Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.

Background: The treatment success rate for tuberculosis (TB) has stagnated at 80–81% in South Korea, indicating unsatisfactory outcomes. Enhancing treatment success rate necessitates the development of individualized treatment approaches for each patient. This study aimed to identify the risk factors associated with unfavorable treatment outcomes to facilitate tailored TB care. Methods: We retrospectively analyzed the data of patients with active TB between January 2019 and December 2020 at a single tertiary referral center. We classified unfavorable treatment outcomes according to the 2021 World Health Organization guidelines as follows:“lost to follow-up” (LTFU), “not evaluated” (NE), “death,” and “treatment failure” (TF).Moreover, we analyzed risk factors for each unfavorable outcome using Cox proportional hazard regression analysis. Results: A total of 659 patients (median age 62 years; male 54.3%) were included in the study.The total unfavorable outcomes were 28.1%: 4.6% LTFU, 9.6% NE, 9.1% deaths, and 4.9% TF. Multivariate analysis showed that a culture-confirmed diagnosis of TB was associated with a lower risk of LTFU (adjusted hazard ratio [aHR], 0.25; 95% confidence interval [CI], 0.10–0.63), whereas the occurrence of adverse drug reactions (ADRs) significantly increased the risk of LTFU (aHR, 6.63; 95% CI, 2.63–16.69). Patients living far from the hospital (aHR, 4.47; 95% CI, 2.50–7.97) and those with chronic kidney disease (aHR, 3.21; 95% CI, 1.33–7.75) were at higher risk of being transferred out to other health institutions (NE). Higher mortality was associated with older age (aHR, 1.06; 95% CI, 1.04–1.09) and comorbidities. The ADRs that occurred during TB treatment were a risk factor for TF (aHR, 6.88; 95% CI, 2.24–21.13). Conclusion Unfavorable outcomes of patients with TB were substantial at a tertiary referral center, and the risk factors for each unfavorable outcome varied. To improve treatment outcomes, close monitoring and the provision of tailored care for patients with TB are necessary.

Background: Coinfections with multiple nontuberculous mycobacterial (NTM) species have not been widely studied. We aimed to evaluate the clinical characteristics and treatment outcomes in patients with NTM-pulmonary disease (PD) caused by coinfection with multiple NTM species. Methods: We retrospectively reviewed patients with NTM-PD at a tertiary referral hospital in Korea between March 2012 and December 2018. Coinfection was defined as two or more species of NTM pathogens isolated from the same respiratory specimen or different specimens within three months. Results: Among 1,009 patients with NTM-PD, 147 (14.6%) NTM coinfections were observed (average age 64.7 years, 69.4% women). NTM species were identified more frequently (median 6 vs. 3 times, P < 0.001) in the coinfection group than in the single species group, and follow-up duration was also longer in the coinfection group (median 44.9 vs. 27.1 months, P < 0.001). Mycobacterium avium complex (MAC) and M. abscessus and M. massiliense (MAB) were the dominant combinations (n = 71, 48.3%). For patients treated for over six months in the MAC plus MAB group (n = 31), sputum culture conversion and microbiological cure were achieved in 67.7% and 41.9% of patients, respectively. We divided the MAC plus MAB coinfection group into three subgroups according to the target mycobacteria; however, no statistical differences were found in the treatment outcomes. Conclusion In NTM-PD cases, a significant number of multiple NTM species coinfections occurred. Proper identification of all cultured NTM species through follow-up is necessary to detect multispecies coinfections. Further research is needed to understand the nature of NTM-PD in such cases.

Nodular fasciitis (NF) is a benign myofibroblastic proliferation that grows very rapidly, mimicking a sarcoma on imaging. It is treated by local excision, and recurrence has been reported in only a few cases, even when excised incompletely. The most prevalent diagnoses of temporomandibular joint (TMJ) masses include synovial chondromatosis, pigmented villonodular synovitis, and sarcomas. Cases of NF in the TMJ are extremely rare, and only 3 cases have been reported to date. Due to its destructive features and rarity, NF has often been misdiagnosed as a more aggressive lesion, which could expose patients to unnecessary and invasive treatment approaches beyond repair. This report presents a case of NF in the TMJ, focusing on various imaging features, along with a literature review aiming to determine the hallmark features of NF in the TMJ and highlight the diagnostic challenges.

Fibrodysplasia ossificans progressiva is a rare hereditary disorder characterized by progressive heterotopic ossifica-tion in muscle and connective tissue, with few reported cases affecting the head and neck region. Although plain radiographic findings and computed tomography features have been well documented, limited reports exist onmagnetic resonance findings. This report presents 2 cases of fibrodysplasia ossificans progressiva, one with limited mouth opening due to heterotopic ossification of the lateral pterygoid muscle and the other with restricted neck movement due to heterotopic ossification of the platysma muscle. Clinical findings of restricted mouth opening or limited neck movement, along with radiological findings of associated heterotopic ossification, should prompt consideration of fibrodysplasia ossificans progressiva in the differential diagnosis. Dentists should be particularly vigilant with patients diagnosed with fibrodysplasia ossificans progressiva to avoid exposure to diagnostic biopsy andinvasive dental procedures.

Mucormycosis is a rare, invasive fungal infection that progresses aggressively and requires prompt surgery and appropriate treatment. The number of cases of mucormycosis in coronavirus disease 2019 (COVID-19) patients has recently increased, and patients with uncontrolled diabetes mellitus are particularly at an elevated risk of infection. This report presents a case of mucormycosis-related osteomyelitis of the maxilla in a 37-year-old man with diabetes mellitus. The patient complained of severe and persistent pain in the right maxilla, accompanied by increased tooth mobility and headache. On contrast-enhanced computed tomographic images, gas-forming osteomyelitis of the right maxilla was observed. Destruction of the maxilla and palatine bone then proceeded aggressively. Sequestrectomy was performed on the right maxilla, and the histopathological diagnosis was mucormycosis. Further investigation after the first operation revealed the patient's history of COVID-19 infection.

Purpose: Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising artificial intelligence methods in the field of medical and dental research. CNNs can provide an effective diagnostic methodology allowing for the detection of early-staged diseases. Therefore, this study aimed to evaluate the performance of a deep CNN algorithm for apical lesion segmentation from panoramic radiographs. Materials and Methods: A total of 1000 panoramic images showing apical lesions were separated into training (n=800, 80%), validation (n=100, 10%), and test (n=100, 10%) datasets. The performance of identifying apical lesions was evaluated by calculating the precision, recall, and F1-score. Results: In the test group of 180 apical lesions, 147 lesions were segmented from panoramic radiographs with an intersection over union (IoU) threshold of 0.3. The F1-score values, as a measure of performance, were 0.828, 0.815, and 0.742, respectively, with IoU thresholds of 0.3, 0.4, and 0.5. Conclusion This study showed the potential utility of a deep learning-guided approach for the segmentation of apical lesions. The deep CNN algorithm using U-Net demonstrated considerably high performance in detecting apical lesions.

Purpose: We aimed to determine the relationship between environmental exposure and nontuberculous mycobacterial pulmonary disease (NTM-PD) in Korea. Materials and Methods: A group of 150 patients with NTM-PD and a control group of 217 patients with other respiratory diseases were prospectively enrolled between June 2018 and December 2020 in Seoul, Korea. They were surveyed with a standardized questionnaire, and their medical records were reviewed. Odds ratio (OR) and 95% confidence intervals (CI) were calculated with multivariate logistic regression analysis. Results: The mean ages of the NTM-PD and control groups were similar (63.8±9.2 years vs. 63.5±10.0 years; p=0.737), and most patients were female (76.0% vs. 68.7%; p=0.157) and nonsmokers (82.0% vs. 72.8%; p=0.021). Mycobacterium avium (49.3%) was the most commonly identified strain among NTM-PD patients, followed by M. intracellulare (32.0%) and M. abscessus subspecies massiliense (12.7%). There were no differences in housing type or frequency of soil- or pet-related exposure between the case and the control groups. However, in subgroup analysis excluding patients with M. intracellulare infection, more case patients frequently visited public baths ≥1 time/week (35.3% vs. 19.4%, p=0.003); this remained significant after multivariate analysis (OR, 2.84; 95% CI, 1.58–5.17). Conclusion Frequent exposure to water at public baths might affect the odds of contracting NTM-PD, excluding individuals infected with M. intracellulare strains.