Multi-Scale deep learning framework for cochlea localization, segmentation and analysis on clinical ultra-high-resolution CT images

Deep Learning Method for Rapid Simultaneous Multistructure Temporal Bone Segmentation

OBJECTIVE

To develop and validate a deep learning algorithm for the automated segmentation of key temporal bone structures from clinical computed tomography (CT) data sets.

STUDY DESIGN

Cross-sectional study.

SETTING

A total of 325 CT scans from a clinical database.

METHOD

A state-of-the-art deep learning (DL) algorithm (SwinUNETR) was used to train a prediction model for rapid segmentation of 9 key temporal bone structures in a data set of 325 clinical CTs. The data set was manually annotated by a specialist to serve as the ground truth. The data set was randomly split into training (n = 260) and testing (n = 65) sets. The model's performance was objectively assessed through external validation on the test set using metrics including Dice, Balanced accuracy, Hausdorff distances, and processing time.

RESULTS

The model achieved an average Dice coefficient of 0.87 for all structures, an average balanced accuracy of 0.94, an average Hausdorff distance of 0.79 mm, and an average processing time of 9.1 seconds per CT.

CONCLUSION

The present DL model for the automated simultaneous segmentation of multiple structures within the temporal bone from CTs achieved high accuracy according to currently commonly employed objective analysis. The results demonstrate the potential of the method to improve preoperative evaluation and intraoperative guidance in otologic surgery.

Radiation dose reduction and image quality improvement with ultra-high resolution temporal bone CT using deep learning-based reconstruction: An anatomical study

PURPOSE

The purpose of this study was to evaluate the achievable radiation dose reduction of an ultra-high resolution computed tomography (UHR-CT) scanner using deep learning reconstruction (DLR) while maintaining temporal bone image quality equal to or better than high-resolution CT (HR-CT).

MATERIALS AND METHODS

UHR-CT acquisitions were performed with variable tube voltages and currents at eight different dose levels (volumic CT dose index [CTDIvol] range: 4.6-79 mGy), 10242 matrix, and 0.25 mm slice thickness and reconstructed using DLR and hybrid iterative reconstruction (HIR) algorithms. HR-CT images were acquired using a standard protocol (120 kV/220 mAs; CTDI vol, 54.2 mGy, 5122 matrix, and 0.5 mm slice thickness). Two radiologists rated the image quality of seven structures using a five point confidence scale on six cadaveric temporal bone CTs. A global image quality score was obtained for each CT protocol by summing the image quality scores of all structures.

RESULTS

With DLR, UHR-CT at 120 kV/220 mAs (CTDIvol, 50.9 mGy) and 140 kV/220 mAs (CTDIvol, 79 mGy) received the highest global image quality scores (4.88 ± 0.32 [standard deviation (SD)] [range: 4-5] and 4.85 ± 0.35 [range: 4-5], respectively; P = 0.31), while HR-CT at 120 kV/220 mAs and UHR-CT at 120 kV/20 mAs received the lowest (i.e., 3.14 ± 0.75 [SD] [range: 2-5] and 2.97 ± 0.86 [SD] [range: 1-5], respectively; P = 0.14). All the DLR protocols had better image quality scores than HR-CT with HIR.

CONCLUSION

UHR-CT with DLR can be performed with up to a tenfold reduction in radiation dose compared to HR-CT with HIR while maintaining or improving image quality.

Improving rehabilitation of deaf patients by advanced imaging before cochlear implantation

INTRODUCTION

Cochlear implants have advanced the management of severe to profound deafness. However, there is a strong disparity in hearing performance after implantation from one patient to another. Moreover, there are several advanced kinds of imaging assessment before cochlear implantation. Microstructural white fiber degeneration can be studied with Diffusion weighted MRI (DWI) or tractography of the central auditory pathways. Functional MRI (fMRI) allows us to evaluate brain function, and CT or MRI segmentation to better detect inner ear anomalies.

OBJECTIVE

This literature review aims to evaluate how helpful pre-implantation anatomic imaging can be to predict hearing rehabilitation outcomes in deaf patients. These techniques include DWI and fMRI of the central auditory pathways, and automated labyrinth segmentation by CT scan, cone beam CT and MRI.

DESIGN

This systematic review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were selected by searching in PubMed and by checking the reference lists of relevant articles. Inclusion criteria were adults over 18, with unilateral or bilateral hearing loss, who had DWI acquisition or fMRI or CT/ Cone Beam CT/ MRI image segmentation.

RESULTS

After reviewing 172 articles, we finally included 51. Studies on DWI showed changes in the central auditory pathways affecting the white matter, extending to the primary and non-primary auditory cortices, even in sudden and mild hearing impairment. Hearing loss patients show a reorganization of brain activity in various areas, such as the auditory and visual cortices, as well as regions involved in language and emotions, according to fMRI studies. Deep Learning's automatic segmentation produces the best CT segmentation in just a few seconds. MRI segmentation is mainly used to evaluate fluid space of the inner ear and determine the presence of an endolymphatic hydrops.

CONCLUSION

Before cochlear implantation, a DWI with tractography can evaluate the central auditory pathways up to the primary and non-primary auditory cortices. This data is then used to generate predictions on the auditory rehabilitation of patients. A CT segmentation with systematic 3D reconstruction allow a better evaluation of cochlear malformations and predictable difficulties during surgery.

Variability in Manual Segmentation of Temporal Bone Structures in Cone Beam CT Images

PURPOSE

Manual segmentation of anatomical structures is the accepted "gold standard" for labeling structures in clinical images. However, the variability in manual segmentation of temporal bone structures in CBCT images of the temporal bone has not been systematically evaluated using multiple reviewers. Therefore, we evaluated the intravariability and intervariability of manual segmentation of inner ear structures in CBCT images of the temporal bone.

METHODS

Preoperative CBCTs scans of the inner ear were obtained from 10 patients who had undergone cochlear implant surgery. The cochlea, facial nerve, chorda tympani, mid-modiolar (MM) axis, and round window (RW) were manually segmented by five reviewers in two separate sessions that were at least 1 month apart. Interreviewer and intrareviewer variabilities were assessed using the Dice coefficient (DICE), volume similarity, mean Hausdorff Distance metrics, and visual review.

RESULTS

Manual segmentation of the cochlea was the most consistent within and across reviewers with a mean DICE of 0.91 (SD = 0.02) and 0.89 (SD = 0.01) respectively, followed by the facial nerve with a mean DICE of 0.83 (SD = 0.02) and 0.80 (SD = 0.03), respectively. The chorda tympani had the greatest amount of reviewer variability due to its thin size, and the location of the centroid of the RW and the MM axis were also quite variable between and within reviewers.

CONCLUSIONS

We observed significant variability in manual segmentation of some of the temporal bone structures across reviewers. This variability needs to be considered when interpreting the results in studies using one manual reviewer.

Landmark-based registration of a cochlear model to a human cochlea using conventional CT scans

Cochlear implants can provide an advanced treatment option to restore hearing. In standard pre-implant procedures, many factors are already considered, but it seems that not all underlying factors have been identified yet. One reason is the low quality of the conventional computed tomography images taken before implantation, making it difficult to assess these parameters. A novel method is presented that uses the Pietsch Model, a well-established model of the human cochlea, as well as landmark-based registration to address these challenges. Different landmark numbers and placements are investigated by visually comparing the mean error per landmark and the registrations' results. The landmarks on the first cochlear turn and the apex are difficult to discern on a low-resolution CT scan. It was possible to achieve a mean error markedly smaller than the image resolution while achieving a good visual fit on a cochlear segment and directly in the conventional computed tomography image. The employed cochlear model adjusts image resolution problems, while the effort of setting landmarks is markedly less than the segmentation of the whole cochlea. As a next step, the specific parameters of the patient could be extracted from the adapted model, which enables a more personalized implantation with a presumably better outcome.

In vivo depiction of cortical bone vascularization with ultra-high resolution-CT and deep learning algorithm reconstruction using osteoid osteoma as a model

PURPOSE

The purpose of this study was to evaluate the ability to depict in vivo bone vascularization using ultra-high-resolution (UHR) computed tomography (CT) with deep learning reconstruction (DLR) and hybrid iterative reconstruction algorithm, compared to simulated conventional CT, using osteoid osteoma as a model.

MATERIALS AND METHODS

Patients with histopathologically proven cortical osteoid osteoma who underwent UHR-CT between October 2019 and October 2022 were retrospectively included. Images were acquired with a 1024 × 1024 matrix and reconstructed with DLR and hybrid iterative reconstruction algorithm. To simulate conventional CT, images with a 512 × 512 matrix were also reconstructed. Two radiologists (R1, R2) independently evaluated the number of blood vessels entering the nidus and crossing the bone cortex, as well as vessel identification and image quality with a 5-point scale. Standard deviation (SD) of attenuation in the adjacent muscle and that of air were used as image noise and recorded.

RESULTS

Thirteen patients with 13 osteoid osteomas were included. There were 11 men and two women with a mean age of 21.8 ± 9.1 (SD) years. For both readers, UHR-CT with DLR depicted more nidus vessels (11.5 ± 4.3 [SD] (R1) and 11.9 ± 4.6 [SD] (R2)) and cortical vessels (4 ± 3.8 [SD] and 4.3 ± 4.1 [SD], respectively) than UHR-CT with hybrid iterative reconstruction (10.5 ± 4.3 [SD] and 10.4 ± 4.6 [SD], and 4.1 ± 3.8 [SD] and 4.3 ± 3.8 [SD], respectively) and simulated conventional CT (5.3 ± 2.2 [SD] and 6.4 ± 2.5 [SD], 2 ± 1.2 [SD] and 2.4 ± 1.6 [SD], respectively) (P < 0.05). UHR-CT with DLR provided less image noise than simulated conventional CT and UHR-CT with hybrid iterative reconstruction (P < 0.05). UHR-CT with DLR received the greatest score and simulated conventional CT the lowest score for vessel identification and image quality.

CONCLUSION

UHR-CT with DLR shows less noise than UHR-CT with hybrid iterative reconstruction and significantly improves cortical bone vascularization depiction compared to simulated conventional CT.

Machine learning framework for simulation of artifacts in paranasal sinuses diagnosis using CT images

In the medical field, diagnostic tools that make use of deep neural networks have reached a level of performance never before seen. A proper diagnosis of a patient's condition is crucial in modern medicine since it determines whether or not the patient will receive the care they need. Data from a sinus CT scan is uploaded to a computer and displayed on a high-definition monitor to give the surgeon a clear anatomical orientation before endoscopic sinus surgery. In this study, a unique method is presented for detecting and diagnosing paranasal sinus disorders using machine learning. The researchers behind the current study designed their own approach. To speed up diagnosis, one of the primary goals of our study is to create an algorithm that can accurately evaluate the paranasal sinuses in CT scans. The proposed technology makes it feasible to automatically cut down on the number of CT scan images that require investigators to manually search through them all. In addition, the approach offers an automatic segmentation that may be used to locate the paranasal sinus region and crop it accordingly. As a result, the suggested method dramatically reduces the amount of data that is necessary during the training phase. As a result, this results in an increase in the efficiency of the computer while retaining a high degree of performance accuracy. The suggested method not only successfully identifies sinus irregularities but also automatically executes the necessary segmentation without requiring any manual cropping. This eliminates the need for time-consuming and error-prone human labor. When tested with actual CT scans, the method in question was discovered to have an accuracy of 95.16 percent while retaining a sensitivity of 99.14 percent throughout.

Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT

PURPOSE

Imaging diagnosis of stapes fixation (SF) is challenging owing to a lack of definite evidence. We developed a comprehensive machine learning (ML) model to identify SF on ultra-high-resolution CT.

MATERIALS AND METHODS

We retrospectively enrolled 109 participants (143 ears) and divided them into the training set (115 ears) and test set (28 ears). Stapes mobility (SF or non-SF) was determined by surgical inspection. In the ML analysis, rectangular regions of interest were placed on consecutive axial slices in the training set. Radiomic features were extracted and fed into the training session. The test set was analyzed using 7 ML models (support vector machine, k nearest neighbor, decision tree, random forest, extra trees, eXtreme Gradient Boosting, and Light Gradient Boosting Machine) and by 2 dedicated neuroradiologists. Diagnostic performance (sensitivity, specificity and accuracy, with surgical findings as the reference) was compared between the radiologists and the optimal ML model by using the McNemar test.

RESULTS

The mean age of the participants was 42.3 ± 17.5 years. The Light Gradient Boosting Machine (LightGBM) model showed the highest sensitivity (0.83), specificity (0.81), accuracy (0.82) and area under the curve (0.88) for detecting SF among the 7 ML models. The neuroradiologists achieved good sensitivities (0.75 and 0.67), moderate-to-good specificities (0.63 and 0.56) and good accuracies (0.68 and 0.61). This model showed no statistical differences with the neuroradiologists (P values 0.289-1.000).

CONCLUSIONS

Compared to the neuroradiologists, the LightGBM model achieved competitive diagnostic performance in identifying SF, and has the potential to be a supportive tool in clinical practice.

Towards fully automated inner ear analysis with deep-learning-based joint segmentation and landmark detection framework

Automated analysis of the inner ear anatomy in radiological data instead of time-consuming manual assessment is a worthwhile goal that could facilitate preoperative planning and clinical research. We propose a framework encompassing joint semantic segmentation of the inner ear and anatomical landmark detection of helicotrema, oval and round window. A fully automated pipeline with a single, dual-headed volumetric 3D U-Net was implemented, trained and evaluated using manually labeled in-house datasets from cadaveric specimen ([Formula: see text]) and clinical practice ([Formula: see text]). The model robustness was further evaluated on three independent open-source datasets ([Formula: see text] scans) consisting of cadaveric specimen scans. For the in-house datasets, Dice scores of [Formula: see text], intersection-over-union scores of [Formula: see text] and average Hausdorff distances of [Formula: see text] and [Formula: see text] voxel units were achieved. The landmark localization task was performed automatically with an average localization error of [Formula: see text] voxel units. A robust, albeit reduced performance could be attained for the catalogue of three open-source datasets. Results of the ablation studies with 43 mono-parametric variations of the basal architecture and training protocol provided task-optimal parameters for both categories. Ablation studies against single-task variants of the basal architecture showed a clear performance benefit of coupling landmark localization with segmentation and a dataset-dependent performance impact on segmentation ability.

Automatic cochlear multimodal 3D image segmentation and analysis using atlas-model-based method

Objectives: To propose an automated fast cochlear segmentation, length, and volume estimation method from clinical 3D multimodal images which has a potential role in the choice of cochlear implant type, surgery planning, and robotic surgeries.

Methods: Two datasets from different countries were used. These datasets include 219 clinical 3D images of cochlea from 3 modalities: CT, CBCT, and MR. The datasets include different ages, genders, and types of cochlear implants. We propose an atlas-model-based method for cochlear segmentation and measurement based on high-resolution μCT model and A-value. The method was evaluated using 3D landmarks located by two experts.

Results: The average error was 0.61 ± 0.22 mm and the average time required to process an image was 5.21 ± 0.93 seconds (P<0.001). The volume of the cochlea ranged from 73.96 mm3 to 106.97 mm3 , the cochlear length ranged from 36.69 to 45.91 mm at the lateral wall and from 29.12 to 39.05 mm at the organ of Corti.

Discussion: We propose a method that produces nine different automated measurements of the cochlea: volume of scala tympani, volume of scala vestibuli, central lengths of the two scalae, the scala tympani lateral wall length, and the organ of Corti length in addition to three measurements related to A-value.

Conclusion: This automatic cochlear image segmentation and analysis method can help clinician process multimodal cochlear images in approximately 5 seconds using a simple computer. The proposed method is publicly available for free download as an extension for 3D Slicer software.

Applications of Artificial Intelligence in Temporal Bone Imaging: Advances and Future Challenges

The applications of artificial intelligence (AI) in temporal bone (TB) imaging have gained significant attention in recent years, revolutionizing the field of otolaryngology and radiology. Accurate interpretation of imaging features of TB conditions plays a crucial role in diagnosing and treating a range of ear-related pathologies, including middle and inner ear diseases, otosclerosis, and vestibular schwannomas. According to multiple clinical studies published in the literature, AI-powered algorithms have demonstrated exceptional proficiency in interpreting imaging findings, not only saving time for physicians but also enhancing diagnostic accuracy by reducing human error. Although several challenges remain in routinely relying on AI applications, the collaboration between AI and healthcare professionals holds the key to better patient outcomes and significantly improved patient care. This overview delivers a comprehensive update on the advances of AI in the field of TB imaging, summarizes recent evidence provided by clinical studies, and discusses future insights and challenges in the widespread integration of AI in clinical practice.

Variation in cochlear size: A systematic review

BACKGROUND

Advancements in imaging and implantation technology have invited reexamination of the classic teaching that the human cochlea maintains uniform size across demographics. Yet, studies yield conflicting results and relatively few broad systematic reviews have examined cochlear size variation.

PURPOSE

The purpose of this study is to quantify cochlear variability across eight different measurement categories and suggest normative values and ranges for each with consideration of disease state and gender where possible.

METHODS

A systematic search was conducted up to October 1, 2022, using the search terms "Cochlea/anatomy and histology"[Mesh]) AND 'size'" with filters "Humans" and "English" across three databases (PubMed, CINAHL, Medline). Further inclusion criteria involved reporting of numerical measurements in any of the eight included categories.

RESULTS

Of the 625 articles manually reviewed for relevance by title and abstract, 91 were selected for full-text review and 33 met all eligibility criteria. 5,791 cochleae were included and weighted means and ranges were calculated: "A" value (defined as the distance from the round window, through the modiolus, to the oppsite lateral wall) = 9.23 mm (8.43-10.4 mm, n = 2559); cochlear duct length (CDL) = 33.04 mm (range 28.2-36.4 mm, n = 2252); cochlear height = 5.14 mm (2.8-6.9 mm, n = 2098); the basal turn lumen diameter = 2.09 mm (1.7-2.2 mm, n = 617); "B" value (defined as perpendicular to "A" value and in the same plane) = 6.52 mm (5.73-6.9 mm, n = 908); width of the basal turn = 6.4 mm (6.22-6.86 mm, n = 356); height of the basal turn = 1.96 mm (1.77-2.56 mm, n = 204); length of the basal turn 21.87 mm (21.03-22.5 mm, n = 384).

CONCLUSION

A notable size range exists across the eight different cochlear parameters considered and we provide normative values for each measurement. Females tend to have smaller CDL and "A" value than males and the sensorineural hearing loss patients had smaller CDL and "A" value but larger cochlear height than the general population.

Brain image segmentation of the corpus callosum by combining Bi-Directional Convolutional LSTM and U-Net using multi-slice CT and MRI

BACKGROUND AND OBJECTIVE

Traditional disease diagnosis is usually performed by experienced physicians, but misdiagnosis or missed diagnosis still exists. Exploring the relationship between changes in the corpus callosum and multiple brain infarcts requires extracting corpus callosum features from brain image data, which requires addressing three key issues. (1) automation, (2) completeness, and (3) accuracy. Residual learning can facilitate network training, Bi-Directional Convolutional LSTM (BDC-LSTM) can exploit interlayer spatial dependencies, and HDC can expand the receptive domain without losing resolution.

METHODS

In this paper, we propose a segmentation method by combining BDC-LSTM and U-Net to segment the corpus callosum from multiple angles of brain images based on computed tomography (CT) and magnetic resonance imaging (MRI) in which two types of sequence, namely T2-weighted imaging as well as the Fluid Attenuated Inversion Recovery (Flair), were utilized. The two-dimensional slice sequences are segmented in the cross-sectional plane, and the segmentation results are combined to obtain the final results. Encoding, BDC- LSTM, and decoding include convolutional neural networks. The coding part uses asymmetric convolutional layers of different sizes and dilated convolutions to get multi-slice information and extend the convolutional layers' perceptual field.

RESULTS

This paper uses BDC-LSTM between the encoding and decoding parts of the algorithm. On the image segmentation of the brain in multiple cerebral infarcts dataset, accuracy rates of 0.876, 0.881, 0.887, and 0.912 were attained for the intersection of union (IOU), dice similarity coefficient (DS), sensitivity (SE), and predictive positivity value (PPV). The experimental findings demonstrate that the algorithm outperforms its rivals in accuracy.

CONCLUSION

This paper obtained segmentation results for three images using three models, ConvLSTM, Pyramid-LSTM, and BDC-LSTM, and compared them to verify that BDC-LSTM is the best method to perform the segmentation task for faster and more accurate detection of 3D medical images. We improve the convolutional neural network segmentation method to obtain medical images with high segmentation accuracy by solving the over-segmentation problem.

Accuracy of radiological prediction of electrode position with otological planning software and implications of high-resolution imaging

OBJECTIVES

In cochlear implantation, preoperative prediction of electrode position has recently gained increasing attention. Currently, planning is usually done by multislice CT (MSCT). However, flat-panel volume CT (fpVCT) and its secondary reconstructions (fpVCTSECO) allow for more precise visualization of the cochlea. Combined with a newly developed otological planning software, the position of every single contact can be effectively predicted. In this study it was investigated how accurately radiological prediction forecasts the postoperative electrode localization and whether higher image resolution is advantageous.

METHODS

Utilizing otological planning software (OTOPLAN®) and different clinical imaging modalities (MSCT, fpVCT and fpVCTSECO) the electrode localization [angular insertion depth (AID)] and respective contact frequencies were predicted preoperatively and examined postoperatively. Furthermore, inter-electrode-distance (IED) and inter-electrode-frequency difference (IEFD) were evaluated postoperatively.

RESULTS

Measurements revealed a preoperative overestimation of AID. Corresponding frequencies were also miscalculated. Determination of IED and IEFD revealed discrepancies at the transition from the basal to the middle turn and round window to the basal turn. All predictions and discrepancies were lowest when using fpVCTSECO.

CONCLUSION

The postoperative electrode position can be predicted quite accurately using otological planning software. However, because of several potential misjudgments, high-resolution imaging, such as offered by fpVCTSECO, should be used pre- and postoperatively.

Application of UNETR for automatic cochlear segmentation in temporal bone CTs

OBJECTIVE

To investigate the feasibility of a deep learning method based on a UNETR model for fully automatic segmentation of the cochlea in temporal bone CT images.

METHODS

The normal temporal bone CTs of 77 patients were used in 3D U-Net and UNETR model automatic cochlear segmentation. Tests were performed on two types of CT datasets and cochlear deformity datasets.

RESULTS

Through training the UNETR model, when batch_size=1, the Dice coefficient of the normal cochlear test set was 0.92, which was higher than that of the 3D U-Net model; on the GE 256 CT, SE-DS CT and Cochlear Deformity CT dataset tests, the Dice coefficients were 0.91, 0.93, 0 93, respectively.

CONCLUSION

According to the anatomical characteristics of the temporal bone, the use of the UNETR model can achieve fully automatic segmentation of the cochlea and obtain an accuracy close to manual segmentation. This method is feasible and has high accuracy.

Coordinate-based fast lightweight path search algorithm for electromagnetic navigation bronchoscopy

Electromagnetic navigation bronchoscopy (ENB) uses electromagnetic positioning technology to guide the bronchoscope to accurately and quickly reach the lesion along the planned path. However, enormous data in high-resolution lung computed tomography (CT) and the complex structure of multilevel branching bronchial tree make fast path search challenging for path planning. We propose a coordinate-based fast lightweight path search (CPS) algorithm for ENB. First, the centerline is extracted from the bronchial tree by applying topological thinning. Then, Euclidean-distance-based coordinate search is applied. The centerline points are represented by their coordinates, and adjacent points along the navigation path are selected considering the shortest Euclidean distance to the target on the centerline nearest the lesion. From the top of the trachea centerline, search is repeated until reaching the target. In 50 high-resolution lung CT images acquired from five scanners, the CPS algorithm achieves accuracy, average search time, and average memory consumption of 100%, 88.5 ms, and 166.0 MB, respectively, reducing search time by 74.3% and 73.1% and memory consumption by 83.3% and 83.0% compared with Dijkstra and A* algorithms, respectively. CPS algorithm is suitable for path search in multilevel branching bronchial tree navigation based on high-resolution lung CT images.

Endolymphatic space is age-dependent

Knowledge of the physiological endolymphatic space (ELS) is necessary to estimate endolymphatic hydrops (ELH) in patients with vestibulocochlear syndromes. Therefore, the current study investigated age-dependent changes in the ELS of participants with normal vestibulocochlear testing. Sixty-four ears of 32 participants with normal vestibulocochlear testing aged between 21 and 75 years (45.8 ± 17.2 years, 20 females, 30 right-handed, two left-handed) were examined by intravenous delayed gadolinium-enhanced magnetic resonance imaging of the inner ear (iMRI). Clinical diagnostics included neuro-otological assessment, video-oculography during caloric stimulation, and head-impulse test. iMRI data analysis provided semi-quantitative visual grading and automatic algorithmic quantitative segmentation of ELS volume (3D, mm³) using a deep learning-based segmentation of the inner ear's total fluid space (TFS) and volumetric local thresholding, as described earlier. As a result, following a 4-point ordinal scale, a mild ELH (grade 1) was found in 21/64 (32.8%) ears uni- or bilaterally in either cochlear, vestibulum, or both. Age and ELS were found to be positively correlated for the inner ear (r(64) = 0.33, p < 0.01), and vestibulum (r(64) = 0.25, p < 0.05). For the cochlea, the values correlated positively without reaching significance (r(64) = 0.21). In conclusion, age-dependent increases of the ELS should be considered when evaluating potential ELH in single subjects and statistical group comparisons.

A Web-Based Automated Image Processing Research Platform for Cochlear Implantation-Related Studies

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.

CT-based radiomics in predicting pathological response in non-small cell lung cancer patients receiving neoadjuvant immunotherapy

Objectives

In radiomics, high-throughput algorithms extract objective quantitative features from medical images. In this study, we evaluated CT-based radiomics features, clinical features, in-depth learning features, and a combination of features for predicting a good pathological response (GPR) in non-small cell lung cancer (NSCLC) patients receiving immunotherapy-based neoadjuvant therapy (NAT).

Materials and methods

We reviewed 62 patients with NSCLC who received surgery after immunotherapy-based NAT and collected clinicopathological data and CT images before and after immunotherapy-based NAT. A series of image preprocessing was carried out on CT scanning images: tumor segmentation, conventional radiomics feature extraction, deep learning feature extraction, and normalization. Spearman correlation coefficient, principal component analysis (PCA), and least absolute shrinkage and selection operator (LASSO) were used to screen features. The pretreatment traditional radiomics combined with clinical characteristics (before_rad_cil) model and pretreatment deep learning characteristics (before_dl) model were constructed according to the data collected before treatment. The data collected after NAT created the after_rad_cil model and after_dl model. The entire model was jointly constructed by all clinical features, conventional radiomics features, and deep learning features before and after neoadjuvant treatment. Finally, according to the data obtained before and after treatment, the before_nomogram and after_nomogram were constructed.

Results

In the before_rad_cil model, four traditional radiomics features (“original_shape_flatness,” “wavelet hhl_firer_skewness,” “wavelet hlh_firer_skewness,” and “wavelet lll_glcm_correlation”) and two clinical features (“gender” and “N stage”) were screened out to predict a GPR. The average prediction accuracy (ACC) after modeling with k-nearest neighbor (KNN) was 0.707. In the after_rad_cil model, nine features predictive of GPR were obtained after feature screening, among which seven were traditional radiomics features: “exponential_firer_skewness,” “exponential_glrlm_runentropy,” “log- sigma-5-0-mm-3d_firer_kurtosis,” “logarithm_skewness,” “original_shape_elongation,” “original_shape_brilliance,” and “wavelet llh_glcm_clustershade”; two were clinical features: “after_CRP” and “after lymphocyte percentage.” The ACC after modeling with support vector machine (SVM) was 0.682. The before_dl model and after_dl model were modeled by SVM, and the ACC was 0.629 and 0.603, respectively. After feature screening, the entire model was constructed by multilayer perceptron (MLP), and the ACC of the GPR was the highest, 0.805. The calibration curve showed that the predictions of the GPR by the before_nomogram and after_nomogram were in consensus with the actual GPR.

Conclusion

CT-based radiomics has a good predictive ability for a GPR in NSCLC patients receiving immunotherapy-based NAT. Among the radiomics features combined with the clinicopathological information model, deep learning feature model, and the entire model, the entire model had the highest prediction accuracy.

A review on AI-based medical image computing in head and neck surgery

Head and neck surgery is a fine surgical procedure with a complex anatomical space, difficult operation and high risk. Medical image computing (MIC) that enables accurate and reliable preoperative planning is often needed to reduce the operational difficulty of surgery and to improve patient survival. At present, artificial intelligence, especially deep learning, has become an intense focus of research in MIC. In this study, the application of deep learning-based MIC in head and neck surgery is reviewed. Relevant literature was retrieved on the Web of Science database from January 2015 to May 2022, and some papers were selected for review from mainstream journals and conferences, such as IEEE Transactions on Medical Imaging, Medical Image Analysis, Physics in Medicine and Biology, Medical Physics, MICCAI, etc. Among them, 65 references are on automatic segmentation, 15 references on automatic landmark detection, and eight references on automatic registration. In the elaboration of the review, first, an overview of deep learning in MIC is presented. Then, the application of deep learning methods is systematically summarized according to the clinical needs, and generalized into segmentation, landmark detection and registration of head and neck medical images. In segmentation, it is mainly focused on the automatic segmentation of high-risk organs, head and neck tumors, skull structure and teeth, including the analysis of their advantages, differences and shortcomings. In landmark detection, the focus is mainly on the introduction of landmark detection in cephalometric and craniomaxillofacial images, and the analysis of their advantages and disadvantages. In registration, deep learning networks for multimodal image registration of the head and neck are presented. Finally, their shortcomings and future development directions are systematically discussed. The study aims to serve as a reference and guidance for researchers, engineers or doctors engaged in medical image analysis of head and neck surgery.

A review on the application of deep learning for CT reconstruction, bone segmentation and surgical planning in oral and maxillofacial surgery

Computer-assisted surgery (CAS) allows clinicians to personalize treatments and surgical interventions and has therefore become an increasingly popular treatment modality in maxillofacial surgery. The current maxillofacial CAS consists of three main steps: (1) CT image reconstruction, (2) bone segmentation, and (3) surgical planning. However, each of these three steps can introduce errors that can heavily affect the treatment outcome. As a consequence, tedious and time-consuming manual post-processing is often necessary to ensure that each step is performed adequately. One way to overcome this issue is by developing and implementing neural networks (NNs) within the maxillofacial CAS workflow. These learning algorithms can be trained to perform specific tasks without the need for explicitly defined rules. In recent years, an extremely large number of novel NN approaches have been proposed for a wide variety of applications, which makes it a difficult task to keep up with all relevant developments. This study therefore aimed to summarize and review all relevant NN approaches applied for CT image reconstruction, bone segmentation, and surgical planning. After full text screening, 76 publications were identified: 32 focusing on CT image reconstruction, 33 focusing on bone segmentation and 11 focusing on surgical planning. Generally, convolutional NNs were most widely used in the identified studies, although the multilayer perceptron was most commonly applied in surgical planning tasks. Moreover, the drawbacks of current approaches and promising research avenues are discussed.

Deep Learning Approaches for Automatic Localization in Medical Images

Recent revolutionary advances in deep learning (DL) have fueled several breakthrough achievements in various complicated computer vision tasks. The remarkable successes and achievements started in 2012 when deep learning neural networks (DNNs) outperformed the shallow machine learning models on a number of significant benchmarks. Significant advances were made in computer vision by conducting very complex image interpretation tasks with outstanding accuracy. These achievements have shown great promise in a wide variety of fields, especially in medical image analysis by creating opportunities to diagnose and treat diseases earlier. In recent years, the application of the DNN for object localization has gained the attention of researchers due to its success over conventional methods, especially in object localization. As this has become a very broad and rapidly growing field, this study presents a short review of DNN implementation for medical images and validates its efficacy on benchmarks. This study presents the first review that focuses on object localization using the DNN in medical images. The key aim of this study was to summarize the recent studies based on the DNN for medical image localization and to highlight the research gaps that can provide worthwhile ideas to shape future research related to object localization tasks. It starts with an overview on the importance of medical image analysis and existing technology in this space. The discussion then proceeds to the dominant DNN utilized in the current literature. Finally, we conclude by discussing the challenges associated with the application of the DNN for medical image localization which can drive further studies in identifying potential future developments in the relevant field of study.

IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space

Background

In-vivo MR-based high-resolution volumetric quantification methods of the endolymphatic hydrops (ELH) are highly dependent on a reliable segmentation of the inner ear's total fluid space (TFS). This study aimed to develop a novel open-source inner ear TFS segmentation approach using a dedicated deep learning (DL) model.

Methods

The model was based on a V-Net architecture (IE-Vnet) and a multivariate (MR scans: T1, T2, FLAIR, SPACE) training dataset (D1, 179 consecutive patients with peripheral vestibulocochlear syndromes). Ground-truth TFS masks were generated in a semi-manual, atlas-assisted approach. IE-Vnet model segmentation performance, generalizability, and robustness to domain shift were evaluated on four heterogenous test datasets (D2-D5, n = 4 × 20 ears).

Results

The IE-Vnet model predicted TFS masks with consistently high congruence to the ground-truth in all test datasets (Dice overlap coefficient: 0.9 ± 0.02, Hausdorff maximum surface distance: 0.93 ± 0.71 mm, mean surface distance: 0.022 ± 0.005 mm) without significant difference concerning side (two-sided Wilcoxon signed-rank test, p>0.05), or dataset (Kruskal-Wallis test, p>0.05; post-hoc Mann-Whitney U, FDR-corrected, all p>0.2). Prediction took 0.2 s, and was 2,000 times faster than a state-of-the-art atlas-based segmentation method.

Conclusion

IE-Vnet TFS segmentation demonstrated high accuracy, robustness toward domain shift, and rapid prediction times. Its output works seamlessly with a previously published open-source pipeline for automatic ELS segmentation. IE-Vnet could serve as a core tool for high-volume trans-institutional studies of the inner ear. Code and pre-trained models are available free and open-source under https://github.com/pydsgz/IEVNet.

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.

Measuring 3D Cochlear Duct Length on MRI: Is It Accurate and Reliable?

BACKGROUND AND PURPOSE

Prior studies have evaluated cochlear length using CT to select the most suitable cochlear implants and obtain patient-specific anatomy. This study aimed to test the accuracy and reliability of cochlear lateral wall length measurements using 3D MR imaging.

MATERIALS AND METHODS

Two observers measured the cochlear lateral wall length of 35 patients (21 men) with postlingual hearing loss using CT and MR imaging. The intraclass correlation coefficient (with 95% confidence intervals) was used to evaluate intraobserver and interobserver reliability for the 3D cochlear measurements.

RESULTS

The mean age of the participants was 39.85 (SD, 16.60) years. Observer 1 measured the mean lateral wall length as 41.52 (SD, 2.25) mm on CT and 41.44 (SD, 2.18) mm on MR imaging, with a mean difference of 0.08 mm (95% CI, -0.11 to 0.27 mm), while observer 2 measured the mean lateral wall length as 41.74 (SD, 2.69) mm on CT and 42.34 (SD, 2.53) mm on MR imaging, with a mean difference of -0.59 mm (95% CI, -1.00 to -0.20 mm). An intraclass correlation coefficient value of 0.90 (95% CI, 0.84-0.94) for CT and 0.69 (95% CI, 0.46-0.82) for MR imaging was obtained for the interobserver reliability for the full-turn cochlear lateral wall length.

CONCLUSIONS

CT-based 3D cochlear measurements show excellent intraobserver and interobserver reliability, while MR imaging-based lateral wall length measurements have good-to-excellent intraobserver reliability and moderate interobserver reliability. These results corroborate the use of CT for 3D cochlear measurements as a reference method and demonstrate MR imaging to be an alternative acquisition technique with comparably reliable results.

Computational Audiology: New Approaches to Advance Hearing Health Care in the Digital Age

The global digital transformation enables computational audiology for advanced clinical applications that can reduce the global burden of hearing loss. In this article, we describe emerging hearing-related artificial intelligence applications and argue for their potential to improve access, precision, and efficiency of hearing health care services. Also, we raise awareness of risks that must be addressed to enable a safe digital transformation in audiology. We envision a future where computational audiology is implemented via interoperable systems using shared data and where health care providers adopt expanded roles within a network of distributed expertise. This effort should take place in a health care system where privacy, responsibility of each stakeholder, and patients' safety and autonomy are all guarded by design.

Bayesian logistic shape model inference: Application to cochlear image segmentation

Incorporating shape information is essential for the delineation of many organs and anatomical structures in medical images. While previous work has mainly focused on parametric spatial transformations applied to reference template shapes, in this paper, we address the Bayesian inference of parametric shape models for segmenting medical images with the objective of providing interpretable results. The proposed framework defines a likelihood appearance probability and a prior label probability based on a generic shape function through a logistic function. A reference length parameter defined in the sigmoid controls the trade-off between shape and appearance information. The inference of shape parameters is performed within an Expectation-Maximisation approach in which a Gauss-Newton optimization stage provides an approximation of the posterior probability of the shape parameters. This framework is applied to the segmentation of cochlear structures from clinical CT images constrained by a 10-parameter shape model. It is evaluated on three different datasets, one of which includes more than 200 patient images. The results show performances comparable to supervised methods and better than previously proposed unsupervised ones. It also enables an analysis of parameter distributions and the quantification of segmentation uncertainty, including the effect of the shape model.

Emerging artificial intelligence applications in otological imaging

PURPOSE OF REVIEW

To highlight the recent literature on artificial intelligence (AI) pertaining to otological imaging and to discuss future directions, obstacles and opportunities.

RECENT FINDINGS

The main themes in the recent literature centre around automated otoscopic image diagnosis and automated image segmentation for application in virtual reality surgical simulation and planning. Other applications that have been studied include identification of tinnitus MRI biomarkers, facial palsy analysis, intraoperative augmented reality systems, vertigo diagnosis and endolymphatic hydrops ratio calculation in Meniere's disease. Studies are presently at a preclinical, proof-of-concept stage.

SUMMARY

The recent literature on AI in otological imaging is promising and demonstrates the future potential of this technology in automating certain imaging tasks in a healthcare environment of ever-increasing demand and workload. Some studies have shown equivalence or superiority of the algorithm over physicians, albeit in narrowly defined realms. Future challenges in developing this technology include the compilation of large high quality annotated datasets, fostering strong collaborations between the health and technology sectors, testing the technology within real-world clinical pathways and bolstering trust among patients and physicians in this new method of delivering healthcare.

Fully Automated Measurement of Cochlear Duct Length From Clinical Temporal Bone Computed Tomography

OBJECTIVES/HYPOTHESIS

To present and validate a novel fully automated method to measure cochlear dimensions, including cochlear duct length (CDL).

STUDY DESIGN

Cross-sectional study.

METHODS

The computational method combined 1) a deep learning (DL) algorithm to segment the cochlea and otic capsule and 2) geometric analysis to measure anti-modiolar distances from the round window to the apex. The algorithm was trained using 165 manually segmented clinical computed tomography (CT). A Testing group of 159 CTs were then measured for cochlear diameter and width (A- and B-values) and CDL using the automated system and compared against manual measurements. The results were also compared with existing approaches and historical data. In addition, pre- and post-implantation scans from 27 cochlear implant recipients were studied to compare predicted versus actual array insertion depth.

RESULTS

Measurements were successfully obtained in 98.1% of scans. The mean CDL to 900° was 35.52 mm (SD, 2.06; range, [30.91-40.50]), the mean A-value was 8.88 mm (0.47; [7.67-10.49]), and mean B-value was 6.38 mm (0.42; [5.16-7.38]). The R² fit of the automated to manual measurements was 0.87 for A-value, 0.70 for B-value, and 0.71 for CDL. For anti-modiolar arrays, the distance between the imaged and predicted array tip location was 0.57 mm (1.25; [0.13-5.28]).

CONCLUSION

Our method provides a fully automated means of cochlear analysis from clinical CTs. The distribution of CDL, dimensions, and cochlear quadrant lengths is similar to those from historical data. This approach requires no radiographic experience and is free from user-related variation.

LEVEL OF EVIDENCE

3 Laryngoscope, 2021.

Precise segmentation of non-enhanced computed tomography in patients with ischemic stroke based on multi-scale U-Net deep network model

BACKGROUND AND OBJECTIVE

Acute ischemic stroke requires timely diagnosis and thrombolytic therapy, but it is difficult to locate and quantify the lesion site manually. The purpose of this study was to explore a more rapid and effective method for automatic image segmentation of acute ischemic stroke.

METHODS

The image features of 30 stroke patients were segmented from non-enhanced computed tomography (CT) images using a multi-scale U-Net deep network model. The Dice loss function training model was used to counter the similar imbalance problem in the data. The difference was compared between manual segmentation and automatic segmentation.

RESULTS

The Dice similarity coefficient based on multi-scale convolution U-Net network segmentation was 0.86±0.04, higher than the Dice based on classic U-Net (0.81±0.07, P=0.001). The lesion contour of automatic segmentation based on multi-scale U-Net was very close to manual segmentation. The error of lesion area is 1.28±0.59 mm², and the Pearson correlation coefficient was r=0.986 (P<0.01). The motion time of automatic segmentation is less than 20 ms.

CONCLUSIONS

Multi-scale U-Net deep network model can effectively segment ischemic stroke lesions in non-enhanced CT and meet real-time clinical requirements.

Comprehensive Analysis of Factors Affecting Cochlear Size: A Systematic Review and Meta-analysis

OBJECTIVES

To determine the cochlea's average size in humans and evaluate the relationships between certain covariates and cochlear size.

METHODS

A systematic search on articles on cochlear size and published in English was conducted using Cochrane, PubMed, Web of Science, and Scopus databases up to September 15, 2020. Data were pooled using random-effects with three models. The effect of demographic, clinical, and measurement-related parameters was specifically analyzed. Meta-regression and subgroup analyses were conducted. The overall effect estimation was made for outcomes.

RESULTS

The meta-analysis included 4,708 cochleae from 56 studies. The overall length of the organ of Corti was 32.94 mm (95% confidence interval [CI]: 32.51-33.38). The first and second models revealed that age, gender, country, continent, measurement method (direct, indirect), measured structure ("A" value, cochlear lateral wall), origin (in vivo, in vitro), and type (histology specimens, plastic casts, imaging) of the cochlear material did not affect the cochlear size. However, study populations (general population, patients with a cochlear implant, and patients with congenital sensorineural hearing loss [CSNHL]) were found to affect the outcomes. Compared to the other populations, patients with CSNHL had shorter cochleae. Therefore, we developed a third model and found that the general population and patients with cochlear implants did not differ in cochlear size.

CONCLUSION

This meta-analysis investigated the factors that could affect the cochlear size and found that patients with CSNHL had significantly shorter cochleae, whereas other covariates had no significant effect. Laryngoscope, 2021.

Mapping Cochlear Duct Length to Electrically Evoked Compound Action Potentials in Cochlear Implantation

OBJECTIVE

Objective measurements may assist in indicating cochlear implants and in predicting outcomes of cochlear implantation surgery. Using electrically evoked compound action potentials (ECAP), information about the function of the auditory nerve can be obtained by analyzing responses to electrical stimulation transmitted and derived by the recording electrode. The aim of this study was to determine whether ECAP characteristics differ depending on the stimulated intracochlear region and the size of the cochlea.

STUDY DESIGN

Retrospective cohort study.

SETTING

University Medical center, tertiary academic referral center.

PATIENTS

Patients undergoing cochlear implant surgery between 2015 and 2018.

INTERVENTION

Cochlear implantation with FLEXsoft electrode arrays (length 31.5 mm, 12 stimulating channels).

MAIN OUTCOME MEASURES

The cochlear duct length (CDL) and the cochlear coverage (CC) were measured using a new computed tomography-based software and correlated to the postoperative speech performance. Additionally, ECAP were measured and associated to the CDL.

RESULTS

A total of 59 ears of 53 cochlear implant users with a mean age of 63.6 (SD 14.9) years were included. The mean estimated CDL was 35.0 (SD 2.2) mm. The mean CC was 90.3% (SD 5.5%). A total of 4,873 ECAP were measured. A statistically significant, moderate, negative correlation between the ECAP slope and the site of stimulation was found (r = -0.29, 95% confidence interval: -0.32 to -0.27, p < 0.0001). No correlation between the CC and the speech performance was found (r = -0.08, 95% confidence interval: -0.33 to 0.18 p = 0.52).

CONCLUSION

ECAP slopes seem to be a reliable tool to identify the electrode's position inside the cochlea and also showed correlations to the anatomy of the patient. A combination of objective measurements such as anatomical parameters and ECAPs are helpful to assist the postoperative fitting and are promising tools to improve patient care.

Practicable assessment of cochlear size and shape from clinical CT images

There is considerable interpersonal variation in the size and shape of the human cochlea, with evident consequences for cochlear implantation. The ability to characterize a specific cochlea, from preoperative computed tomography (CT) images, would allow the clinician to personalize the choice of electrode, surgical approach and postoperative programming. In this study, we present a fast, practicable and freely available method for estimating cochlear size and shape from clinical CT. The approach taken is to fit a template surface to the CT data, using either a statistical shape model or a locally affine deformation (LAD). After fitting, we measure cochlear size, duct length and a novel measure of basal turn non-planarity, which we suggest might correlate with the risk of insertion trauma. Gold-standard measurements from a convenience sample of 18 micro-CT scans are compared with the same quantities estimated from low-resolution, noisy, pseudo-clinical data synthesized from the same micro-CT scans. The best results were obtained using the LAD method, with an expected error of 8-17% of the gold-standard sample range for non-planarity, cochlear size and duct length.

Automatic segmentation of temporal bone structures from clinical conventional CT using a CNN approach

BACKGROUND

Automatic segmentation of temporal bone structures from patients' conventional computed tomography (CT) data plays an important role in the image-guided cochlear implant surgery. Existing convolutional neural network approaches have difficulties in segmenting such small tubular structures.

METHODS

We propose a light-weight three-dimensional convolutional neural network referred to as W-Net to achieve multiobjective segmentation of temporal bone structures including the cochlear labyrinth, ossicular chain and facial nerve from conventional temporal bone CT images. Data augmentation with morphological enhancement is proposed to increase the segmentation accuracy of small tubular structures. Evaluation against the state-of-the-art methods is performed.

RESULTS

Our method achieved mean Dice similarity coefficients (DSCs) of 0.90, 0.85 and 0.77 for the cochlear labyrinth, ossicular chain and facial nerve, respectively. These results were also close to the DSCs between human expert annotators (0.91, 0.91 and 0.72).

CONCLUSIONS

Our method achieves human-level accuracy in the segmentation of the cochlear labyrinth, ossicular chain and facial nerve.

Deep learning for the fully automated segmentation of the inner ear on MRI

Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automated segmentation of the inner ear in MRI, a 3D U-net was trained on 944 MRI scans with manually segmented inner ears as reference standard. The model was validated on an independent, multicentric dataset consisting of 177 MRI scans from three different centers. The model was also evaluated on a clinical validation set containing eight MRI scans with severe changes in the morphology of the labyrinth. The 3D U-net model showed precise Dice Similarity Coefficient scores (mean DSC-0.8790) with a high True Positive Rate (91.5%) and low False Discovery Rate and False Negative Rates (14.8% and 8.49% respectively) across images from three different centers. The model proved to perform well with a DSC of 0.8768 on the clinical validation dataset. The proposed auto-segmentation model is equivalent to human readers and is a reliable, consistent, and efficient method for inner ear segmentation, which can be used in a variety of clinical applications such as surgical planning and quantitative image analysis.

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Middle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.

Effect of Filtered Back-Projection Filters to Low-Contrast Object Imaging in Ultra-High-Resolution (UHR) Cone-Beam Computed Tomography (CBCT)

In this study, the effect of filter schemes on several low-contrast materials was compared using standard and ultra-high-resolution (UHR) cone-beam computed tomography (CBCT) imaging. The performance of the UHR-CBCT was quantified by measuring the modulation transfer function (MTF) and the noise power spectrum (NPS). The MTF was measured at the radial location around the cylindrical phantom, whereas the NPS was measured in the eight different homogeneous regions of interest. Six different filter schemes were designed and implemented in the CT sinogram from each imaging configuration. The experimental results indicated that the filter with smaller smoothing window preserved the MTF up to the highest spatial frequency, but larger NPS. In addition, the UHR imaging protocol provided 1.77 times better spatial resolution than the standard acquisition by comparing the specific spatial frequency (f₅₀) under the same conditions. The f₅₀s with the flat-top window in UHR mode was 1.86, 0.94, 2.52, 2.05, and 1.86 lp/mm for Polyethylene (Material 1, M1), Polystyrene (M2), Nylon (M3), Acrylic (M4), and Polycarbonate (M5), respectively. The smoothing window in the UHR protocol showed a clearer performance in the MTF according to the low-contrast objects, showing agreement with the relative contrast of materials in order of M3, M4, M1, M5, and M2. In conclusion, although the UHR-CBCT showed the disadvantages of acquisition time and radiation dose, it could provide greater spatial resolution with smaller noise property compared to standard imaging; moreover, the optimal window function should be considered in advance for the best UHR performance.