A Deep Learning Algorithm to Identify Anatomical Landmarks on Computed Tomography of the Temporal Bone.

BACKGROUND: Petrous temporal bone cone-beam computed tomography scans help aid diagnosis and accurate identification of key operative landmarks in temporal bone and mastoid surgery. Our primary objective was to determine the accuracy of using a deep learning convolutional neural network algorithm to augment identification of structures on petrous temporal bone cone-beam computed tomography. Our secondary objective was to compare the accuracy of convolutional neural network structure identification when trained by a senior versus junior clinician. METHODS: A total of 129 petrous temporal bone cone-beam computed tomography scans were obtained from an Australian public tertiary hospital. Key intraoperative landmarks were labeled in 68 scans using bounding boxes on axial and coronal slices at the level of the malleoincudal joint by an otolaryngology registrar and board-certified otolaryngologist. Automated structure identification was performed on axial and coronal slices of the remaining 61 scans using a convolutional neural network (Microsoft Custom Vision) trained using the labeled dataset. Convolutional neural network structure identification accuracy was manually verified by an otolaryngologist, and accuracy when trained by the registrar and otolaryngologist labeled datasets respectively was compared. RESULTS: The convolutional neural network was able to perform automated structure identification in petrous temporal bone cone-beam computed tomography scans with a high degree of accuracy in both axial (0.958) and coronal (0.924) slices (P < .001). Convolutional neural network accuracy was proportionate to the seniority of the training clinician in structures with features more difficult to distinguish on single slices such as the cochlea, vestibule, and carotid canal. CONCLUSION: Convolutional neural networks can perform automated structure identification in petrous temporal bone cone-beam computed tomography scans with a high degree of accuracy, with the performance being proportionate to the seniority of the training clinician. Training of the convolutional neural network by the most senior clinician is desirable to maximize the accuracy of the results.

Large volume haemorrhage following transoral robotic surgery (TORS) as a result of fibromuscular dysplasia: first reported case.

We present a case of a 61-year-old woman who suffered a haemorrhagic complication of an aneurysmal left lingual artery, secondary to fibromuscular dysplasia, following transoral robotic surgery (TORS). She was admitted through the emergency department 3 days after resection of a central base of tongue tumour. She suffered a massive haemorrhage requiring intensive care admission, blood transfusion, intubation, operative and endovascular intervention. The diagnosis of fibromuscular dysplasia was made at angiography. During attempts to embolise the culprit left lingual artery, the vessel dissected at its origin leading to arrest of bleeding. Repeat angiograms during her admission demonstrated unchanged appearances and ruled out recanalisation of the vessel. She was extubated and remained stable on the ward, discharged home some days later in good health. To our knowledge, this is the first ever reported case of fibromuscular dysplasia affecting the lingual artery leading to aneurysmal dilation and severe haemorrhage following TORS.

A Rare Cause of a Fluctuating Cystic Lesion in the External Auditory Canal.

Temporomandibular joint (TMJ) ganglionic cyst is an uncommon entity and only a few have been reported in the literature. TMJ ganglion within the external auditory canal presenting clinically as a fluctuating cystic lesion has never been reported. Here, we present a unique case of such a lesion together with otoscopic and radiological images as well as provide a descriptive review of TMJ ganglionic cysts.