ABSTRACT
Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method's performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset.
Subject(s)
Ear, Inner , Ear, Inner/diagnostic imaging , Principal Component Analysis , ROC Curve , Tomography, X-Ray ComputedABSTRACT
Introduction: The perception of phonemes is guided by both low-level acoustic cues and high-level linguistic context. However, differentiating between these two types of processing can be challenging. In this study, we explore the utility of pupillometry as a tool to investigate both low- and high-level processing of phonological stimuli, with a particular focus on its ability to capture novelty detection and cognitive processing during speech perception. Methods: Pupillometric traces were recorded from a sample of 22 Danish-speaking adults, with self-reported normal hearing, while performing two phonological-contrast perception tasks: a nonword discrimination task, which included minimal-pair combinations specific to the Danish language, and a nonword detection task involving the detection of phonologically modified words within sentences. The study explored the perception of contrasts in both unprocessed speech and degraded speech input, processed with a vocoder. Results: No difference in peak pupil dilation was observed when the contrast occurred between two isolated nonwords in the nonword discrimination task. For unprocessed speech, higher peak pupil dilations were measured when phonologically modified words were detected within a sentence compared to sentences without the nonwords. For vocoded speech, higher peak pupil dilation was observed for sentence stimuli, but not for the isolated nonwords, although performance decreased similarly for both tasks. Conclusion: Our findings demonstrate the complexity of pupil dynamics in the presence of acoustic and phonological manipulation. Pupil responses seemed to reflect higher-level cognitive and lexical processing related to phonological perception rather than low-level perception of acoustic cues. However, the incorporation of multiple talkers in the stimuli, coupled with the relatively low task complexity, may have affected the pupil dilation.
ABSTRACT
Understanding cochlear anatomy is crucial for developing less traumatic electrode arrays and insertion guidance for cochlear implantation. The human cochlea shows considerable variability in size and morphology. This study analyses 1000+ clinical temporal bone CT images using a web-based image analysis tool. Cochlear size and shape parameters were obtained to determine population statistics and perform regression and correlation analysis. The analysis revealed that cochlear morphology follows Gaussian distribution, while cochlear dimensions A and B are not well-correlated to each other. Additionally, dimension B is more correlated to duct lengths, the wrapping factor and volume than dimension A. The scala tympani size varies considerably among the population, with the size generally decreasing along insertion depth with dimensional jumps through the trajectory. The mean scala tympani radius was 0.32 mm near the 720° insertion angle. Inter-individual variability was four times that of intra-individual variation. On average, the dimensions of both ears are similar. However, statistically significant differences in clinical dimensions were observed between ears of the same patient, suggesting that size and shape are not the same. Harnessing deep learning-based, automated image analysis tools, our results yielded important insights into cochlear morphology and implant development, helping to reduce insertion trauma and preserving residual hearing.
ABSTRACT
Auditory science increasingly builds on concepts and testing paradigms originated in behavioral psychology and cognitive neuroscience - an evolution of which the resulting discipline is now known as cognitive hearing science. Experimental cognitive hearing science paradigms call for hybrid cognitive and psychobehavioral tests such as those relating the attentional system, working memory, and executive functioning to low-level auditory acuity or speech intelligibility. Building complex multi-stimuli experiments can rapidly become time-consuming and error-prone. Platform-based experiment design can help streamline the implementation of cognitive hearing science experimental paradigms, promote the standardization of experiment design practices, and ensure reliability and control. Here, we introduce a set of features for the open-source python-based OpenSesame platform that allows the rapid implementation of custom behavioral and cognitive hearing science tests, including complex multichannel audio stimuli while interfacing with various synchronous inputs/outputs. Our integration includes advanced audio playback capabilities with multiple loudspeakers, an adaptive procedure, compatibility with standard I/Os and their synchronization through implementation of the Lab Streaming Layer protocol. We exemplify the capabilities of this extended OpenSesame platform with an implementation of the three-alternative forced choice amplitude modulation detection test and discuss reliability and performance. The new features are available free of charge from GitHub: https://github.com/elus-om/BRM_OMEXP .
Subject(s)
Hearing , Speech Perception , Humans , Reproducibility of Results , Auditory Perception , Executive Function , CognitionABSTRACT
Despite substantial technical advances and wider clinical use, cochlear implant (CI) users continue to report high and elevated listening effort especially under challenging noisy conditions. Among all the objective measures to quantify listening effort, pupillometry is one of the most widely used and robust physiological measures. Previous studies with normally hearing (NH) and hearing-impaired (HI) listeners have shown that the relation between speech performance in noise and listening effort (as measured by peak pupil dilation) is not linear and exhibits an inverted-U shape. However, it is unclear whether the same psychometric relation exists in CI users, and whether individual differences in auditory sensitivity and central cognitive capacity affect this relation. Therefore, we recruited 17 post-lingually deaf CI adults to perform speech-in-noise tasks from 0 to 20 dB SNR with a 4 dB step size. Simultaneously, their pupillary responses and self-reported subjective effort were recorded. To characterize top-down and bottom-up individual variabilities, a spectro-temporal modulation task and a set of cognitive abilities were measured. Clinical word recognition in quiet and Quality of Life (QoL) were also collected. Results showed that at a group level, an inverted-U shape psychometric curve between task difficulty (SNR) and peak pupil dilation (PPD) was not observed. Individual shape of the psychometric curve was significantly associated with some individual factors: CI users with higher clinical word and speech-in-noise recognition showed a quadratic decrease of PPD over increasing SNRs; CI users with better non-verbal intelligence and lower QoL showed smaller average PPD. To summarize, individual differences in CI users had a significant impact on the psychometric relation between pupillary response and task difficulty, hence affecting the interpretation of pupillary response as listening effort (or engagement) at different task difficulty levels. Future research and clinical applications should further characterize the possible effects of individual factors (such as motivation or engagement) in modulating CI users' occurrence of 'tipping point' on their psychometric functions, and develop an individualized method for reliably quantifying listening effort using pupillometry.
ABSTRACT
The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus-a web-based research platform for automated pre- and post-implantation cochlear analysis. Nautilus delineates cochlear structures from pre-operative clinical CT images by combining deep learning and Bayesian inference approaches. It enables the extraction of electrode locations from a post-operative CT image using convolutional neural networks and geometrical inference. By fusing pre- and post-operative images, Nautilus is able to provide a set of personalized pre- and post-operative metrics that can serve the exploration of clinically relevant questions in cochlear implantation therapy. In addition, Nautilus embeds a self-assessment module providing a confidence rating on the outputs of its pipeline. We present a detailed accuracy and robustness analyses of the tool on a carefully designed dataset. The results of these analyses provide legitimate grounds for envisaging the implementation of image-guided cochlear implant practices into routine clinical workflows.
ABSTRACT
INTRODUCTION: A growing body of evidence suggests that hearing loss is a significant and potentially modifiable risk factor for cognitive impairment. Although the mechanisms underlying the associations between cognitive decline and hearing loss are unclear, listening effort has been posited as one of the mechanisms involved with cognitive decline in older age. To date, there has been a lack of research investigating this association, particularly among adults with mild cognitive impairment (MCI). METHODS AND ANALYSIS: 15-25 cognitively healthy participants and 15-25 patients with MCI (age 40-85 years) will be recruited to participate in an exploratory study investigating the association between cognitive functioning and listening effort. Both behavioural and objective measures of listening effort will be investigated. The sentence-final word identification and recall (SWIR) test will be administered with single talker non-intelligible speech background noise while monitoring pupil dilation. Evaluation of cognitive function will be carried out in a clinical setting using a battery of neuropsychological tests. This study is considered exploratory and proof of concept, with information taken to help decide the validity of larger-scale trials. ETHICS AND DISSEMINATION: Written approval exemption was obtained by the Scientific Ethics Committee in the central region of Denmark (De Videnskabsetiske Komiteer i Region Hovedstaden), reference 19042404, and the project is registered pre-results at clinicaltrials.gov, reference NCT04593290, Protocol ID 19042404. Study results will be disseminated in peer-reviewed journals and conferences.
Subject(s)
Hearing Loss , Speech Perception , Adult , Aged , Aged, 80 and over , Case-Control Studies , Cognition , Humans , Listening Effort , Middle AgedABSTRACT
BACKGROUND: The gold standard measurement for recording sleep is polysomnography performed in a hospital environment for 1 night. This requires individuals to sleep with a device and several sensors attached to their face, scalp, and body, which is both cumbersome and expensive. Self-trackers, such as wearable sensors (eg, smartwatch) and nearable sensors (eg, sleep mattress), can measure a broad range of physiological parameters related to free-living sleep conditions; however, the optimal duration of such a self-tracker measurement is not known. For such free-living sleep studies with actigraphy, 3 to 14 days of data collection are typically used. OBJECTIVE: The primary goal of this study is to investigate if 3 to 14 days of sleep data collection is sufficient while using self-trackers. The secondary goal is to investigate whether there is a relationship among sleep quality, physical activity, and heart rate. Specifically, we study whether individuals who exhibit similar activity can be clustered together and to what extent the sleep patterns of individuals in relation to seasonality vary. METHODS: Data on sleep, physical activity, and heart rate were collected over 6 months from 54 individuals aged 52 to 86 years. The Withings Aura sleep mattress (nearable; Withings Inc) and Withings Steel HR smartwatch (wearable; Withings Inc) were used. At the individual level, we investigated the consistency of various physical activities and sleep metrics over different time spans to illustrate how sensor data from self-trackers can be used to illuminate trends. We used exploratory data analysis and unsupervised machine learning at both the cohort and individual levels. RESULTS: Significant variability in standard metrics of sleep quality was found between different periods throughout the study. We showed specifically that to obtain more robust individual assessments of sleep and physical activity patterns through self-trackers, an evaluation period of >3 to 14 days is necessary. In addition, we found seasonal patterns in sleep data related to the changing of the clock for daylight saving time. CONCLUSIONS: We demonstrate that >2 months' worth of self-tracking data are needed to provide a representative summary of daily activity and sleep patterns. By doing so, we challenge the current standard of 3 to 14 days for sleep quality assessment and call for the rethinking of standards when collecting data for research purposes. Seasonal patterns and daylight saving time clock change are also important aspects that need to be taken into consideration when choosing a period for collecting data and designing studies on sleep. Furthermore, we suggest using self-trackers (wearable and nearable ones) to support longer-term evaluations of sleep and physical activity for research purposes and, possibly, clinical purposes in the future.
ABSTRACT
PURPOSE: To compare listening ability (speech reception thresholds) and real-life listening experience in users with a percutaneous bone conduction device (BCD) with two listening programs differing only in high-frequency gain. In situ real-life experiences were recorded with ecological momentary assessment (EMA) techniques combined with real-time acoustical data logging and standard retrospective questionnaires. METHODS: Nineteen experienced BCD users participated in this study. They all used a Ponto 4 BCD from Oticon Medical during a 4-week trial period. Environmental data and device parameters (i.e., device usage and volume control) were logged in real-time on an iPhone via a custom iOS research app. At the end of the trial period, subjects filled in APHAB, SSQ, and preference questionnaires. Listening abilities with the two programs were evaluated with speech reception threshold tests. RESULTS: The APHAB and SSQ questionnaires did not reveal any differences between the two listening programs. The EMAs revealed group-level effects, indicating that in speech and noisy listening environments, subjects preferred the default listening program, and found the program with additional high-frequency gain too loud. This finding was corroborated by the volume log-subjects avoided the higher volume control setting and reacted more to changes in environmental sound pressure levels when using the high-frequency gain program. Finally, day-to-day changes in EMAs revealed acclimatization effects in the listening experience for ratings of "sound quality" and "program suitability" of the BCD, but not for ratings of "loudness perception" and "speech understanding". The acclimatization effect did not differ among the listening programs. CONCLUSION: Adding custom high-frequency amplification to the BCD target-gain prescription improves speech reception in laboratory tests under quiet conditions, but results in poorer real-life listening experiences due to loudness.
ABSTRACT
The association of smart mobile devices and lab-on-chip technologies offers unprecedented opportunities for the emergence of direct-to-consumer in vitro medical diagnostics applications. Despite their clear transformative potential, obstacles remain to the large-scale disruption and long-lasting success of these systems in the consumer market. For instance, the increasing level of complexity of instrumented lab-on-chip devices, coupled to the sporadic nature of point-of-care testing, threatens the viability of a business model mainly relying on disposable/consumable lab-on-chips. We argued recently that system evolvability, defined as the design characteristic that facilitates more manageable transitions between system generations via the modification of an inherited design, can help remedy these limitations. In this paper, we discuss how platform-based design can constitute a formal entry point to the design and implementation of evolvable smart device/lab-on-chip systems. We present both a hardware/software design framework and the implementation details of a platform prototype enabling at this stage the interfacing of several lab-on-chip variants relying on current- or impedance-based biosensors. Our findings suggest that several change-enabling mechanisms implemented in the higher abstraction software layers of the system can promote evolvability, together with the design of change-absorbing hardware/software interfaces. Our platform architecture is based on a mobile software application programming interface coupled to a modular hardware accessory. It allows the specification of lab-on-chip operation and post-analytic functions at the mobile software layer. We demonstrate its potential by operating a simple lab-on-chip to carry out the detection of dopamine using various electroanalytical methods.