Objective:To evaluate the diagnostic accuracy of the convolutional neural network（CNN） in diagnosing nasopharyngeal carcinoma using endoscopic narrowband imaging. Methods:A total of 834 cases with nasopharyngeal lesions were collected from the People's Hospital of Guangxi Zhuang Autonomous Region between 2014 and 2016. We trained the DenseNet201 model to classify the endoscopic images, evaluated its performance using the test dataset, and compared the results with those of two independent endoscopic experts. Results:The area under the ROC curve of the CNN in diagnosing nasopharyngeal carcinoma was 0.98. The sensitivity and specificity of the CNN were 91.90% and 94.69%, respectively. The sensitivity of the two expert-based assessment was 92.08% and 91.06%, respectively, and the specificity was 95.58% and 92.79%, respectively. There was no significant difference between the diagnostic accuracy of CNN and the expert-based assessment （P=0.282, P=0.085）. Moreover, there was no significant difference in the accuracy in discriminating early-stage and late-stage nasopharyngeal carcinoma（P=0.382）. The CNN model could rapidly distinguish nasopharyngeal carcinoma from benign lesions, with an image recognition time of 0.1 s/piece. Conclusion:The CNN model can quickly distinguish nasopharyngeal carcinoma from benign nasopharyngeal lesions, which can aid endoscopists in diagnosing nasopharyngeal lesions and reduce the rate of nasopharyngeal biopsy.
Humans ; Nasopharyngeal Carcinoma ; Narrow Band Imaging ; China ; Neural Networks, Computer ; Nasopharyngeal Neoplasms/diagnostic imaging*

Carcinoma ; diagnostic imaging ; Fluorodeoxyglucose F18 ; Humans ; Nasopharyngeal Neoplasms ; diagnostic imaging ; Positron-Emission Tomography

Carcinoma ; diagnostic imaging ; secondary ; Humans ; Male ; Middle Aged ; Nasopharyngeal Neoplasms ; pathology ; Pancreatic Neoplasms ; diagnostic imaging ; secondary ; Ultrasonography

The parapharyngeal space (PPS) is an inverted pyramid-shaped deep space in the head and neck region, and a variety of tumors, such as salivary gland tumors, neurogenic tumors, nasopharyngeal carcinomas with parapharyngeal invasion, and lymphomas, can be found in this space. The differential diagnosis of PPS tumors remains challenging for radiologists. This study aimed to develop and test a modified method for locating PPS tumors on magnetic resonance (MR) images to improve preoperative differential diagnosis. The new protocol divided the PPS into three compartments: a prestyloid compartment, the carotid sheath, and the areas outside the carotid sheath. PPS tumors were located in these compartments according to the displacements of the tensor veli palatini muscle and the styloid process, with or without blood vessel separations and medial pterygoid invasion. This protocol, as well as a more conventional protocol that is based on displacements of the internal carotid artery (ICA), was used to assess MR images captured from a series of 58 PPS tumors. The consequent distributions of PPS tumor locations determined by both methods were compared. Of all 58 tumors, our new method determined that 57 could be assigned to precise PPS compartments. Nearly all (13/14; 93%) tumors that were located in the pre-styloid compartment were salivary gland tumors. All 15 tumors within the carotid sheath were neurogenic tumors. The vast majority (18/20; 90%) of trans-spatial lesions were malignancies. However, according to the ICA-based method, 28 tumors were located in the pre-styloid compartment, and 24 were located in the post-styloid compartment, leaving 6 tumors that were difficult to locate. Lesions located in both the pre-styloid and the post-styloid compartments comprised various types of tumors. Compared with the conventional ICA-based method, our new method can help radiologists to narrow the differential diagnosis of PPS tumors to specific compartments.
Carcinoma ; Diagnosis, Differential ; Humans ; Lymphoma ; diagnosis ; diagnostic imaging ; Magnetic Resonance Spectroscopy ; Nasopharyngeal Neoplasms ; diagnosis ; diagnostic imaging ; Neck ; diagnostic imaging ; Nervous System Neoplasms ; diagnosis ; diagnostic imaging ; Pharynx ; diagnostic imaging ; Radiography ; Salivary Gland Neoplasms ; diagnosis ; diagnostic imaging

Adult ; Aged ; Female ; Fluorodeoxyglucose F18 ; Humans ; Male ; Middle Aged ; Nasopharyngeal Neoplasms ; diagnosis ; diagnostic imaging ; pathology ; Neoplasm Recurrence, Local ; diagnostic imaging ; Neoplasm, Residual ; diagnostic imaging ; Positron-Emission Tomography

OBJECTIVETo investigate the value of the additional skull lateral static imaging in whole-body bone imaging (WBI) vs CT for evaluation of skull base invasion in patients with nasopharyngeal carcinoma.

METHODSA total of 405 patients with pathologically confirmed NPC underwent WBI with additional static imaging of the left and right skull as well as CT examination of the nasopharynx and skull base within one week before the radiotherapy.

RESULTSThe concordance rates between WBI and CT for positive and negative diagnosis were 29.48% and 76.05% in these cases, respectively, with the total concordance rate of 81.23%. The concordance rates between skull lateral static imaging with visual judgment and CT examination for positive and negative diagnosis were 67.95% and 74.07%, respectively, showing a total concordance rate of 87.16%. Skull lateral static imaging with semi-quantitative analysis and CT examination showed concordance rates for positive and negative diagnosis of 75.64% and 74.07%, respectively, with a total rate of 88.64%. In 27 patients with negative diagnosis by CT but a positive one in skull lateral static imaging with semi-quantitative analysis, 9 had a positive diagnosis by magnetic resonance imaging.

CONCLUSIONSSkull lateral static imaging can be of value in the diagnosis of skull base invasion in NPC patients and may serve as an effective means for screening skull base invasion in NPC.

Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Nasopharyngeal Neoplasms ; diagnostic imaging ; pathology ; Neoplasm Invasiveness ; Radionuclide Imaging ; Skull ; diagnostic imaging ; pathology ; Skull Neoplasms ; diagnostic imaging ; secondary ; Technetium Tc 99m Medronate ; Tomography, X-Ray Computed ; Whole Body Imaging ; Young Adult

OBJECTIVE: To assess the diagnostic value of 18-fluoro-2-deoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in detecting residual/recurrent nasopharyngeal carcinoma. METHOD: The literatures published between January 1990 and September 2013 were searched in PubMed, EM-BASE, EBSCO, Web of Science, CBM, CNKI, VIP and Wanfang databases. Two researchers independently selected studies, extracted data and assessed the quality of included studies according to the QUADAS tool. Summary sensitivity, specificity, diagnostic odds ratios (DOR), and receiver-operating characteristic (SROC) curves were obtained using Meta-Disc software. Subgroup analysis was also conducted. RESULT: Twenty-six studies were included in this meta-analysis, involving 1203 patients. The pooled sensitivity, specificity and DOR were 0. 92 (95% CI:0.89-0.94), 0. 87 (95% CI:0.84-0.90) and 51. 10 (95% CI:34.29-76.15), respectively. The area under the curve (AUC) and Q index estimate for PET/CT were 0. 9494 and 0. 8897, respectively. The results of subgroup analysis showed no significant differences between subgroups(P>0.05). CONCLUSION In a word, 18F-FDG PET/CT performed well for diagnosis of residual/recurrent nasopharyngeal carcinoma, with relatively high sensitivity and specificity.
Carcinoma ; Fluorodeoxyglucose F18 ; Humans ; Nasopharyngeal Carcinoma ; Nasopharyngeal Neoplasms ; diagnostic imaging ; Positron-Emission Tomography ; ROC Curve ; Radiopharmaceuticals ; Recurrence ; Sensitivity and Specificity ; Tomography, X-Ray Computed

OBJECTIVETo investigate the prevalent area where the nasopharyngeal carcinoma (NPC) initially would develop most frequently in the nasopharynx.

METHODSFrom March, 1994 to June, 2003, the data of original micro-focus of 32 pathologically confirmed NPC were retrospectively reviewed, All cases were shown by CT to have stages T(0) or T(1) lesions.

RESULTSOn clinical examination, only 3 cases (9.4%) were found to have original micro-tumor in the recess, the other 29 cases (90.6%) had developed from the other regions including 20 (69.0%) from the roof and 9 cases (31.0%) from the posterior wall, all with the mucosa in the recess smooth and symmetrical. However, CT images showed that membrane of all the nasopharyngeal walls, including the recess, were normal in 24 cases (75.0%); except the micro-foci were observed on one side of the posterior wall in 5 cases (15.6%) but still with the recess normal, One lateral wall and/or the recess were involved with abnormal appearance in 3 cases (9.4%) who were clinically found to have NPC focus originated from the recess.

CONCLUSIONOur data suggest that the roof of nasopharyngeal cavity may be the area likely to develop the original NPC micro-focus, followed in frequency by the posterior wall, with the recess the least likely. The recess involvement observed in advanced lesions may be the extension of the NPC focus from the original site on the roof or the posterior wall of nasopharynx.

Adult ; Female ; Humans ; Male ; Middle Aged ; Nasopharyngeal Neoplasms ; diagnostic imaging ; pathology ; Nasopharynx ; diagnostic imaging ; pathology ; Retrospective Studies ; Tomography, X-Ray Computed

OBJECTIVETo investigate the diagnostic value of F-18-fluoro-deoxyglucose positron emission tomography (FDG-PET) for the recurrent or residual nasopharyngeal carcinomas in the skull base area.

METHODSNine post-irradiation nasopharyngeal carcinoma patients did FDG-PET scanning, CT/MRI imaging and underwent nasopharynx and skull base-biopsy under endoscopy. The results of FDG-PET were evaluated and compared with CT/MRI studies and biopsies.

RESULTSIn 9 cases of post-irradiation nasopharyngeal carcinoma, CT/MRI detected 7 recurrent cases and 2 suspected recurrent cases in occipital bone and clivus. All 9 cases had accumulated FDG in nasopharynx and cranial base. A definite diagnosis was made by biopsy, 3 cases were confirmed recurrence, and others 6 cases were proved mucous chronic inflammation and (or) osteoradionecrosis. The accuracy of FDG-PET was 33.3% (3/9), and the false positive rate was 66.7% (6/9).

CONCLUSIONSDiagnosis of recurrent or residual nasopharyngeal carcinomas in the skull base area with FDG-PET had high false-positive rate, final diagnosis must depend on histopathologic examination under endoscopy.

Adult ; Aged ; False Positive Reactions ; Female ; Fluorodeoxyglucose F18 ; Humans ; Male ; Middle Aged ; Nasopharyngeal Neoplasms ; diagnostic imaging ; drug therapy ; radiotherapy ; Positron-Emission Tomography ; methods ; Skull Base ; diagnostic imaging

OBJECTIVE: To study the clinical value of ultrasonography in diagnosing nasopharyngeal carcinoma. METHOD: Seventy-five patients with suspicious clinical symptoms of recurrent nasopharyngeal carcinoma were studied 0.5-3.0 years after radiotherapy. All received ultrasonography, computed tomography examination, nasendoscopy and nasopharyngeal biopsy. The diagnostic value of ultrasonography were then evaluated. RESULT: Of 75 cases, recurrent nasopharyngeal carcinomas were detected in 35 cases by ultrasonography. There were 26 cases confirmed pathologically, 9 cases false positive, 25 cases true negative and 15 cases false negative. Meanwhile, of 75 cases recurrent nasopharyngeal carcinomas were indicated in 35 cases by computed tomography. There were 27 cases confirmed pathologically, 8 cases false positive, 26 cases true negative and 14 cases false negative. There were no significant difference between the sensitivity, specificity and accuracy of ultrasonography and computed tomography in diagnosing recurrent nasopharyngeal carcinoma. CONCLUSION Either ultrasonography or computed tomography has good diagnostic values in detecting recurrent nasopharyngeal carcinoma. Furthermore, both of them can complement each other.
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Nasopharyngeal Neoplasms ; diagnostic imaging ; pathology ; Neck ; Neoplasm Recurrence, Local ; diagnostic imaging ; Sensitivity and Specificity ; Ultrasonography ; methods