Detection of auditory brainstem response peaks using image processing techniques in infants with normal hearing sensitivity

Abstract

IntroductionThe auditory brainstem response (ABR) is measured to find the brainstem-level peripheral auditory nerve system integrity in children having normal hearing. The Auditory Evoked Potential (AEP)s are generated using acoustic stimuli. Interpreting these waves requires competence to avoid misdiagnosing hearing problems. Automating ABR test labeling with computer vision may reduce human error. MethodThe ABR test results of 26 children aged 1 to 20 months with normal hearing in both ears were used. A new approach is suggested for automatically calculating the peaks of waves of different intensities (in decibels). The procedure entails acquiring wave images from an Audera device using the Color Thresholder method, segmenting each wave as a single wave image using the Image Region Analyzer application, converting all wave images into waves using Image Processing (IP) techniques, and finally calculating the latency of the peaks for each wave to be used by an audiologist for diagnosing the disease. FindingsImage processing techniques were able to detect 1, 3, and 5 waves in the diagnosis field with accuracy (0.82), (0.98), and (0.98), respectively, and its precision for waves 1, 3, and 5, were respectively (0.32), (0.97) and (0.87). This evaluation also worked well in the thresholding part and 82.7 % correctly detected the ABR waves. ConclusionOur findings indicate that the audiology test battery suite can be made more accurate, quick, and error-free by using technology to automatically detect and label ABR waves.