Malformations of the lateral semicircular canal correlated with data from the audiogram

Training and validation of a deep learning U-net architecture general model for automated segmentation of inner ear from CT

BACKGROUND

The intricate three-dimensional anatomy of the inner ear presents significant challenges in diagnostic procedures and critical surgical interventions. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNN), have shown promise for segmenting specific structures in medical imaging. This study aimed to train and externally validate an open-source U-net DL general model for automated segmentation of the inner ear from computed tomography (CT) scans, using quantitative and qualitative assessments.

METHODS

In this multicenter study, we retrospectively collected a dataset of 271 CT scans to train an open-source U-net CNN model. An external set of 70 CT scans was used to evaluate the performance of the trained model. The model's efficacy was quantitatively assessed using the Dice similarity coefficient (DSC) and qualitatively assessed using a 4-level Likert score. For comparative analysis, manual segmentation served as the reference standard, with assessments made on both training and validation datasets, as well as stratified analysis of normal and pathological subgroups.

RESULTS

The optimized model yielded a mean DSC of 0.83 and achieved a Likert score of 1 in 42% of the cases, in conjunction with a significantly reduced processing time. Nevertheless, 27% of the patients received an indeterminate Likert score of 4. Overall, the mean DSCs were notably higher in the validation dataset than in the training dataset.

CONCLUSION

This study supports the external validation of an open-source U-net model for the automated segmentation of the inner ear from CT scans.

RELEVANCE STATEMENT

This study optimized and assessed an open-source general deep learning model for automated segmentation of the inner ear using temporal CT scans, offering perspectives for application in clinical routine. The model weights, study datasets, and baseline model are worldwide accessible.

KEY POINTS

A general open-source deep learning model was trained for CT automated inner ear segmentation. The Dice similarity coefficient was 0.83 and a Likert score of 1 was attributed to 42% of automated segmentations. The influence of scanning protocols on the model performances remains to be assessed.

Individualized repositioning with a mechanical rotational chair facilitates successful treatment of patients with very retractable benign paroxysmal positional vertigo

BACKGROUND

About 12.5 % of patients diagnosed with benign paroxysmal positional vertigo (BPPV), experience persistent BPPV where it is unknown why some BPPV cases are very refractory (vrBPPV) to treatment.

OBJECTIVES

The primary objective was to investigate if patients with vrBPPV could be successfully treated with a mechanical rotation chair (MRC) adjusted to the exact vertical semicircular canal (SCC) angles of the individual patient. Secondary endpoint was to determine if inner ear anomalies were predominant in these patients.

METHODS

This prospective clinical trial included 20 patients (main group) who underwent computed tomography (CT) with measurements of the bony island and the width between the SCC walls of the posterior leg of the lateral SCCs. The inter-SCC angles, the angles between the sagittal plane and the vertical SCCs were compared to the presumed mean standard angles of the SCCs. Of these, 14 patients (subgroup) underwent individualized treatment with the Rotundum® repositioning chair according to their measured SCC angles.

RESULTS

All measured SCC angles differed significantly (p < 0.05) from the presumed mean standard SCC angles, except the angle between the sagittal plane and the left posterior SCC (p-SCC). Three out of 14 patients experienced subjective and objective remission after treatment with this MRC. Six out of 14 patients experienced either subjective remission or objective remission.

CONCLUSIONS

Patients with vrBPPV have vertical SCC angles that differ significantly from the presumed mean standard SCC angles. Individualized treatment with this MRC successfully treated 21.4 % of the patients with vrBPPV and provided subjective relief for 42.9 %.

Research on congenital severe-to-profound sensorineural hearing loss associated with central lucency of the bony island of the lateral semicircular canal

BACKGROUND

Central lucency of the bony island of the lateral semicircular canal (LSCC) is commonly found in patients with congenital severe-to-profound sensorineural hearing loss (SNHL).

OBJECTIVE

Exploring the significance of bony island lucency of LSCC in congenital severe-to-profound SNHL patients.

MATERIAL AND METHODS

Retrospective measurements of the inner ear structures were made on axial temporal bone CT scans from 182 (364 ears) congenital severe-to-profound SNHL patients and 50 (100 ears) tympanic membrane perforation (TMP) patients.

RESULTS

The incidence of bony island lucency of LSCC was 46.7% in the congenital severe-to-profound SNHL group and 0% in the TMP group. There was a statistically significant difference in inner ear structures among congenital severe-to-profound SNHL patients with normal inner ear structure and bony island lucency of LSCC, congenital severe-to-profound SNHL patients with normal inner ear structure and no bony island lucency of LSCC, and TMP patients. The importance of the bony island lucency of LSCC was further confirmed through multiple linear regression analysis.

CONCLUSIONS AND SIGNIFICANCE

Bony island lucency may have significance in congenital severe-to-profound SNHL and may be a manifestation of largely overlooked SCC malformation or hypoplasia of the inner ear.

Partial Duplication of the Lateral Semicircular Canal—A Novel Anatomical Malformation in a Child with Barakat Syndrome

Several known genetic causes of sensorineural deafness are associated with dysplasia of inner ear structures, including the cochlea and labyrinth. Here, we present a child with Barakat syndrome and sensorineural hearing loss, found to have multiple inner ear anomalies including partial duplication of the posterior limb of the left lateral semicircular canal. To our knowledge, duplication of the semicircular canal has not previously been reported. This finding expands our understanding of the range of anatomical variations observed in congenital inner ear malformations, and further characterizes the phenotypic manifestations of Barakat syndrome.

Case Report: Challenging Otologic Surgery in Patients With 22q11.2 Deletion Syndrome

Patients with 22q11.2 deletion syndrome frequently have conductive hearing loss and/or chronic otitis media. Otologic surgery is often opted for. We present two patients undergoing otologic surgery. This case report outlines the typical otologic surgical challenges in patients with 22q11.2 deletion syndrome. Case one is a 52 year old male patient with chronic otitis media who underwent a mastoidectomy. The pre-operative CT scan showed a fused lateral semicircular canal and vestibule. Peroperatively, the lateral semicircular canal could not be used as a landmark to identify the facial nerve. Case two is a 10 year old female patient with conductive hearing loss. A middle ear inspection was performed where a bony epitympanic fixation of the malleus was encountered. In addition, the manubrium of the malleus was atrophic and also fixated. The bony fixation was removed, as was the manubrium of the malleus. Otologists should be aware of these typical anatomical variations in patients with 22q11.2 deletion syndrome. We recommend to use CT scanning of the middle and inner ear when preparing for otologic surgery in 22q11.2 deletion syndrome.