Search

Objectives: The aims of the present study were to construct a deep learning model for automatic segmentation of the temporomandibular joint (TMJ) disc on magnetic resonance (MR) images, and to evaluate the performances using the internal and external test data. Methods: In total, 1200 MR images of closed and open mouth positions in patients with temporomandibular disorder (TMD) were collected from two hospitals (Hospitals A and B). The training and validation data comprised 1000 images from Hospital A, which were used to create a segmentation model. The performance was evaluated using 200 images from Hospital A (internal validity test) and 200 images from Hospital B (external validity test). Results: Although the analysis of performance determined with data from Hospital B showed low recall (sensitivity), compared with the performance determined with data from Hospital A, both performances were above 80%. Precision (positive predictive value) was lower when test data from Hospital A were used for the position of anterior disc displacement. According to the intra-articular TMD classification, the proportions of accurately assigned TMJs were higher when using images from Hospital A than when using images from Hospital B. Conclusion: The segmentation deep learning model created in this study may be useful for identifying disc positions on MR images.

Objectives: We evaluated the diagnostic performance of a deep learning system for the detection of Sjögren’s syndrome (SjS) in ultrasonography (US) images, and compared it with the performance of inexperienced radiologists. Methods: 100 patients with a confirmed diagnosis of SjS according to both the Japanese criteria and American-European Consensus Group criteria and 100 non-SjS patients that had a dry mouth and suspected SjS but were definitively diagnosed as non-SjS were enrolled in this study. All the patients underwent US scans of both the parotid glands (PG) and submandibular glands (SMG). The training group consisted of 80 SjS patients and 80 non-SjS patients, whereas the test group consisted of 20 SjS patients and 20 non-SjS patients for deep learning analysis. The performance of the deep learning system for diagnosing SjS from the US images was compared with the diagnoses made by three inexperienced radiologists. Results: The accuracy, sensitivity and specificity of the deep learning system for the PG were 89.5, 90.0 and 89.0%, respectively, and those for the inexperienced radiologists were 76.7, 67.0 and 86.3%, respectively. The deep learning system results for the SMG were 84.0, 81.0 and 87.0%, respectively, and those for the inexperienced radiologists were 72.0, 78.0 and 66.0%, respectively. The AUC for the inexperienced radiologists was significantly different from that of the deep learning system. Conclusions: The deep learning system had a high diagnostic ability for SjS. This suggests that deep learning could be used for diagnostic support when interpreting US images.

Objectives: This study estimated the diagnostic performance of a deep learning system for detection of Sjögren's syndrome (SjS) on CT, and compared it with the performance of radiologists. Methods: CT images were assessed from 25 patients confirmed to have SjS based on the both Japanese criteria and American-European Consensus Group criteria and 25 control subjects with no parotid gland abnormalities who were examined for other diseases. 10 CT slices were obtained for each patient. From among the total of 500 CT images, 400 images (200 from 20 SjS patients and 200 from 20 control subjects) were employed as the training data set and 100 images (50 from 5 SjS patients and 50 from 5 control subjects) were used as the test data set. The performance of a deep learning system for diagnosing SjS from the CT images was compared with the diagnoses made by six radiologists (three experienced and three inexperienced radiologists). Results: The accuracy, sensitivity, and specificity of the deep learning system were 96.0%, 100% and 92.0%, respectively. The corresponding values of experienced radiologists were 98.3%, 99.3% and 97.3% being equivalent to the deep learning, while those of inexperienced radiologists were 83.5%, 77.9% and 89.2%. The area under the curve of inexperienced radiologists were significantly different from those of the deep learning system and the experienced radiologists. Conclusions: The deep learning system showed a high diagnostic performance for SjS, suggesting that it could possibly be used for diagnostic support when interpreting CT images.

OBJECTIVES: The distal root of the mandibular first molar occasionally has an extra root, which can directly affect the outcome of endodontic therapy. In this study, we examined the diagnostic performance of a deep learning system for classification of the root morphology of mandibular first molars on panoramic radiographs. Dental cone-beam CT (CBCT) was used as the gold standard. METHODS: CBCT images and panoramic radiographs of 760 mandibular first molars from 400 patients who had not undergone root canal treatments were analyzed. Distal roots were examined on CBCT images to determine the presence of a single or extra root. Image patches of the roots were segmented from panoramic radiographs and applied to a deep learning system, and its diagnostic performance in the classification of root morphplogy was examined. RESULTS: Extra roots were observed in 21.4% of distal roots on CBCT images. The deep learning system had diagnostic accuracy of 86.9% for the determination of whether distal roots were single or had extra roots. CONCLUSIONS: The deep learning system showed high accuracy in the differential diagnosis of a single or extra root in the distal roots of mandibular first molars.

The purpose of this study was to investigate factors associated with lymph node (LN) metastasis to identify which nasopharyngeal cancer (NPC) patients can undergo a reduction in the prophylactic radiation field. MRI of biopsy-proven NPC patients was evaluated to determine primary tumour extension and the existence of LN metastasis.Sex, age, pathological type, T stage, primary tumour size, existence beyond the midline of the nasopharynx at the primary site and parapharyngeal extension of the primary tumour were assessed regarding their impact on the laterality of LN metastasis using the χ(2) test.Of the 167 patients, 149 (89%) showed nodal involvement. The existence beyond the midline of the nasopharynx was significantly associated with the laterality of LN metastasis (p0.0001). Most patients (82%) with primary tumour presence within the midline showed only ipsilateral LN metastasis or no LN metastasis. In addition, contralateral LN metastases were seen only at Level II and the retropharyngeal LN among most of other patients.These results suggest that LN areas other than Level II and the retropharyngeal LN on the contralateral side could be omitted in patients with primary tumour presence within the midline and without the contralateral Level II or the retropharyngeal LN. Whether disease control is compromised by reducing the radiation field for subclinical diseases is a problem that should be solved in the future by prospective study.

To identify patients with nasopharyngeal cancer in whom the cervical radiation field can be reduced, we classified the growth patterns of nasopharyngeal cancer based on MRI findings into 4 types and performed an evaluation. Based on MRI findings, we classified the growth patterns of primary cancer in 94 patients with nasopharyngeal cancer into Type 1 (superficial type), Type 2 (lateral invasive type), Type 3 (upward invasive type), and Type 4 (anterior extension type), and further classified Type 2, based upon nasopharyngoscopic findings, into Type 2a (unilateral invasive type) and Type 2b (bilateral invasive type). The cervical lymph node metastasis areas were evaluated according to these types. Type 2 showed a significantly higher incidence of cervical lymph node metastasis only on the ipsilateral side than the other types (p = 0.0024). In particular, all patients with Type 2a had cervical lymph node metastasis only on the ipsilateral side (p = 0.0212). This study suggests that the distribution of metastasised cervical lymph nodes depends on the pattern of tumour extent of the primary site.

Adenoid cystic carcinoma (ACC) is known for its slow-growing but severely infiltrative nature with little tissue reaction. Although the masticatory muscles are often involved, their imaging features have not been well elucidated. We hereby report three patients with widespread ACC, which initially appeared with trismus and/or temporomandibular symptoms and involved the masticator space. Possible features of masticator space involvement are presented on magnetic resonance (MR) images. Masticatory muscle changes on MR images consisted of two aspects, namely, denervation changes and direct tumour invasion.

The purpose of this study was to clarify the CT features of odontogenic myxoma.CT appearances were analysed in 17 patients with histologically verified odontogenic myxoma collected from five dental hospitals in Japan.On the CT images, tumour borders were generally well defined with a smooth margin both for bony and soft tissue structures in all patients. Cortical status was clearly evaluated using CT and the continuity was interrupted in nine patients. Intralesional trabeculations were observed in 13 patients. Of these 13, 6 patients showed the characteristic appearance of angular or straight trabeculations within the tumour. The trabeculations were frequently observed at the peripheral portion of the tumour. In three maxillary tumours, soft tissue margins were observed beyond the cortical margin and/or intralesional trabeculations. In 10 of the 13 lesions evaluated, the majority of the whole tumour area showed relatively lower density compared with surrounding muscles.CT clearly demonstrated characteristic features of odontogenic myxoma. CT analysis may contribute to establishing a consensus regarding the interpretation of conventional radiographic appearances in odontogenic myxoma.

To clarify the diagnostic utility of CT in the evaluation of carcinoma of the maxillary gingiva and hard palate.The CT scans of 27 patients with squamous cell carcinoma of the upper gingiva and hard palate were reviewed. Tumor extent and bone destruction were compared with the surgical and histopathological findings to estimate the sensitivity, specificity and accuracy of CT.The primary tumor was detected by CT in 89% of patients. The grade of bone destruction determined by CT correlated well with that verified at surgery or by histopathological examination. The sensitivity, specificity, and accuracy of CT for invasion to the buccal mucosa were 64%, 89% and 75% respectively. For maxillary sinus invasion, CT showed low specificity but high sensitivity. The accuracy was 86% when the criterion for sinus invasion was the presence of an enhanced mass continuous with the primary tumor.CT is helpful for the evaluation of tumor extent in the upper gingiva and hard palate carcinoma. However, invasion of the maxillary sinus should be considered carefully, because CT findings suggestive of destruction of the floor of the maxillary sinus are not always consistent with sinus invasion.

Acute parotitis occasionally spreads rapidly down the neck with severe symptoms of swelling and pain. However, the inflammatory course of parotitis with extraglandular spread has seldom been described. On CT images, we have noticed a unique area just below the parotid gland that is surrounded by the platysma muscle and the superficial layer of the deep cervical fascia (DCF). In this case report, we describe the CT imaging features of acute parotitis, focusing on this area.

To ascertain the normal range of maxillary sinus size and its changes with age on computed tomography (CT) and define convenient indices for sinus size, in addition, to examine the association of the height of the sinus floor with age and status of the dentition.The transverse and anteroposterior dimensions of the normal maxillary sinuses in 107 subjects were measured on axial CT and the relationship between these values and the sinus volume analysed. The height of the sinus floor was obtained by measuring the vertical distance from the anterior nasal spine to the sinus floor.The mean transverse and anteroposterior widths of the normal adult maxillary sinuses were 2.70 (s.d., 0.60) cm and 3.56 (s.d., 0.47) cm, respectively. There was a close correlation with sinus volume which could be predicted well from the multiple regression formula. These values increased up to the age of 20 y, but then decreased. There was no significant difference between subjects aged 50-79 years with and without maxillary premolars and molars. The width of the adult sinus correlated with the interzygomatic buttress distance and body weight. The mean height of the adult maxillary sinus floor was 0.37 (s.d., 0.44) cm inferior to the anterior nasal spine. It correlated negatively with sinus volume and fell with age up to 20 y, then rose again. In adults, it was not significantly influenced by the dentition status, and rose in proportion to the decrease in the interzygomatic buttress distance, and body height and weight.The transverse and anteroposterior widths of the maxillary sinus on axial CT are convenient indices for its size. The height of the sinus floor altered with changes in sinus volume, but was not directly influenced by the status of the dentition.

It is unclear whether computer-aided detection (CAD) systems for panoramic radiography can help inexperienced dentists to diagnose maxillary sinusitis. The aim of this study was to clarify whether a CAD system for panoramic radiography can contribute to improved diagnostic performance for maxillary sinusitis by inexperienced dentists.The panoramic radiographs of 49 patients with maxillary sinusitis and 49 patients with healthy sinuses were evaluated in this study. The diagnostic performance of the CAD system was determined. 12 inexperienced dentists and 4 expert oral and maxillofacial radiologists observed the total of 98 panoramic radiographs and judged the presence or absence of maxillary sinusitis, under conditions with and without the support of the CAD system. The receiver operating characteristic curves of the two groups were compared.The CAD system provided sensitivity of 77.6%, specificity of 69.4% and accuracy of 73.5%. The diagnostic performance of the inexperienced dentists increased with the support of the CAD system. When the inexperienced dentists diagnosed maxillary sinusitis with CAD support, the area under the curve (AUC) was significantly higher than that without CAD support. When the focus was only on panoramic radiographs in which CAD support led to a correct diagnosis, the AUC of the inexperienced dentists increased to an equivalent level to that of the experienced radiologists.The CAD system supported the inexperienced dentists in diagnosing maxillary sinusitis on the panoramic radiographs. If the accuracy of the CAD system can be increased, the benefits of CAD support will be further enhanced.

Objectives Shear-wave sonoelastography is expected to facilitate low operator dependency, high reproducibility and quantitative evaluation, whereas there are few reports on available normative values of in vivo tissue in head and neck fields. The purpose of this study was to examine the reliabilities on measuring hardness using shear-wave sonoelastography and to clarify normal values of masseter muscle hardness in healthy volunteers. Methods Phantoms with known hardness ranging from 20 to 140 kPa were scanned with shear-wave sonoelastography, and inter- and intraoperator reliabilities were examined compared with strain sonoelastography. The relationships between the actual and measured hardness were analyzed. The masseter muscle hardness in 30 healthy volunteers was measured using shear-wave sonoelastography.The inter- and intraoperator intraclass correlation coefficients were almost perfect. Strong correlations were seen between the actual and measured hardness. The mean hardness of the masseter muscles in healthy volunteers was 42.82 ± 5.56 kPa at rest and 53.36 ± 8.46 kPa during jaw clenching.The hardness measured with shear-wave sonoelastography showed high-level reliability. Shear-wave sonoelastography may be suitable for evaluation of the masseter muscles.

An increased attenuation area (IAA) is sometimes seen in the cystic cavity of odontogenic keratocysts (OKCs) on CT scans. The significance of IAA was compared radiologically and histologically in 26 cysts in which a provisional diagnosis of OKC had been made. First, the presence of IAA in the cystic cavity was assessed. Then, relationship between the presence of IAA and data obtained from the cysts, including the CT and histological findings and the visual appearance of the cyst contents, was evaluated. An IAA was frequently seen in large multilocular cysts. There was no relationship between the presence of IAA and aggressive features of the cyst on CT or the cyst contents. Histologically, subepithelial inflammation was often observed in the cysts with IAA. In order to ascertain whether the IAA was due to the keratin mass, a CT scan of a bundle of hair in a water bath was performed and shown to have a similar density. Our study demonstrated that IAA in cystic cavities results from desquamated keratin. Since this seems to occur in long-standing or inflamed multilocular OKCs, it could be used as a significant finding in the diagnosis of OKC.

An understanding of the age-related changes in the volume of the normal maxillary sinus will help to identify sinus abnormalities. Normal maxillary sinus volume was measured on axial CT scans in 115 cases, and analysed in relation to age, the presence of premolar and molar teeth, size of the midfacial skeleton and body height and weight. The volume ranged from 4.56-35.21 cm3 (mean: 14.71 +/- s.d. 6.33 cm3) in patients aged over 20 years. There was no significant sex difference and a close correlation between the two sides was found. The volume increased up to the age of 20 years, but then decreased. There was no significant difference in patients with and without maxillary premolars and molars between the ages of 50 and 79 years. The difference in right and left dentitions had no influence on the maxillary sinus volume over the age of 20 years. Adult maxillary sinus volume correlated with the interzygomatic buttress distance. In adult females, there was a significant correlation between the volume and the...

To verify the use of a single coupling agent as a reference to obtain the elasticity index (EI) ratios and to investigate the EI ratios of the masseter muscles of healthy volunteers.Muscle phantoms with known elasticity (20, 40 and 60 kPa in the Young's modulus) were examined by strain-type sonoelastography using a coupling agent as the reference. Eight examiners tested soft (with 7 kPa) and hard (with 40 kpa) reference coupling agents separately. The correlation coefficients were determined between the EI ratio and Young's modulus of muscle phantoms. The interclass correlation coefficients were calculated for inter- and intraexaminer agreement.Strong correlations were found between the EI ratios and Young's modulus for both soft and hard references. The variations of the EI ratios were larger with soft coupling agents than those with hard coupling agents, and they increased in phantoms with 60 kPa elasticity. There were no differences in the EI ratios of the masseter muscle at rest between males and females or between the right and left sides. The ratio increased during clenching.The hard reference coupling agent was suitable for obtaining EI ratio of the masseter muscle. No differences were found in the EI ratios of the masseter muscle either between sexes or between the right and left sides at rest, and the ratios increased with the widening of their variations during clenching.