Extravalidation and reproducibility results of a commercial deep learning-based automatic detection algorithm for pulmonary nodules on chest radiographs at tertiary hospital.

INTRODUCTION: To extra validate and evaluate the reproducibility of a commercial deep convolutional neural network (DCNN) algorithm for pulmonary nodules on chest radiographs (CRs) and to compare its performance with radiologists. METHODS: This retrospective study enrolled 434 CRs (normal to abnormal ratio, 246:188) from 378 patients that visited a tertiary hospital. DCNN performance was compared with two radiology residents and two thoracic radiologists. Abnormality assessment (using the area under the receiver operating characteristics (AUROC)) and nodule detection (using jackknife alternative free-response ROC (JAFROC)) were compared among three groups (DCNN only, radiologist without DCNN and radiologist with DCNN). A subset of 56 paired cases, having two CRs taken within a 7-day period, were assessed for intraobserver reproducibility using the intraclass correlation coefficient. Independent characteristics of pulmonary nodules detected by DCNN were assessed by multiple logistic regression analysis. RESULTS: The AUROC for abnormality detection for the three groups were 0.87, 0.93 and 0.96, respectively (P < 0.05), whereas the JAFROC analysis of nodule detection was 0.926, 0.929 and 0.964. Reproducibility for the three groups was 0.80, 0.67 and 0.80, which shows an increase in radiologists using DCNN (P < 0.05). Nodules detected by DCNN were more solid, round-shaped and well marginated, not masked and laterally located (P < 0.05). CONCLUSIONS: Extra validation results of DCNN showed high ROC results and there was a significant improvement in the performance when radiologists used DCNN. Reproducibility by DCNN alone showed good agreement, and there was an improvement from moderate to good agreement for radiologists using DCNN.

Dehiscent high-riding jugular bulb presenting as conductive hearing loss: A case report.

RATIONALE: Jugular bulb anomalies are asymptomatic lesions commonly seen in routine practice. However, some patients with jugular bulb anomalies may present with symptoms such as tinnitus or conductive hearing loss (CHL). PATIENT CONCERNS: A 9 year old boy complained right sided hearing disturbance without any vestibular symptoms. Pure tone audiometry (PTA) revealed a mild right sided conductive hearing loss. Otoscopy showed a red-purplish mass like lesion in his right middle ear cavity, which was regarded as hypervascular tumor. DIAGNOSIS: Based on otoscopic findings, preliminary differential diagnoses included jugular bulb anomaly, hemotympanum, cholesterol granuloma and paraganglioma. INTERVENTIONS: We performed contrast enhanced computed tomography of the temporal bone (TBCT). OUTCOMES: CT scan showed and enhancing lesion which was bulging from his right jugular foramen to the middle ear with dehiscent jugular bulb. The lesion showed the same degree of contrast enhancement with the venous vasculature. This lesion contacted with the tympanic membrane, incudostapedial joint and round window, which might be attributable to interruption of sound transmission mechanics. Otherwise there was no evidence of mass or trauma related lesions in the temporal bone. LESSONS: Although most of jugular bulb anomalies are asymptomatic, patients may present with conductive hearing loss due to the interference of sound transmission mechanics.