Validation of active shape model techniques for intracochlear anatomy segmentation in computed tomography images.

Purpose: 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 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. Approach: Using 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 reliability. Results: Optimized 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. Conclusions: We 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.

Automatic Segmentation of Intracochlear Anatomy in MR Images Using a Weighted Active Shape Model.

There is evidence that cochlear MR signal intensity may be useful in prognosticating the risk of hearing loss after middle cranial fossa (MCF) resection of acoustic neuroma (AN), but the manual segmentation of this structure is difficult and prone to error. This hampers both large-scale retrospective studies and routine clinical use of this information. To address this issue, we present a fully automatic method that permits the segmentation of the intra-cochlear anatomy in MR images, which uses a weighted active shape model we have developed and validated to segment the intra-cochlear anatomy in CT images. We take advantage of a dataset for which both CT and MR images are available to validate our method on 132 ears in 66 high-resolution T2-weighted MR images. Using the CT segmentation as ground truth, we achieve a mean Dice (DSC) value of 0.81 and 0.79 for the scala tympani (ST) and the scala vestibuli (SV), which are the two main intracochlear structures.Clinical Relevance- The proposed method is accurate and fully automated for MR image segmentation. It can be used to support large retrospective studies that explore relations between MR signal in preoperative images and outcomes. It can also facilitate the routine and clinical use of this information.

Hybrid active shape and deep learning method for the accurate and robust segmentation of the intracochlear anatomy in clinical head CT and CBCT images.

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.

Insertion Depth for Optimized Positioning of Precurved Cochlear Implant Electrodes.

HYPOTHESIS: Generic guidelines for insertion depth of precurved electrodes are suboptimal for many individuals. BACKGROUND: Insertion depths that are too shallow result in decreased cochlear coverage, and ones that are too deep lift electrodes away from the modiolus and degrade the electro-neural interface. Guidelines for insertion depth are generically applied to all individuals using insertion depth markers on the array that can be referenced against anatomical landmarks. METHODS: To normalize our measurements, we determined the optimal position and insertion vector where a precurved array best fits the cochlea for each patient in an IRB-approved, N = 131 subject CT database. The distances from the most basal electrode on an optimally placed array to anatomical landmarks, including the round window (RW) and facial recess (FR), was measured for all patients. RESULTS: The standard deviations of the distance from the most basal electrode to the FR and RW are 0.65 mm and 0.26 mm, respectively. Owing to the high variability in FR distance, using the FR as a landmark to determine insertion depth results in >0.5 mm difference with ideal depth in 44% of cases. Alignment of either of the two most proximal RW markers with the RW would result in over-insertion failures for >80% of cases, whereas the use of the third, most medial marker would result in under-insertion in only 19% of cases. CONCLUSIONS: Normalized measurements using the optimized insertion vector show low variance in distance from the basal electrode position to the RW, thereby suggesting it as a better landmark for determining insertion depth than the FR.

Two-level Training of a 3d U-Net for Accurate Segmentation of the Intra-cochlear Anatomy in Head CTs with Limited Ground Truth Training Data.

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 image-guided 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.

Resource estimation in high performance medical image computing.

Medical imaging analysis processes often involve the concatenation of many steps (e.g., multi-stage scripts) to integrate and realize advancements from image acquisition, image processing, and computational analysis. With the dramatic increase in data size for medical imaging studies (e.g., improved resolution, higher throughput acquisition, shared databases), interesting study designs are becoming intractable or impractical on individual workstations and servers. Modern pipeline environments provide control structures to distribute computational load in high performance computing (HPC) environments. However, high performance computing environments are often shared resources, and scheduling computation across these resources necessitates higher level modeling of resource utilization. Submission of 'jobs' requires an estimate of the CPU runtime and memory usage. The resource requirements for medical image processing algorithms are difficult to predict since the requirements can vary greatly between different machines, different execution instances, and different data inputs. Poor resource estimates can lead to wasted resources in high performance environments due to incomplete executions and extended queue wait times. Hence, resource estimation is becoming a major hurdle for medical image processing algorithms to efficiently leverage high performance computing environments. Herein, we present our implementation of a resource estimation system to overcome these difficulties and ultimately provide users with the ability to more efficiently utilize high performance computing resources.