Otolaryngology - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 12
-
ItemAutomatic analysis of cochlear response using electrocochleography signals during cochlear implant surgery(PUBLIC LIBRARY SCIENCE, 2022-07-14)Cochlear implants (CIs) provide an opportunity for the hearing impaired to perceive sound through electrical stimulation of the hearing (cochlear) nerve. However, there is a high risk of losing a patient's natural hearing during CI surgery, which has been shown to reduce speech perception in noisy environments as well as music appreciation. This is a major barrier to the adoption of CIs by the hearing impaired. Electrocochleography (ECochG) has been used to detect intra-operative trauma that may lead to loss of natural hearing. There is early evidence that ECochG can enable early intervention to save natural hearing of the patient. However, detection of trauma by observing changes in the ECochG response is typically carried out by a human expert. Here, we discuss a method of automating the analysis of cochlear responses during CI surgery. We establish, using historical patient data, that the proposed method is highly accurate (∼94% and ∼95% for sensitivity and specificity respectively) when compared to a human expert. The automation of real-time cochlear response analysis is expected to improve the scalability of ECochG and improve patient safety.
-
ItemA Deep Learning Framework for Segmenting Brain Tumors Using MRI and Synthetically Generated CT Images(MDPI, 2022-01)Multi-modal three-dimensional (3-D) image segmentation is used in many medical applications, such as disease diagnosis, treatment planning, and image-guided surgery. Although multi-modal images provide information that no single image modality alone can provide, integrating such information to be used in segmentation is a challenging task. Numerous methods have been introduced to solve the problem of multi-modal medical image segmentation in recent years. In this paper, we propose a solution for the task of brain tumor segmentation. To this end, we first introduce a method of enhancing an existing magnetic resonance imaging (MRI) dataset by generating synthetic computed tomography (CT) images. Then, we discuss a process of systematic optimization of a convolutional neural network (CNN) architecture that uses this enhanced dataset, in order to customize it for our task. Using publicly available datasets, we show that the proposed method outperforms similar existing methods.
-
ItemStreet Sign Recognition Using Histogram of Oriented Gradients and Artificial Neural Networks(MDPI, 2019-04)Street sign identification is an important problem in applications such as autonomous vehicle navigation and aids for individuals with vision impairments. It can be especially useful in instances where navigation techniques such as global positioning system (GPS) are not available. In this paper, we present a method of detection and interpretation of Malaysian street signs using image processing and machine learning techniques. First, we eliminate the background from an image to segment the region of interest (i.e., the street sign). Then, we extract the text from the segmented image and classify it. Finally, we present the identified text to the user as a voice notification. We also show through experimental results that the system performs well in real-time with a high level of accuracy. To this end, we use a database of Malaysian street sign images captured through an on-board camera.
-
ItemRegion-Specific Automated Feedback in Temporal Bone Surgery Simulation(IEEE, 2015)The use of virtual reality simulators for surgical training has gained popularity in recent years, with an ever increasing body of evidence supporting the benefits and validity of simulation-based training. However, a crucial component of effective skill acquisition has not been adequately addressed, namely the provision of timely performance feedback. The utility of a surgical simulator is limited if it still requires the presence of experts to guide trainees. Automated feedback that emulates the advise provided by experts is necessary to facilitate independent learning. We propose an automated system that provides region-specific feedback on surgical technique within a temporal bone surgery simulator. The design of this system allows easy transfer of feedback models to multiple temporal bone specimens in the simulator. The system was validated by an expert otologist and was found to provide highly accurate and timely feedback.
-
ItemPresentation of automated procedural guidance in surgical simulation: results of two randomised controlled trials(Cambridge University Press, 2018-03)OBJECTIVE: To investigate the effectiveness and usability of automated procedural guidance during virtual temporal bone surgery. METHODS: Two randomised controlled trials were performed to evaluate the effectiveness, for medical students, of two presentation modalities of automated real-time procedural guidance in virtual reality simulation: full and step-by-step visual presentation of drillable areas. Presentation modality effectiveness was determined through a comparison of participants' dissection quality, evaluated by a blinded otologist, using a validated assessment scale. RESULTS: While the provision of automated guidance on procedure improved performance (full presentation, p = 0.03; step-by-step presentation, p < 0.001), usage of the two different presentation modalities was vastly different (full presentation, 3.73 per cent; step-by-step presentation, 60.40 per cent). CONCLUSION: Automated procedural guidance in virtual temporal bone surgery is effective in improving trainee performance. Step-by-step presentation of procedural guidance was engaging, and therefore more likely to be used by the participants.
-
ItemA rotation and translation invariant method for 3D organ image classification using deep convolutional neural networks(PEERJ INC, 2019-03-04)Three-dimensional (3D) medical image classification is useful in applications such as disease diagnosis and content-based medical image retrieval. It is a challenging task due to several reasons. First, image intensity values are vastly different depending on the image modality. Second, intensity values within the same image modality may vary depending on the imaging machine and artifacts may also be introduced in the imaging process. Third, processing 3D data requires high computational power. In recent years, significant research has been conducted in the field of 3D medical image classification. However, most of these make assumptions about patient orientation and imaging direction to simplify the problem and/or work with the full 3D images. As such, they perform poorly when these assumptions are not met. In this paper, we propose a method of classification for 3D organ images that is rotation and translation invariant. To this end, we extract a representative two-dimensional (2D) slice along the plane of best symmetry from the 3D image. We then use this slice to represent the 3D image and use a 20-layer deep convolutional neural network (DCNN) to perform the classification task. We show experimentally, using multi-modal data, that our method is comparable to existing methods when the assumptions of patient orientation and viewing direction are met. Notably, it shows similarly high accuracy even when these assumptions are violated, where other methods fail. We also explore how this method can be used with other DCNN models as well as conventional classification approaches.
-
ItemThe Melbourne Mastoidectomy Scale: Validation of an end-product dissection scale for cortical mastoidectomy(WILEY, 2020-09)Introduction Cortical mastoidectomy is a common otolaryngology procedure and represents a compulsory part of otolaryngology training. As such, a specific validated assessment score is needed for the progression of competency‐based training in this procedure. Although multiple temporal bone dissection scales have been developed, they have all been validated for advanced temporal bone dissection including posterior tympanotomy, rather than the task of cortical mastoidectomy. Methods The Melbourne Mastoidectomy Scale, a 20‐item end‐product dissection scale to assess cortical mastoidectomy, was developed. The scale was validated using dissections by 30 participants (10 novice, 10 intermediate and 10 expert) on a virtual reality temporal bone simulator. All dissections were assessed independently by three blinded graders. Additionally, all procedures were graded with an abbreviated Welling Scale by one grader. Results There was high inter‐rater reliability between the three graders (r = .9210, P < .0001). There was a significant difference in scores between the three groups (P < .0001). Additionally, there was a large effect size between all three groups: the differences between the novice group and both the intermediate group (P = .0119, η2 = 0.2482) and expert group (P < .001, η2 = 0.6356) were significant. The difference between the intermediate group and expert group again had a large effect size (η2 = 0.3217), but was not significant. The Melbourne Mastoidectomy Scale correlated well with an abbreviated Welling Scale (r = .8485, P < .0001). Conclusion The Melbourne Mastoidectomy Scale offers a validated score for use in the assessment of cortical mastoidectomy.
-
ItemA deep learning based framework for the registration of three dimensional multi-modal medical images of the head(NATURE PORTFOLIO, 2021-01-21)Image registration is a fundamental task in image analysis in which the transform that moves the coordinate system of one image to another is calculated. Registration of multi-modal medical images has important implications for clinical diagnosis, treatment planning, and image-guided surgery as it provides the means of bringing together complimentary information obtained from different image modalities. However, since different image modalities have different properties due to their different acquisition methods, it remains a challenging task to find a fast and accurate match between multi-modal images. Furthermore, due to reasons such as ethical issues and need for human expert intervention, it is difficult to collect a large database of labelled multi-modal medical images. In addition, manual input is required to determine the fixed and moving images as input to registration algorithms. In this paper, we address these issues and introduce a registration framework that (1) creates synthetic data to augment existing datasets, (2) generates ground truth data to be used in the training and testing of algorithms, (3) registers (using a combination of deep learning and conventional machine learning methods) multi-modal images in an accurate and fast manner, and (4) automatically classifies the image modality so that the process of registration can be fully automated. We validate the performance of the proposed framework on CT and MRI images of the head obtained from a publicly available registration database.
-
ItemThe Construct Validity and Reliability of an Assessment Tool for Competency in Cochlear Implant Surgery(HINDAWI LTD, 2014)INTRODUCTION: We introduce a rating tool that objectively evaluates the skills of surgical trainees performing cochlear implant surgery. METHODS: Seven residents and seven experts performed cochlear implant surgery sessions from mastoidectomy to cochleostomy on a standardized virtual reality temporal bone. A total of twenty-eight assessment videos were recorded and two consultant otolaryngologists evaluated the performance of each participant using these videos. RESULTS: Interrater reliability was calculated using the intraclass correlation coefficient for both the global and checklist components of the assessment instrument. The overall agreement was high. The construct validity of this instrument was strongly supported by the significantly higher scores in the expert group for both components. CONCLUSION: Our results indicate that the proposed assessment tool for cochlear implant surgery is reliable, accurate, and easy to use. This instrument can thus be used to provide objective feedback on overall and task-specific competency in cochlear implantation.
-
ItemA Vision-Based Machine Learning Method for Barrier Access Control Using Vehicle License Plate Authentication(MDPI, 2020-06)Automatic vehicle license plate recognition is an essential part of intelligent vehicle access control and monitoring systems. With the increasing number of vehicles, it is important that an effective real-time system for automated license plate recognition is developed. Computer vision techniques are typically used for this task. However, it remains a challenging problem, as both high accuracy and low processing time are required in such a system. Here, we propose a method for license plate recognition that seeks to find a balance between these two requirements. The proposed method consists of two stages: detection and recognition. In the detection stage, the image is processed so that a region of interest is identified. In the recognition stage, features are extracted from the region of interest using the histogram of oriented gradients method. These features are then used to train an artificial neural network to identify characters in the license plate. Experimental results show that the proposed method achieves a high level of accuracy as well as low processing time when compared to existing methods, indicating that it is suitable for real-time applications.