Deep learning model for analyzing the relationship between mandibular third molar and inferior alveolar nerve in panoramic radiography.

In this study, the accuracy of the positional relationship of the contact between the inferior alveolar canal and mandibular third molar was evaluated using deep learning. In contact analysis, we investigated the diagnostic performance of the presence or absence of contact between the mandibular third molar and inferior alveolar canal. We also evaluated the diagnostic performance of bone continuity diagnosed based on computed tomography as a continuity analysis. A dataset of 1279 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014-2021) was used for the validation. The deep learning models were ResNet50 and ResNet50v2, with stochastic gradient descent and sharpness-aware minimization (SAM) as optimizers. The performance metrics were accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). The results indicated that ResNet50v2 using SAM performed excellently in the contact and continuity analyses. The accuracy and AUC were 0.860 and 0.890 for the contact analyses and 0.766 and 0.843 for the continuity analyses. In the contact analysis, SAM and the deep learning model performed effectively. However, in the continuity analysis, none of the deep learning models demonstrated significant classification performance.

Effective deep learning for oral exfoliative cytology classification.

The use of sharpness aware minimization (SAM) as an optimizer that achieves high performance for convolutional neural networks (CNNs) is attracting attention in various fields of deep learning. We used deep learning to perform classification diagnosis in oral exfoliative cytology and to analyze performance, using SAM as an optimization algorithm to improve classification accuracy. The whole image of the oral exfoliation cytology slide was cut into tiles and labeled by an oral pathologist. CNN was VGG16, and stochastic gradient descent (SGD) and SAM were used as optimizers. Each was analyzed with and without a learning rate scheduler in 300 epochs. The performance metrics used were accuracy, precision, recall, specificity, F1 score, AUC, and statistical and effect size. All optimizers performed better with the rate scheduler. In particular, the SAM effect size had high accuracy (11.2) and AUC (11.0). SAM had the best performance of all models with a learning rate scheduler. (AUC = 0.9328) SAM tended to suppress overfitting compared to SGD. In oral exfoliation cytology classification, CNNs using SAM rate scheduler showed the highest classification performance. These results suggest that SAM can play an important role in primary screening of the oral cytological diagnostic environment.

Incidence and Risk of Anti-Resorptive Agent-Related Osteonecrosis of the Jaw after Tooth Extraction: A Retrospective Study.

Bone-modifying agents (BMA) such as bisphosphonates and denosumab are frequently used for the treatment of bone metastases, osteoporosis, and multiple myeloma. BMA may lead to anti-resorptive agent-related osteonecrosis of the jaw (ARONJ). This study aimed to clarify the risk factors for and probabilities of developing ARONJ after tooth extraction in patients undergoing BMA therapy. In this study, the records of 505 target sites of 302 patients undergoing BMA who presented with mandibular fractures at the Department of Oral and Maxillofacial Surgery, Kagawa Prefectural Central Hospital, from March 2014 to January 2022, were retrospectively analyzed for the onset of ARONJ after tooth extraction. The following variables were investigated as attributes: anatomy, health status, and dental treatment. The correlation coefficient was calculated for the success or failure of endodontic surgery for each variable, the odds ratio was calculated for the upper variable, and the factors related to the onset of ARONJ were identified. The incidence rate of ARONJ was found to be 3.2%. Hypoparathyroidism was an important factor associated with ARONJ development. Thus, systemic factors are more strongly related to the onset of ARONJ after tooth extraction than local factors.

The Effectiveness of Pre-Operative Screening Tests in Determining Viral Infections in Patients Undergoing Oral and Maxillofacial Surgery.

We analyzed the rate of patients with hepatitis B virus (HBV), hepatitis C virus (HCV), or human immunodeficiency virus (HIV) infection diagnosed by pre-operative screening and estimated its cost. We retrospectively analyzed patients who underwent elective surgery at our maxillofacial surgery department between April 2014 and March 2022. We compared the number of patients with each infection identified by pre-operative screening and a pre-operative questionnaire. We also compared the prevalence of infections with varying age, sex, and oral diseases, and calculated the cost of screening per positive result. The prevalence of HBV, HCV, and HIV was 0.39% (62/15,842), 0.76% (153/15,839), and 0.07% (10/12,745), respectively. The self-reported rates were as follows: HBV, 63.4% (26/41); HCV, 50.4% (62/123); HIV, 87.5% (7/8). Differences in sex were statistically significant for all infectious diseases; age significantly affected HBV and HCV rates. There was no association between the odds ratio of oral disease and viral infections. The cost per positive result was $1873.8, $905.8, and $11,895.3 for HBV, HCV, and HIV, respectively. Although self-assessment using questionnaires is partially effective, it has inadequate screening accuracy. Formulating an auxiliary diagnosis of infectious diseases with oral diseases was challenging. The cost determined was useful for hepatitis, but not HIV.

Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning?

Attention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification using convolutional neural networks (CNNs). The data consisted of 10191 dental implant images from 13 implant brands that cropped the site, including dental implants as pretreatment, from digital panoramic radiographs of patients who underwent surgery at Kagawa Prefectural Central Hospital between 2005 and 2021. ResNet 18, 50, and 152 were evaluated as CNN models that were compared with and without the ABN. We used accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve as performance metrics. We also performed statistical and effect size evaluations of the 30-time performance metrics of the simple CNNs and the ABN model. ResNet18 with ABN significantly improved the dental implant classification performance for all the performance metrics. Effect sizes were equivalent to "Huge" for all performance metrics. In contrast, the classification performance of ResNet50 and 152 deteriorated by adding the attention mechanism. ResNet18 showed considerably high compatibility with the ABN model in dental implant classification (AUC = 0.9993) despite the small number of parameters. The limitation of this study is that only ResNet was verified as a CNN; further studies are required for other CNN models.

Prognostic Factors in Endodontic Surgery Using an Endoscope: A 1 Year Retrospective Cohort Study.

This retrospective study clarified the success rate of endoscopic endodontic surgeries and identified predictors accounting for successful surgeries. In this retrospective study, 242 patients (90 males, 152 females) who underwent endoscopic endodontic surgery at a single general hospital and were diagnosed through follow-up one year later were included. Risk factors were categorized into attributes, general health, anatomy, and surgery. Then, the correlation coefficient was calculated for the success or failure of endodontic surgery for each variable, the odds ratio was calculated for the upper variable, and factors related to the surgical prognosis factor were identified. The success rate of endodontic surgery was 95.3%, showing that it was a highly predictable treatment. The top three correlation coefficients were post, age, and perilesional sclerotic signs. Among them, the presence of posts was the highest, compared with the odds ratio, which was 9.592. This retrospective study revealed the success rate and risk factors accounting for endoscopic endodontic surgeries. Among the selected clinical variables, the presence of posts was the most decisive risk factor determining the success of endodontic surgeries.

Identification of osteoporosis using ensemble deep learning model with panoramic radiographs and clinical covariates.

Osteoporosis is becoming a global health issue due to increased life expectancy. However, it is difficult to detect in its early stages owing to a lack of discernible symptoms. Hence, screening for osteoporosis with widely used dental panoramic radiographs would be very cost-effective and useful. In this study, we investigate the use of deep learning to classify osteoporosis from dental panoramic radiographs. In addition, the effect of adding clinical covariate data to the radiographic images on the identification performance was assessed. For objective labeling, a dataset containing 778 images was collected from patients who underwent both skeletal-bone-mineral density measurement and dental panoramic radiography at a single general hospital between 2014 and 2020. Osteoporosis was assessed from the dental panoramic radiographs using convolutional neural network (CNN) models, including EfficientNet-b0, -b3, and -b7 and ResNet-18, -50, and -152. An ensemble model was also constructed with clinical covariates added to each CNN. The ensemble model exhibited improved performance on all metrics for all CNNs, especially accuracy and AUC. The results show that deep learning using CNN can accurately classify osteoporosis from dental panoramic radiographs. Furthermore, it was shown that the accuracy can be improved using an ensemble model with patient covariates.

Subcutaneous Emphysema Related to Dental Treatment: A Case Series.

Cervicofacial subcutaneous emphysema (SE) is primarily caused by dental treatment introducing gas into the subcutaneous tissue. Air rapidly dissects into the subcutaneous tissue with face and neck swelling, leading to respiratory distress, patient discomfort, and chest pain. Computed tomography (CT) can detect spreading SE patterns. However, the true volume of SE and the degree of air changes in the body over time remain unknown. We evaluated the healing process of SE and the temporal changes in the volume of emphysema in three cases detected using our hospital's electronic health record systems based on inclusion and exclusion criteria over the past 10 years, with CT and three-dimensional (3D) images. The first case was a 46-year-old woman who presented with complaints of swelling from her right eyelid to the neck and clavicles, pain on swallowing, respiratory distress, and hoarseness. The second case was a 35-year-old man who presented with complaints of swelling over the face. The third case was a 36-year-old man who presented with complaints of swelling from the left cheek to the neck. CT revealed SE and pneumomediastinum in all cases. All the patients were administered an antibacterial drug. The CT and 3D images showed an improvement in emphysema 3 days after the onset, with more than half of the volume reduction in emphysema. This made it possible to evaluate the changes in the air content of SE. Observation with CT until the healing process of SE is completed is crucial, and 3D images also help evaluate changes over time.

Evaluation of multi-task learning in deep learning-based positioning classification of mandibular third molars.

Pell and Gregory, and Winter's classifications are frequently implemented to classify the mandibular third molars and are crucial for safe tooth extraction. This study aimed to evaluate the classification accuracy of convolutional neural network (CNN) deep learning models using cropped panoramic radiographs based on these classifications. We compared the diagnostic accuracy of single-task and multi-task learning after labeling 1330 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014-2021). The mandibular third molar classifications were analyzed using a VGG 16 model of a CNN. We statistically evaluated performance metrics [accuracy, precision, recall, F1 score, and area under the curve (AUC)] for each prediction. We found that single-task learning was superior to multi-task learning (all p < 0.05) for all metrics, with large effect sizes and low p-values. Recall and F1 scores for position classification showed medium effect sizes in single and multi-task learning. To our knowledge, this is the first deep learning study to examine single-task and multi-task learning for the classification of mandibular third molars. Our results demonstrated the efficacy of implementing Pell and Gregory, and Winter's classifications for specific respective tasks.

Endoscopic-assisted resection of pleomorphic adenoma in the accessory parotid gland.

Background : An accessory parotid gland (APG) is a common anatomical structure that occurs in 10%-56% of individuals. Pleomorphic adenomas are the most common benign tumors of the APG, and their ideal treatment is surgical excision, although there is a risk for aesthetic disorders and facial nerve damage due to the site of origin. Moreover, despite being benign, these tumors are known to recur. Therefore, it is necessary to achieve both reliable excision and avoidance of facial nerve damage. Case presentation : We report a case of a 49-year-old Japanese man with a mass in his left cheek. The lesion was diagnosed as a benign salivary gland tumor derived from the APG by computed tomography imaging, magnetic resonance imaging and fine needle aspiration cytology. We resected the tumor using modified high submandibular incision under the endoscopic-assisted field of view. Discussion and Conclusions : The tumor was less invasive and reliably resected using an endoscope. In surgical treatment, the endoscopic-assisted technique is very useful to achieve complete tumor resection and prevent relapse while avoiding serious complications due to surgical procedures. J. Med. Invest. 68 : 376-380, August, 2021.

Feasibility of Navigation-Assisted Bone Lid Surgery for Deeply Impacted Maxillary Tooth - A Case Report.

RATIONALE: Bone lid surgery (BLS) is minimally invasive surgery that removes the cortical bone and returns it to original position after removing lesions. However, jawbone lesions are completely covered with cortical bone, and it can be difficult to accurately determine the lesion position from the outside. PATIENT CONCERNS: A 24-year-old Japanese woman, identified as having an impacted maxillary canine, was referred to our department. Periapical radiolucent lesion, with lateral incisor root absorption by canine compression, was confirmed. DIAGNOSIS: The diagnosis was incisor root absorption due to an impacted canine. TREATMENT: As a potential solution, we performed navigation-assisted BLS. OUTCOMES: Using navigation, we could confirm the state of impacted tooth under the covered bone. We could establish reliable bone cutting and the removed cortical bone was successfully returned to the presurgical position. TAKE-AWAY LESSONS: Navigation-assisted BLS for the removal of impacted teeth may increase surgical accuracy and minimize invasion.

Relationship between Oral Bacterial Count and Postoperative Complications among Patients with Cardiovascular Disease Treated by Surgery: A Retrospective Cohort Study.

In this retrospective observational study, we evaluated the relationship between perioperative oral bacterial counts and postoperative complications in cardiovascular disease (CVD) patients. From April 2012 to December 2018, all patients scheduled for surgery received perioperative oral management (POM) by oral specialists at a single center. Tongue dorsum bacterial counts were measured on the pre-hospitalization day, preoperatively, and postoperatively. Background data were collected retrospectively. Among the 470 consecutive patients, the postoperative complication incidence rate was 10.4% (pericardial fluid storage, n = 21; postoperative pneumonia, n = 13; surgical site infection, n = 9; mediastinitis, n = 2; and seroma, postoperative infective endocarditis, lung torsion, and pericardial effusion, n = 1 each). Oral bacterial counts were significantly higher in the pre-hospitalization than in the pre- and postoperative samples (p < 0.05). Sex, cerebrovascular disease, and operation time differed significantly between complications and no-complications groups (p < 0.05). Multivariate analysis with propensity score adjustment showed a significant association between postoperative oral bacterial count and postoperative complications (odds ratio 1.26; 95% confidence interval, 1.00-1.60; p = 0.05). Since the development of cardiovascular complications is a multifactorial process, the present study cannot show that POM reduces complications but indicates POM may prevent complications in CVD patients.

Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis.

Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the image-only models. This study aimed to statistically evaluate the osteoporosis identification ability of deep learning by combining hip radiographs with patient variables. Materials andMethods: We collected a dataset containing 1699 images from patients who underwent skeletal-bone-mineral density measurements and hip radiography at a general hospital from 2014 to 2021. Osteoporosis was assessed from hip radiographs using convolutional neural network (CNN) models (ResNet18, 34, 50, 101, and 152). We also investigated ensemble models with patient clinical variables added to each CNN. Accuracy, precision, recall, specificity, F1 score, and area under the curve (AUC) were calculated as performance metrics. Furthermore, we statistically compared the accuracy of the image-only model with that of an ensemble model that included images plus patient factors, including effect size for each performance metric. Results: All metrics were improved in the ResNet34 ensemble model compared with the image-only model. The AUC score in the ensemble model was significantly improved compared with the image-only model (difference 0.004; 95% CI 0.002-0.0007; p = 0.0004, effect size: 0.871). Conclusions: This study revealed the additional effect of patient variables in identification of osteoporosis using deep CNNs with hip radiographs. Our results provided evidence that the patient variables had additive synergistic effects on the image in osteoporosis identification.

Biological Effects of Bioresorbable Materials in Alveolar Ridge Augmentation: Comparison of Early and Slow Resorbing Osteosynthesis Materials.

The purpose of this study was to investigate the bone healing properties and histological environment of a u-HA/PLLA/PGA (u-HA-uncalcined and unsintered hydroxyapatite, PLLA-Poly L-lactic acid, PGA-polyglycolic acid) composite device in humans, and to understand the histological dynamics of using this device for maxillofacial treatments. Twenty-one subjects underwent pre-implant maxillary alveolar ridge augmentation with mandibular cortical bone blocks using u-HA/PLLA or u-HA/PLLA/PGA screws for fixation. Six months later, specimens of these screws and their adjacent tissue were retrieved. A histological and immunohistochemical evaluation of these samples was performed using collagen 1a, ALP (alkaline phosphatase), and osteocalcin. We observed that alveolar bone augmentation was successful for all of the subjects. Upon histological evaluation, the u-HA/PLLA screws had merged with the bone components, and the bone was directly connected to the biomaterial. In contrast, direct bone connection was not observed for the u-HA/PLLA/PGA screw. Immunohistological findings showed that in the u-HA/PLLA group, collagen 1a was positive for fibers that penetrated vertically into the bone. Alkaline phosphatase was positive only in the u-HA/PLLA stroma, and the stroma was negative for osteocalcin. In this study, u-HA/PLLA showed a greater bioactive bone conductivity than u-HA/PLLA/PGA and a higher biocompatibility for direct bone attachment. Furthermore, u-HA/PLLA was shown to have the potential for bone formation in the stroma.

Multi-Task Deep Learning Model for Classification of Dental Implant Brand and Treatment Stage Using Dental Panoramic Radiograph Images.

It is necessary to accurately identify dental implant brands and the stage of treatment to ensure efficient care. Thus, the purpose of this study was to use multi-task deep learning to investigate a classifier that categorizes implant brands and treatment stages from dental panoramic radiographic images. For objective labeling, 9767 dental implant images of 12 implant brands and treatment stages were obtained from the digital panoramic radiographs of patients who underwent procedures at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2020. Five deep convolutional neural network (CNN) models (ResNet18, 34, 50, 101 and 152) were evaluated. The accuracy, precision, recall, specificity, F1 score, and area under the curve score were calculated for each CNN. We also compared the multi-task and single-task accuracies of brand classification and implant treatment stage classification. Our analysis revealed that the larger the number of parameters and the deeper the network, the better the performance for both classifications. Multi-tasking significantly improved brand classification on all performance indicators, except recall, and significantly improved all metrics in treatment phase classification. Using CNNs conferred high validity in the classification of dental implant brands and treatment stages. Furthermore, multi-task learning facilitated analysis accuracy.

Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates.

This study considers the use of deep learning to diagnose osteoporosis from hip radiographs, and whether adding clinical data improves diagnostic performance over the image mode alone. For objective labeling, we collected a dataset containing 1131 images from patients who underwent both skeletal bone mineral density measurement and hip radiography at a single general hospital between 2014 and 2019. Osteoporosis was assessed from the hip radiographs using five convolutional neural network (CNN) models. We also investigated ensemble models with clinical covariates added to each CNN. The accuracy, precision, recall, specificity, negative predictive value (npv), F1 score, and area under the curve (AUC) score were calculated for each network. In the evaluation of the five CNN models using only hip radiographs, GoogleNet and EfficientNet b3 exhibited the best accuracy, precision, and specificity. Among the five ensemble models, EfficientNet b3 exhibited the best accuracy, recall, npv, F1 score, and AUC score when patient variables were included. The CNN models diagnosed osteoporosis from hip radiographs with high accuracy, and their performance improved further with the addition of clinical covariates from patient records.

Relationship between oral condition and risk factors for jaw osteonecrosis in patients with hip fractures.

Purpose : Antiresorptive agents, such as bisphosphonates, are useful for the prevention of the recurrence of hip fractures. However, their administration has a risk of antiresorptive agent-related osteonecrosis of the jaw (ARONJ), and risk factors include poor oral hygiene. It is difficult for an orthopedic surgeon to examine a patient's oral condition thoroughly. This study evaluated the relationship between risk factors for ARONJ and intraoral findings in hip fracture patients. Materials and Methods : We evaluated 79 patients (average age of 82.2 years) with hip fracture surgery who underwent an oral assessment by dentists. The risk assessments of the intraoral findings were classified into four levels (levels 0-3), with levels 2 and 3 requiring dental treatment intervention. Data that could be extracted as risk factors of ARONJ were also examined. Results : Level 1 was found most frequently (54.4%), followed by level 0 (35.4%), level 2 (8.9%), level 3 (1.3%). The area under the receiver operating characteristic curve for the number of risk factors for the two groups (dental treatment intervention required and unnecessary) and oral findings were 0.732. When the cut-off value was set to two risk factors, the specificity and sensitivity was 53.5% and 87.5%. Conclusions : For hip fracture patients with a more than 2 risk factors, dental visits are recommended to prevent ARONJ. This is a useful evaluation method that can be used to screen for ONJ from data obtained from other risk factors, even if it is difficult to evaluate the oral condition in hospitals where dentists are absent. J. Med. Invest. 67 : 328-331, August, 2020.

Clinical retrospective study of dental implant removal: do patients who require implant removal desire implant prosthesis again?

BACKGROUND: This study investigated the causes of dental implant removal due to complications, and examined whether patients who had dental implant removal desired re-implant prosthesis treatments. MATERIAL AND METHODS: A retrospective case–control study was conducted on patients who had their dental implants removed. We investigated whether the removed dental implant was replaced with other implant prostheses. Age, sex, diabetes, smoking, implant site distribution, reason for implant removal, and blade and root-form implants were categorized as predictive variables. The outcome variable was desire for re-implantation or use of other prosthetic methods after implant removal. A logistic regression model was created to identify patient factors that could predict the re-implantation of dental prostheses after implant removal. RESULTS: A total of 215 dental implants were removed from 143 patients. The most common reason for implant removal was peri-implantitis that was identified in 165 implants. After implant removal, re-implantation was per-formed in 98 implants (45.6%). Bivariate analyses showed that age, diabetes, implant type, and reason for implant removal were associated with the desire for re-implanted prostheses. The multiple regression model revealed that age, implant type, and reason for implant removal were associated with an increased desire for re-implant pros-theses after implant removal. CONCLUSIONS: Re-implantation of prostheses after the removal of dental implants was desired by patients who were younger, had implants placed in the root form, and had implants removed due to prosthetic-related complications

No disponible

Relationship between Oral Health Status and Postoperative Fever among Patients with Lung Cancer Treated by Surgery: A Retrospective Cohort Study.

A retrospective observational study using an oral bacteria counter was conducted to evaluate the trends in the number of oral bacteria in the perioperative period of lung cancer patients and to verify the relationship between oral health status and postoperative fever. All patients received perioperative oral management (POM) by oral specialists between April 2012 and December 2018 at Kagawa Prefectural Central Hospital, Kagawa, Japan prior to lung cancer surgery. Bacteria counts from the dorsum of the tongue were measured on the day of pre-hospitalization, pre-operation, and post-operation, and background data were also collected retrospectively. In total, 441 consecutive patients were enrolled in the study. Bonferroni's multiple comparison test showed significantly higher oral bacteria counts at pre-hospitalization compared to pre- and post-operation (p < 0.001). Logistic regression analysis showed that body mass index, performance status, number of housemates, number of teeth, and white blood cell count at pre-operation were significantly associated with postoperative fever. The study showed that POM can reduce the level of oral bacterial counts, that the risk of postoperative complications is lower with dentulous patients, and that appropriate POM is essential for prevent of complications. Therefore, POM may play an important role in perioperative management of lung cancer patients.

Clinical study on primary screening of oral cancer and precancerous lesions by oral cytology.

BACKGROUND: This study was conducted to compare the histological diagnostic accuracy of conventional oral-based cytology and liquid-based cytology (LBC) methods. METHODS: Histological diagnoses of 251 cases were classified as negative (no malignancy lesion, inflammation, or mild/moderate dysplasia) and positive [severe dysplasia/carcinoma in situ (CIS) and squamous cell carcinoma (SCC)]. Cytological diagnoses were classified as negative for intraepithelial lesion or malignancy (NILM), oral low-grade squamous intraepithelial lesion (OLSIL), oral high-grade squamous intraepithelial lesion (OHSIL), or SCC. Cytological diagnostic results were compared with histology results. RESULTS: Of NILM cytology cases, the most frequent case was negative [LBC n = 50 (90.9%), conventional n = 22 (95.7%)]. Among OLSIL cytodiagnoses, the most common was negative (LBC n = 34; 75.6%, conventional n = 14; 70.0%). Among OHSIL cytodiagnoses (LBC n = 51, conventional n = 23), SCC was the most frequent (LBC n = 31; 60.8%, conventional n = 7; 30.4%). Negative cases were common (LBC n = 13; 25.5%, conventional n = 14; 60.9%). Among SCC cytodiagnoses SCC was the most common (LBC n = 16; 88.9%, conventional n = 14; 87.5%). Regarding the diagnostic results of cytology, assuming OHSIL and SCC as cytologically positive, the LBC method/conventional method showed a sensitivity of 79.4%/76.7%, specificity of 85.1%/69.2%, false-positive rate of 14.9%/30.7%, and false-negative rate of 20.6%/23.3%. CONCLUSIONS: LBC method was superior to conventional cytodiagnosis methods. It was especially superior for OLSIL and OHSIL. Because of the false-positive and false-negative cytodiagnoses, it is necessary to make a comprehensive diagnosis considering the clinical findings.