PurposeCochlear implants (CIs) have been shown to be highly effective restorative devices for patients suffering from severe-to-profound hearing loss. Hearing outcomes with CIs depend on electrode positions with respect to intracochlear anatomy. Intracochlear anatomy can only be directly visualized using high-resolution modalities, such as micro-computed tomography (μCT), which cannot be used in vivo. However, active shape models (ASM) have been shown to be robust and effective for segmenting intracochlear anatomy in large scale datasets of patient computed tomographies (CTs). We present an extended dataset of μCT specimens and aim to evaluate the ASM’s performance more comprehensively than has been previously possible.ApproachUsing a dataset of 16 manually segmented cochlea specimens on μCTs, we found parameters that optimize mean CT segmentation performance and then evaluate the effect of library size on the ASM. The optimized ASM was further evaluated on a clinical dataset of 134 CT images to assess method reliabilityResultsOptimized parameters lead to mean CT segmentation performance to 0.36 mm point-to-point error, 0.10 mm surface error, and 0.83 Dice score. Larger library sizes provide diminishing returns on segmentation performance and total variance captured by the ASM. We found our method to be clinically reliable with the main performance limitation that was found to be the candidate search process rather than model representation.ConclusionsWe have presented a comprehensive validation of the ASM for use in intracochlear anatomy segmentation. These results are critical to understand the limitations of the method for clinical use and for future development.
Cochlear Implants (CI) are a widely successful neural-prosthetic device for improving quality of life for individuals experiencing severe to profound hearing loss. A minimally invasive technique for inserting the CI electrode, percutaneous cochlear access, typically involves a surgical trajectory through the facial recess. Image-based surgical planning techniques are heavily reliant on accurate segmentation of the chorda tympani since it is one of the delineating structures of the facial recess. Furthermore, damage to this structure can lead to loss of taste for the patient. However, the chorda’s thin nature and the surrounding appearance of pneumatized bone pose difficulties when segmenting this structure in conventional CT. Our previous automatic method still leads to unacceptable inaccuracies in difficult images. In this work, we propose the use of a conditional generative adversarial network for automatic segmentation of this structure. We use a weakly supervised approach, leveraging a dataset of sixteen hand-labelled images and 130 weakly-labelled images acquired through automatic atlas-based techniques. Our resulting network displays a 49% increase in segmentation performance over our previous automatic method with a mean localization error of 0.49mm. Even in the worst case, our method still provides sub-millimeter localization errors of 0.82mm. These results are encouraging for potential use in clinical settings as safe trajectory planning typically involves 1 mm error margins to sensitive structures.
While state-of-the-art deep learning methods consistently provide the most accurate image segmentation results when sufficient training datasets are available, in some applications large datasets are difficult to acquire. For example, a model for inner ear structures can only be constructed by ex vivo specimen imaging modalities such as µCT. Constructing such datasets is costly and time consuming. Active shape models (ASM) have been a successful technique in medical image segmentation and require less extensive datasets for training. However, the ability of the ASM framework to capture complex shape variation is limited by representing variations across all global-pose-normalized training exemplars in a single, linear vector space. In this work, we describe a novel non-linear extension to the ASM in the form of a multi element ASMs. Instead of modelling shape from a single global pose as with the original ASM formulation, we capture differences in regional pose using a concept of multiple weighted ASMs which we call elements. Each element uses a unique set of landmark importance weights for use during the shape registration and model fitting process. Landmark weights are optimized to minimize the overall multi-element ASM’s fitting error on the training set shapes. We demonstrate the advantage of this approach in segmenting the labyrinth structure in the inner ear. We find that the multi element ASM consistently outperforms a traditional ASM on similar sample sizes, and multi-element ASMs trained on 10 samples outperform traditional ASMs trained with 15 samples. These results show the method’s potential advantages in applications that are limited by small shape libraries.
During cochlear implant (CI) surgical procedures, the surgeon inserts an electrode array into the patient’s cochlea to restore hearing sensation through auditory nerve stimulation. Due to the significant variability in cochlear anatomy from person to person, patient-customized CI surgery planning has the potential to improve the outcome of the CI procedure. For presurgery planning, accurate segmentation of intra-cochlear structures is essential. In this work, we investigate the performance of intra-cochlear segmentation algorithms as a function of variations in image acquisition parameters (i.e., resolution, blurring effect and noise level) that exist in clinical CT images. A dataset of preoperative μCT images of 11 cadaveric temporal bone specimens was used to generate 110 synthetic pseudo-CT images with varying resolution and filter parameters. An active shape model (ASM) based method was evaluated to segment the intra-cochlear structures in those pseudo-CT images. Our results show that the volume of the segmented structures is significantly and strongly correlated with both the resolution and the reconstruction filter strength of the synthetic pseudo-CT images. Recognizing this bias is important for clinicians who use these segmentations or take manual measurements of the cochlea from CT images for pre-surgical planning of CI procedures.
Purpose: Robust and accurate segmentation methods for the intracochlear anatomy (ICA) are a critical step in the image-guided cochlear implant programming process. We have proposed an active shape model (ASM)-based method and a deep learning (DL)-based method for this task, and we have observed that the DL method tends to be more accurate than the ASM method while the ASM method tends to be more robust.
Approach: We propose a DL-based U-Net-like architecture that incorporates ASM segmentation into the network. A quantitative analysis is performed on a dataset that consists of 11 cochlea specimens for which a segmentation ground truth is available. To qualitatively evaluate the robustness of the method, an experienced expert is asked to visually inspect and grade the segmentation results on a clinical dataset made of 138 image volumes acquired with conventional CT scanners and of 39 image volumes acquired with cone beam CT (CBCT) scanners. Finally, we compare training the network (1) first with the ASM results, and then fine-tuning it with the ground truth segmentation and (2) directly with the specimens with ground truth segmentation.
Results: Quantitative and qualitative results show that the proposed method increases substantially the robustness of the DL method while having only a minor detrimental effect (though not significant) on its accuracy. Expert evaluation of the clinical dataset shows that by incorporating the ASM segmentation into the DL network, the proportion of good segmentation cases increases from 60/177 to 119/177 when training only with the specimens and increases from 129/177 to 151/177 when pretraining with the ASM results.
Conclusions: A hybrid ASM and DL-based segmentation method is proposed to segment the ICA in CT and CBCT images. Our results show that combining DL and ASM methods leads to a solution that is both robust and accurate.
Cochlear implants (CIs) are neuroprosthetic devices that can improve hearing in patients with severe-to-profound hearing loss. Postoperatively, a CI device needs to be programmed by an audiologist to determine parameter settings that lead to the best outcomes. Our group has developed an image-guided cochlear implant programming (IGCIP) system to simplify this laborious post-programming procedure and improve hearing outcomes. IGCIP requires image processing techniques to analyze the location of the inserted electrode arrays (EAs) with respect to the intracochlear anatomy (ICA). An active shape model (ASM)-based method is currently in routine use in our IGCIP system for ICA segmentation. Recently, we have proposed a hybrid ASM/deep learning (DL) segmentation method that improves segmentation accuracy. In this work, we first evaluate the effect of this method on so-called distance-vs.-frequency curves (DVFs), which permit to visualize electrode interaction and are used to provide programming guidance. An expert evaluation study is then performed to manually configure the electrodes based on the DVFs and grade the quality of the electrode configurations derived from ASM and hybrid ASM/DL segmentations compared to the one derived from ground truth segmentation. Results we have obtained show that the hybrid ASM/DL segmentation technique tends to generate DVFs with smaller frequency error and distance error, and electrode configurations which are comparable to the existing ASM-based method.
Cochlear implants (CIs) have been shown to be highly effective restorative devices for patients suffering from severe-to-profound hearing loss. Hearing outcomes with CIs are dependent on the positions of the electrodes with respect to intracochlear anatomy. However, intra-cochlear anatomy can only be directly visualized using high resolution modalities such as μCT, which cannot be used in vivo. Despite this limitation, we have developed an active shape model approach for segmenting the intra-cochlear anatomy by leveraging the visible structures as landmarks. Still, due to the limited availability of μCT specimens, the segmentation method was validated on only a small dataset of 5 samples. In this study, we expand the dataset to 16 samples and provide a more comprehensive validation of the method’s performance with respect to model parameters and training set size. We found parameters that optimize mean surface segmentation performance to 0.11mm. Parameters that corresponded to tighter constraints generally led to smaller errors, and returns on segmentation performance begin diminishing after 11 samples, thus suggesting that the main performance bottleneck is due to the searching scheme rather than a limited training set size. These results are critical to understand the limitations of the method for clinical use and for future development.
Cochlear implants (CIs) use electrode arrays that are surgically inserted into the cochlea to treat patients with hearing loss. For CI recipients, sound bypasses the natural transduction mechanism and directly stimulates the neural regions, thus creating a sense of hearing. Post-operatively, CIs need to be programmed. Traditionally, this is done by an audiologist who is blind to the positions of the electrodes relative to the cochlea and only relies on the subjective response of the patient. Multiple programming sessions are usually needed, which can take a frustratingly long time. We have developed an imageguided cochlear implant programming (IGCIP) system to facilitate the process. In IGCIP, we segment the intra-cochlear anatomy and localize the electrode arrays in the patient’s head CT image. By utilizing their spatial relationship, we can suggest programming settings that can significantly improve hearing outcomes. To segment the intra-cochlear anatomy, we use an active shape model (ASM)-based method. Though it produces satisfactory results in most cases, sub-optimal segmentation still happens. As an alternative, herein we explore using a deep learning method to perform the segmentation task. Large image sets with accurate ground truth (in our case manual delineation) are typically needed to train a deep learning model for segmentation but such a dataset does not exist for our application. To tackle this problem, we use segmentations generated by the ASM-based method to pre-train the model and fine-tune it on a small image set for which accurate manual delineation is available. Using this method, we achieve better results than the ASM-based method.
Cholesteatomas are benign lesions that form in the middle ear (ME). They can cause debilitating side effects including hearing loss, recurrent ear infection and drainage, and balance disruption. The current approach for positively identifying cholesteatomas requires intraoperative visualization either by lifting the ear drum or transmitting an endoscope through the ear canal and tympanic membrane – procedures which are typically done in and operating room with the patient under general anesthesia. We are developing a novel endoscope that can be inserted trans-nasally and could potentially be used in an outpatient setting allowing clinicians to easily detect and visualize cholesteatomas and other middle ear conditions. A crucial part of designing this device is determining the degrees of freedom necessary to visualize the regions of interest in the middle ear space. To permit virtual evaluation of scope design, in this work we propose to create a library of models of the most difficult to visualize region of the middle ear, the retrotympanum (RT), which is located deep and posterior to the tympanic membrane. We have designed a semi-automated atlas-based approach for segmentation of the RT. Our approach required 2-3 minutes of manual interaction for each of 20 cases tested. Each result was verified to be accurate by an experienced otologist. These results show the method is efficient and accurate enough to be applied to a large scale dataset. We also created a statistical shape model from the resulting segmentations that can be used to synthesize new plausible RT shapes for comprehensive virtual evaluation of endoscope designs and show that it can represent new RT shapes with average errors of 0.5 mm.
Cochlear implants (CIs) use a surgically implanted electrode array to treat severe-to-profound sensorineural hearing loss. Audiologists program CIs by selecting a number of stimulation parameters for the CI processor to optimize hearing performance. It has been shown in previous research that audiologists arrive at CI settings that lead to a better hearing outcome when they are provided an estimate of which regions of the auditory nerve are being activated by each electrode for a patient. If the neural fibers could be localized, neural fiber models could be used to estimate activa tion in response to electrode activation for individual patients. However, the neural fibers are so small they are not visible in clinical images. In this project, our aim is to develop an active-shape model based solution to automatically localize the Internal Auditory Canal (IAC), which houses the auditory nerves and has borders that are visible in CT scans, to serve as a landmark for localizing the nerve fibers . Seven manually segmented IAC volumes were used to create and validate our method using a leave-one-out approach. We found that the mean surface errors of the dataset ranged from ~0.4 to ~1.2 CT voxels (0.13 mm to 0.37 mm). These results suggest that our IAC segmentation is highly accurate and could provide an excellent landmark for estimating fiber position.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.