Robot-assisted perception augmentation for online detection of insertion failure during cochlear implant surgery

Artificial Intelligence and Pediatric Otolaryngology

Artificial intelligence (AI) studies show how to program computers to simulate human intelligence and perform data interpretation, learning, and adaptive decision-making. Within pediatric otolaryngology, there is a growing body of evidence for the role of AI in diagnosis and triaging of acute otitis media and middle ear effusion, pediatric sleep disorders, and syndromic craniofacial anomalies. The use of automated machine learning with robotic devices intraoperatively is an evolving field of study, particularly in the realms of pediatric otologic surgery and computer-aided planning for maxillofacial reconstruction, and we will likely continue seeing novel applications of machine learning in otolaryngologic surgery.

Development of Automated Tool for Electrode Array Insertion and its Study on Intracochlear Pressure

Cochlear implantation is the most successful approach for people with profound sensorineural hearing loss. Manual insertion of the electrode array may result in damaging the soft tissue structures and basilar membrane. An automated electrode array insertion device is reported to be less traumatic in cochlear implant surgery.

OBJECTIVES

The present work develops a simple, reliable, and compact device for automatically inserting the electrode array during cochlear implantation and test the device to observe intracochlear pressure during simulated electrode insertion.

METHODS

The device actuates the electrode array by a roller mechanism. For testing the automated device, a straight cochlea having the dimension of the scala tympani and a model electrode is developed using a 3D printer. A pressure sensor is utilized to observe the pressure change at different insertional conditions.

RESULTS

The electrode is inserted into a prototype cochlea at different speeds without any pause, and it is noticed that the pressure is increased with the depth of insertion of the electrode irrespective of the speed of electrode insertion. The rate of pressure change is observed to be increased exponentially with the speed of insertion.

CONCLUSION

At an insertion speed of 0.15 mm/s, the peak pressure is observed to be 133 Pa, which can be further evaluated in anatomical models for clinical scenarios.

LEVEL OF EVIDENCE

N/A Laryngoscope, 134:1388-1395, 2024.

Cochlear Implant Fold Detection in Intra-operative CT Using Weakly Supervised Multi-task Deep Learning

In cochlear implant (CI) procedures, an electrode array is surgically inserted into the cochlea. The electrodes are used to stimulate the auditory nerve and restore hearing sensation for the recipient. If the array folds inside the cochlea during the insertion procedure, it can lead to trauma, damage to the residual hearing, and poor hearing restoration. Intraoperative detection of such a case can allow a surgeon to perform reimplantation. However, this intraoperative detection requires experience and electrophysiological tests sometimes fail to detect an array folding. Due to the low incidence of array folding, we generated a dataset of CT images with folded synthetic electrode arrays with realistic metal artifact. The dataset was used to train a multitask custom 3D-UNet model for array fold detection. We tested the trained model on real post-operative CTs (7 with folded arrays and 200 without). Our model could correctly classify all the fold-over cases while misclassifying only 3 non fold-over cases. Therefore, the model is a promising option for array fold detection.

Machine Learning and Cochlear Implantation-A Structured Review of Opportunities and Challenges

OBJECTIVE

The use of machine learning technology to automate intellectual processes and boost clinical process efficiency in medicine has exploded in the past 5 years. Machine learning excels in automating pattern recognition and in adapting learned representations to new settings. Moreover, machine learning techniques have the advantage of incorporating complexity and are free from many of the limitations of traditional deterministic approaches. Cochlear implants (CI) are a unique fit for machine learning techniques given the need for optimization of signal processing to fit complex environmental scenarios and individual patients' CI MAPping. However, there are many other opportunities where machine learning may assist in CI beyond signal processing. The objective of this review was to synthesize past applications of machine learning technologies for pediatric and adult CI and describe novel opportunities for research and development.

DATA SOURCES

The PubMed/MEDLINE, EMBASE, Scopus, and ISI Web of Knowledge databases were mined using a directed search strategy to identify the nexus between CI and artificial intelligence/machine learning literature.

STUDY SELECTION

Non-English language articles, articles without an available abstract or full-text, and nonrelevant articles were manually appraised and excluded. Included articles were evaluated for specific machine learning methodologies, content, and application success.

DATA SYNTHESIS

The database search identified 298 articles. Two hundred fifty-nine articles (86.9%) were excluded based on the available abstract/full-text, language, and relevance. The remaining 39 articles were included in the review analysis. There was a marked increase in year-over-year publications from 2013 to 2018. Applications of machine learning technologies involved speech/signal processing optimization (17; 43.6% of articles), automated evoked potential measurement (6; 15.4%), postoperative performance/efficacy prediction (5; 12.8%), and surgical anatomy location prediction (3; 7.7%), and 2 (5.1%) in each of robotics, electrode placement performance, and biomaterials performance.

CONCLUSION

The relationship between CI and artificial intelligence is strengthening with a recent increase in publications reporting successful applications. Considerable effort has been directed toward augmenting signal processing and automating postoperative MAPping using machine learning algorithms. Other promising applications include augmenting CI surgery mechanics and personalized medicine approaches for boosting CI patient performance. Future opportunities include addressing scalability and the research and clinical communities' acceptance of machine learning algorithms as effective techniques.

Investigating variability in cochlear implant electrode array alignment and the potential of visualization guidance

Background Internal cochlear anatomy is difficult to discern from external inspection, hindering cochlear implant electrode insertion. Methods A user study characterized the repeatability of standard surgical technique and examined the role of visual inspection and guidance cues in reducing electrode array insertion misalignment. Results Without guidance, a large spread in angles of insertion, up to 30°, was observed, highlighting the need for intraoperative guidance. Visual inspection did not significantly improve overall orientation, suggesting the need for alternate intracochlear visualization methods and/or increased training to effectively improve surgeon understanding of the visualized images. Visual cues and guidance software increased repeatability of surgeon performance, reducing one metric of repeatability to ±2°. Conclusions This study establishes a baseline for surgeon variability in cochlear implant insertion and supports the need and lays the groundwork for future intraoperative guidance techniques.