left maxillary sinus with an impacted third molar. Computed tomography revealed loss of the anterior and lateral sinus walls. The cyst was enucleated surgically. The final diagnosis was confirmed by histopathological examination, which revealed focal areas of cholesterol clefts in the cystic wall of the dentigerous cyst.

Assessing the Efficacy of Planmeca ProMax® 3D Cone-Beam CT Machine in the Detection of Root Fractures With Varied Metal Artifact Reduction Settings and Three Kilovoltage Peak Levels.

BACKGROUND: This study aims to examine the accuracy of cone-beam computed tomography (CBCT) machines in detecting root fracture when using different metal artifact reduction (MAR) settings at different kilovoltage peak (kVp) levels. METHODOLOGY: Sixty-six tooth roots were treated endodontically using a standardized technique. Of these, 33 roots were randomly selected to be fractured; the other 33 roots were intact and used as controls. The roots were placed randomly in prepared beef ribs to mimic the alveolar bone. Imaging was performed by Planmeca ProMax® 3D (Planmeca, Helsinki, Finland) using different MAR settings (no, low, mid, and high) at three different levels of kVp: 70, 80, and 90. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. RESULTS: There was a significant difference in accuracy when using different MAR settings within the group of 70 kVp. Likewise, within the group of 90 kVp. There was no significant difference between different MAR settings at 80 kVp. Using low MAR/90 kVp had significantly higher accuracy relative to other MAR settings at 90 kVp; it also had the highest values of sensitivity, specificity, and AUC in the study. Using mid and high MAR at 70 kVp or 90 kVp decreased accuracy significantly. Mid MAR/90 kVp was the least effective setting in this study. CONCLUSIONS:  Using low MAR at 90 kVp significantly increased the accuracy within the group of 90 kVp. In contrast, mid MAR and high MAR in 70 and 90 kVp, respectively, decreased accuracy significantly.

Nasopharynx evaluation in children of unilateral cleft palate patients and normal with cone beam computed tomography.

OBJECTIVE: This study aimed to examine the morphological characteristics of the nasopharynx in unilateral Cleft lip/palate (CL/P) children and non-cleft children using cone beam computed tomography (CBCT). METHODS: A retrospective study consisted of 54 patients, of which 27 patients were unilateral CL/P, remaining 27 patients have no CL/P. Eustachian tubes orifice (ET), Rosenmuller fossa (RF) depth, presence of pharyngeal bursa (PB), the distance of posterior nasal spine (PNS)-pharynx posterior wall were quantitatively evaluated. RESULTS: The main effect of the CL/P groups was found to be effective on RF depth-right (p < 0.001) and RF depth-left (p < 0.001). The interaction effect of gender and CL/P groups was not influential on measurements. The cleft-side main effect was found to be effective on RF depth-left (p < 0.001) and RF depth-right (p = 0002). There was no statistically significant relationship between CL/P groups and the presence of bursa pharyngea. CONCLUSIONS: Because it is the most common site of nasopharyngeal carcinoma (NPC), the anatomy of the nasopharynx should be well known in the early diagnosis of NPC.

Trainable WEKA (Waikato Environment for Knowledge Analysis) Segmentation Tool: Machine-Learning-Enabled Segmentation on Features of Panoramic Radiographs.

INTRODUCTION: Segmentation of dental radiographs is a comprehensive subject in oral care and diagnosis. It is the process of delineating anatomical structures to simplify the diagnostic process for oral and maxillofacial radiologists. PURPOSE: This paper will provide an in-depth analysis of the latest benchmarks in oral imaging by studying the segmentation of panoramic radiographs using Trainable WEKA (Waikato Environment for Knowledge Analysis) Segmentation (TWS). The aim of this research is to accurately automate segmentation where it can be implemented on a large scale of clients in order to simplify radiological diagnosis. METHODS AND MATERIALS: The experimentation was conducted by modifying open-source radiographs from UFBA UESC DENTAL IMAGES dataset. In order to simulate realistic conditions such as noise affecting regions of interest, panoramic radiographs were degraded and blurred with Gaussian noise. Accuracy was quantified by measuring the difference between the automated image and the dentist-annotated image using MorphoLibJ. To ensure the precision in results, automated predicted segmentations were observed by an oral maxillofacial radiologist and compared with the dentist-renditioning annotations of the panoramic radiographs (orthopantomograms). RESULTS: The TWS classifier on radiographs with an average of 32 teeth and greater (Dice value of 0.66) and an average of less than 32 teeth (F1 score of 0.59) was significant. The calculated t-value for the Jaccard index is 2.78 and the t-value for the Dice score is 2.81. The results, considering the statistical scores, were due to the independent variable. The radiographs with 32 teeth and greater had higher Intersection over Union scores and F1 scores because of less discrepancy in tooth alignment. CONCLUSIONS: Segmentation of dental radiographs can be conducted by machine learning instead of manual segmentation.

Delayed diagnosis of a primary intraosseous squamous cell carcinoma: A case report.

Primary intraosseous squamous cell carcinoma is a rare malignant central jaw tumor derived from odontogenic epithelial remnants. Predominantly, it affects mandible, although both jaw bones may be involved. This report describes a 60-year-old man who was initially misdiagnosed with a periapical infection related to the right lower wisdom tooth. After four months, the patient presented to a private dental clinic with a massive swelling at the right side of the mandible. Panoramic radiographs and advanced imaging revealed a lesion with complete erosion of the right ramus, which extended to the orbital floor. A biopsy from the mandibular angle revealed large pleomorphic atypical squamous cells, which is the primary microscopic feature of a poorly differentiated squamous cell carcinoma.

The Morphology of the Infraorbital Nerve and Foramen in the Presence of an Accessory Infraorbital Foramen.

BACKGROUND: The accessory infraorbital foramen (AIOF) is an anatomical variation associated with the infraorbital foramen (IOF) and nerve (ION). Its occurrence and neural contents have clinical implications regarding failure of loco-regional anesthesia and risk of neural damage during surgical interventions involving the maxillary region. Thus, morphologic characterization of the AIOF and neural contents as well as the spatial relationships to the IOF are potentially useful for optimizing surgical procedures. Additionally, predictive features of the AIOF based on its relationship to IOF morphology could enable the surgeon to anticipate its presence and proceed accordingly. The purpose of this study was to determine whether the presence of an AIOF and its neural contents affected the size, shape, and composition of the IOF and ION. The specific hypothesis tested was that the topography and fascicular composition of the ION and IOF differs between individuals possessing an AIOF and those lacking this anatomical variant. METHODS: Gross topographic features of the IOF (42 crania) were compared between specimens possessing (test) or lacking (control) an AIOF. Nerve fascicles of ION (60 cadaveric sides) were examined histologically and compared morphometrically between specimens presenting or lacking an AIOF. An additional sample of 30 crania was subjected to cone-beam computed tomography (CBCT) analysis to determine the course of the canal leading to the AIOF. RESULTS: The AIOF incidence was 47.6% (20 crania) and 32.1% of the sides (27 sides). A single AIOF was observed in 24 sides and double AIOF in three sides. The AIOF occurred bilaterally in 7 specimens (16.7%). The majority of AIOF (86.7%) were located superomedial to IOF. A slightly higher frequency of the AIOF was found in left side compared to the right. Using CBCT, a patient sample showed an AIOF incidence in 21 sides of 16 patients (65.6%). A single AIOF was observed in 19 sides. Only 1 double AIOF was found in the scans, whereas 3 were found in the dry skull group. The AIOF occurred bilaterally in 3 scans (10%). The majority of AIOF (90.4%) were located superomedial to the IOF based on the CBCT scans. The AIOF was consistently seen connected to the infraorbital canal and progressed superiorly and medially from the infraorbital canal to the maxillary surface. The size of the ION without an AIOF was not significantly different than the ION in the presence of an AIOF (1.45 × 10/1.32 × 10 µm, P < 0.35) based on fascicular area. However, the number of ION fascicles was greater in specimens without an AIOF compared to those showing this feature (15.15/12.71, P < 0.04) CONCLUSION:: Results indicate that the area of the ION is not affected by an AIOF, suggesting that the field of innervation of this area is not modified by its occurrence. However, the ION appears to divide more proximally into its component branches when the AIOF is present.

Radiographic Diagnosis of Fibrous Dysplasia in Maxilla.

Fibrous dysplasia is a rare bone disorder characterized by the replacement of normal bone by abnormal fibrous tissue. Here we present a 16-year-old female with a fibrous dysplasia in the maxilla and obliteration of the sinus in the same side. Cone beam computed tomography scan revealed a mixed radiopacity that extended from the alveolar crest of the right posterior teeth to the right orbital floor in the superior-inferior direction. The radiopaque areas had homogenous ground glass appearance. There is a loss of bone trabeculation, thinning of the cortical boundaries but still intact, and a loss of the lamina dura around the right posterior permanent teeth. The radiographical features of the lesion were indicative of fibrous dysplasia in the maxilla.

Osteoma Cutis and Tonsillolith: A Cone Beam Computed Tomography Study.

In this study, we report a rare case of osteoma cutis (OC) and tonsillolith, diagnosed using cone beam computed tomography. The dystrophic calcifications in the face and tonsils were incidentally found during examination of the patient's scan with no relation to the main chief complaint. The diagnosis was OC, combined with dystrophic calcification of the tonsils. It is important to mention that OC is a rare soft-tissue ossification of cutaneous tissue, typically on the face and clinically asymptomatic. It may be primary but the majority of cases are secondary. Incidental finding of OC and tonsilloliths on a two-dimensional dental radiograph does not provide sufficient information concerning the location of these calcifications. Thus, cone beam computed tomography (CBCT) provides critical information for the diagnosis of asymptomatic OC lesions not available through any other means of clinical detection.

An Immature Ten-year Long-standing Case of Ossifying Fibroma.

Ossifying fibroma is a rare benign bone neoplasm common in middle age, with definite female predominance. Here, we describe a case of an ossifying fibroma in a 36-year-old female, with a right facial deformity. The lesion had been present for almost 10 years. The panoramic image showed a multilocular appearance with scattered radiopacities. Advanced imaging revealed an expansile multilocular lesion with multiple small radiopaque foci and a few dense radiopaque masses. A histopathological examination confirmed the diagnosis. The case represents a non-aggressive form of an immature ossifying fibroma.

Radiographic Diagnosis of a Central Giant Cell Granuloma Using Advanced Imaging: Cone Beam Computed Tomography.

Central giant cell granuloma (CGCG) is a benign non-neoplastic, proliferative intraosseous lesion of the jaw with an unknown etiology often diagnosed during the first two decades of life. The true nature of this lesion is controversial and remains elusive. Here, we report a case of central giant cell granuloma, diagnosed using cone-beam computed tomography (CBCT). A 21-year-old female presented to the clinic complaining of a painless swelling involving the right side of the mandible that had started one year previously. A CBCT scan revealed a well-defined, multilocular radiolucent lesion on the right side of the mandible extending from the molar region to the ramus with wispy septations. Wispy septations and undulating borders are some of the characteristic radiographic features of a central giant cell granuloma. The patient underwent an excisional biopsy. The biopsy revealed multinucleated giant cells in a fibrous stroma confirming our radiographic diagnosis of a central giant cell lesion.

The Face ­ A Neurosensory Perspective

The face is a unique part of the body with its individual anatomical characteristics. While the dental clinician is usually focused on the oral cavity, the physical examination should involve close attention to the neurosensory status of the facial skin. Furthermore, skin sensitivity should be assessed pre- and postoperatively in conjunction with dental interventions. The face can be divided into several functional units, such as the eyes, nose, mouth/lips, and cheeks. With regard to the neurosensory supply of the skin, various innervation territories of the face can be distinguished representing the three divisions of the trigeminal nerve. In addition, cutaneous branches of the cervical plexus provide sensitivity to the lower and lateral portions of the face. The objective of the present article is to provide the dental clinician with a literature update of the neurosensory innervation of the face.

Three-dimensional myocardial scarring along myofibers after coronary ischemia-reperfusion revealed by computerized images of histological assays.

Adverse left ventricular (LV) remodeling after acute myocardial infarction is characterized by LV dilatation and development of a fibrotic scar, and is a critical factor for the prognosis of subsequent development of heart failure. Although myofiber organization is recognized as being important for preserving physiological cardiac function and structure, the anatomical features of injured myofibers during LV remodeling have not been fully defined. In a mouse model of ischemia-reperfusion (I/R) injury induced by left anterior descending coronary artery ligation, our previous histological assays demonstrated that broad fibrotic scarring extended from the initial infarct zone to the remote zone, and was clearly demarcated along midcircumferential myofibers. Additionally, no fibrosis was observed in longitudinal myofibers in the subendocardium and subepicardium. However, a histological analysis of tissue sections does not adequately indicate myofiber injury distribution throughout the entire heart. To address this, we investigated patterns of scar formation along myofibers using three-dimensional (3D) images obtained from multiple tissue sections from mouse hearts subjected to I/R injury. The fibrotic scar area observed in the 3D images was consistent with the distribution of the midcircumferential myofibers. At the apex, the scar formation tracked along the myofibers in an incomplete C-shaped ring that converged to a triangular shape toward the end. Our findings suggest that myocyte injury after transient coronary ligation extends along myofibers, rather than following the path of coronary arteries penetrating the myocardium. The injury pattern observed along myofibers after I/R injury could be used to predict prognoses for patients with myocardial infarction.