Inflammation of the Temporal Bone

Deep Learning Method for Rapid Simultaneous Multistructure Temporal Bone Segmentation

OBJECTIVE

To develop and validate a deep learning algorithm for the automated segmentation of key temporal bone structures from clinical computed tomography (CT) data sets.

STUDY DESIGN

Cross-sectional study.

SETTING

A total of 325 CT scans from a clinical database.

METHOD

A state-of-the-art deep learning (DL) algorithm (SwinUNETR) was used to train a prediction model for rapid segmentation of 9 key temporal bone structures in a data set of 325 clinical CTs. The data set was manually annotated by a specialist to serve as the ground truth. The data set was randomly split into training (n = 260) and testing (n = 65) sets. The model's performance was objectively assessed through external validation on the test set using metrics including Dice, Balanced accuracy, Hausdorff distances, and processing time.

RESULTS

The model achieved an average Dice coefficient of 0.87 for all structures, an average balanced accuracy of 0.94, an average Hausdorff distance of 0.79 mm, and an average processing time of 9.1 seconds per CT.

CONCLUSION

The present DL model for the automated simultaneous segmentation of multiple structures within the temporal bone from CTs achieved high accuracy according to currently commonly employed objective analysis. The results demonstrate the potential of the method to improve preoperative evaluation and intraoperative guidance in otologic surgery.

Imaging of Temporal Bone Mass Lesions: A Pictorial Review

Tumoral lesions of the temporal bone include benign or malignant tumors and congenital or inflammatory lesions. Temporal bone lesions are difficult to approach. Therefore, making a preoperative diagnosis and considering whether the lesions require treatment are necessary; if they require treatment, then the type of treatment requires consideration. These tumors cannot be observed directly and must be diagnosed based on symptoms and imaging findings. However, the differentiation of temporal bone lesions is difficult because they are rare and large in variety. In this pictorial review, we divided temporal bone lesions by location such as along the facial nerve, along the internal jugular vein, around the endolymphatic sac, in the internal auditory canal/cerebellopontine angle, petrous apex, middle ear, and mastoid, focusing on the imaging findings of temporal bone lesions. Then, we created a diagnostic flowchart that suggested that the systematic separation of imaging findings is useful for differentiation. Although it is necessary to make comprehensive judgments based on the clinical symptoms, patient background, and imaging findings to diagnose temporal bone mass lesions, capturing imaging features can be a useful differentiation method.

Imaging of Acute and Chronic Skull Base Infection

Skull base infections are uncommon but can be life threatening without timely recognition. Imaging plays a crucial role because symptoms can be vague and nonlocalizing. Necrotizing otitis externa in diabetic or immunocompromised patients is the commonest cause of skull base osteomyelitis (SBO), followed by sinogenic infections and idiopathic central SBO. Multiparametric magnetic resonance (MR) and high-resolution CT are the mainstays for establishing a diagnosis and estimating disease extent, with MR being superior in ascertaining marrow and soft tissue involvement. Monitoring treatment response, of which imaging is a fundamental part, is challenging, with emerging promising imaging tools.

Imaging of Petrous Apex Lesions

The petrous apex may be affected by a range of lesions, commonly encountered as incidental and asymptomatic findings on imaging performed for other clinical reasons. Symptoms associated with petrous apex lesions commonly relate to mass effect and/or direct involvement of closely adjacent structures. Petrous apex lesions are optimally assessed using a combination of high-resolution CT and MRI of the skull base. Management of petrous apex lesions varies widely, reflecting the range of possible pathologies, with imaging playing a key role, including lesion characterization, surveillance, surgical planning, and oncological contouring.

Imaging the facial nerve: A contemporary review of anatomy and pathology

PURPOSE

The facial nerve is the seventh paired cranial nerve which anatomically can be divided into six distinct segments. There are a wide range of pathologies that may occur along each segment of the nerve. The aim of this pictorial review is to untangle the complex appearances of the facial nerve, both in its normal anatomical course and when affected by pathology.

METHOD

This review takes an evidence-based segmental approach to the evaluation of the facial nerve in terms of its anatomy and clinical features of common pathologies affecting specific segments of the nerve. The typical multimodal radiological findings of common facial nerve pathologies are included in the review using imaging from select pathologically confirmed cases.

RESULTS

A wide range of pathologies ranging from congenital abnormalities to inflammatory, infective and neoplastic processes can affect the facial nerve. As select segments of the nerve are better evaluated on certain imaging modalities a clear understanding of the anatomy and clinical features associated with specific facial nerve pathologies enables the radiologist to tailor the imaging test to best answer the clinical question.

CONCLUSIONS

This review provides a segmental clinical-radiological approach to imaging the facial nerve. In addition, recent developments in facial nerve imaging that may come into mainstream use in the near future are touched upon.

High-resolution computed tomography (HRCT) in pediatric and adult patients with unsafe chronic suppurative otitis media (CSOM) and its surgical correlation

Background and Aim:

Atticoantral, alias unsafe type of CSOM affects the posterosuperior part of the middle ear cleft and is frequently coupled with complications and bony erosions. This study aimed to correlate the high-resolution computed tomography (HRCT) temporal bone and intraoperative findings in the patients with the unsafe type of CSOM.

Methods:

This prospective study included 50 patients (28 males: 22 females; mean age 24 ± 14 years) who presented with clinically suspected unsafe CSOM. All patients underwent HRCT of the temporal bone and subsequent surgical procedure. The intraoperative and histopathological findings were compared with HRCT findings. Descriptive statistics, sensitivity, specificity, and positive and negative predictive value for HRCT were calculated. Student's t-test and Chi-square test were performed.

Results:

Out of 50 patients, left, right, and bilateral ear involvement were seen in 42% (21/50), 38% (19/50), and 20% (10/50) patients, respectively. Ear discharge was the most common symptom (100%) followed by earache (66%), vertigo (16%), and tinnitus (14%), respectively. Cholesteatoma was reported in 82% (49/60) of ears on HRCT while histopathological and intraoperative evaluation confirmed the diagnosis in 40 out of 49 ears. In 18% (11/60) ears, the cholesteatoma was not diagnosed on HRCT evaluation; however, the intraoperative and histopathological assessment revealed cholesteatoma in six patients while the rest had granulation tissue. For detection of ossicular erosions, tegmen erosions, erosions of facial nerve canal, erosions of sigmoid sinus plate, and erosions of lateral/posterior semicircular canals; HRCT had high sensitivity (86.44%–100%) and specificity (93.33%–100%).

Conclusion:

HRCT has a superb correlation with intraoperative findings and is a valuable tool for preoperative assessment of temporal bone pathologies.

Reliability of diffusion-weighted magnetic resonance imaging in differentiation of recurrent cholesteatoma and granulation tissue after intact canal wall mastoidectomy

Objective

To assess the reliability of diffusion-weighted magnetic resonance imaging in differentiating recurrent cholesteatoma from granulation tissue after intact canal wall mastoidectomy.

Methods

A prospective study was conducted of 56 consecutive patients with suspected cholesteatoma recurrence after intact canal wall mastoidectomy who underwent diffusion-weighted imaging and delayed contrast magnetic resonance imaging of the temporal bone. The final diagnosis was recurrence in 38 patients and granulation tissue in 18 patients.

Results

Cholesteatoma detection on diffusion-weighted imaging based on two sets of readings had sensitivity of 94.7 and 94.7 per cent, specificity of 94.4 and 88.9 per cent, and accuracy of 94.6 and 92.8 per cent, with good intra-observer agreement (Κ= 0.72,p= 0.001). Cholesteatoma detection on delayed contrast magnetic resonance imaging had sensitivity of 81.6 and 78.9 per cent, specificity of 77.8 and 66.7 per cent, and accuracy of 80.4 and 75.0 per cent, with fair intra-observer agreement (Κ= 0.57,p= 0.001). The mean cholesteatoma diameter on diffusion-weighted imaging was 7.7 ± 1.8 and 7.9 ± 1.8 mm, with excellent intra-observer agreement (Κ= 0.994,p= 0.001).

Conclusion

Diffusion-weighted imaging is a reliable method for differentiating recurrent cholesteatoma and granulation tissue after intact canal wall mastoidectomy.