Dynamic 3-D MR Visualization and Detection of Upper Airway Obstruction During Sleep Using Region-Growing Segmentation

Automatic Multiple Articulator Segmentation in Dynamic Speech MRI Using a Protocol Adaptive Stacked Transfer Learning U-NET Model

Dynamic magnetic resonance imaging has emerged as a powerful modality for investigating upper-airway function during speech production. Analyzing the changes in the vocal tract airspace, including the position of soft-tissue articulators (e.g., the tongue and velum), enhances our understanding of speech production. The advent of various fast speech MRI protocols based on sparse sampling and constrained reconstruction has led to the creation of dynamic speech MRI datasets on the order of 80-100 image frames/second. In this paper, we propose a stacked transfer learning U-NET model to segment the deforming vocal tract in 2D mid-sagittal slices of dynamic speech MRI. Our approach leverages (a) low- and mid-level features and (b) high-level features. The low- and mid-level features are derived from models pre-trained on labeled open-source brain tumor MR and lung CT datasets, and an in-house airway labeled dataset. The high-level features are derived from labeled protocol-specific MR images. The applicability of our approach to segmenting dynamic datasets is demonstrated in data acquired from three fast speech MRI protocols: Protocol 1: 3 T-based radial acquisition scheme coupled with a non-linear temporal regularizer, where speakers were producing French speech tokens; Protocol 2: 1.5 T-based uniform density spiral acquisition scheme coupled with a temporal finite difference (FD) sparsity regularization, where speakers were producing fluent speech tokens in English, and Protocol 3: 3 T-based variable density spiral acquisition scheme coupled with manifold regularization, where speakers were producing various speech tokens from the International Phonetic Alphabetic (IPA). Segments from our approach were compared to those from an expert human user (a vocologist), and the conventional U-NET model without transfer learning. Segmentations from a second expert human user (a radiologist) were used as ground truth. Evaluations were performed using the quantitative DICE similarity metric, the Hausdorff distance metric, and segmentation count metric. This approach was successfully adapted to different speech MRI protocols with only a handful of protocol-specific images (e.g., of the order of 20 images), and provided accurate segmentations similar to those of an expert human.

Surgical Navigation System for Hypertensive Intracerebral Hemorrhage Based on Mixed Reality

Hypertensive intracerebral hemorrhage (HICH) is an intracerebral bleeding disease that affects 2.5 per 10,000 people worldwide each year. An effective way to cure this disease is puncture through the dura with a brain puncture drill and tube; the accuracy of the insertion determines the quality of the surgery. In recent decades, surgical navigation systems have been widely used to improve the accuracy of surgery and minimize risks. Augmented reality- and mixed reality-based surgical navigation is a promising new technology for surgical navigation in the clinic, aiming to improve the safety and accuracy of the operation. In this study, we present a novel multimodel mixed reality navigation system for HICH surgery in which medical images and virtual anatomical structures can be aligned intraoperatively with the actual structures of the patient in a head-mounted device and adjusted when the patient moves in real time while under local anesthesia; this approach can help the surgeon intuitively perform intraoperative navigation. A novel registration method is used to register the holographic space and serves as an intraoperative optical tracker, and a method for calibrating the HICH surgical tools is used to track the tools in real time. The results of phantom experiments revealed a mean registration error of 1.03 mm and an average time consumption of 12.9 min. In clinical usage, the registration error was 1.94 mm, and the time consumption was 14.2 min, showing that this system is sufficiently accurate and effective for clinical application.

Novel User-Friendly Application for MRI Segmentation of Brain Resection following Epilepsy Surgery

Delineation of resected brain cavities on magnetic resonance images (MRIs) of epilepsy surgery patients is essential for neuroimaging/neurophysiology studies investigating biomarkers of the epileptogenic zone. The gold standard to delineate the resection on MRI remains manual slice-by-slice tracing by experts. Here, we proposed and validated a semiautomated MRI segmentation pipeline, generating an accurate model of the resection and its anatomical labeling, and developed a graphical user interface (GUI) for user-friendly usage. We retrieved pre- and postoperative MRIs from 35 patients who had focal epilepsy surgery, implemented a region-growing algorithm to delineate the resection on postoperative MRIs and tested its performance while varying different tuning parameters. Similarity between our output and hand-drawn gold standards was evaluated via dice similarity coefficient (DSC; range: 0-1). Additionally, the best segmentation pipeline was trained to provide an automated anatomical report of the resection (based on presurgical brain atlas). We found that the best-performing set of parameters presented DSC of 0.83 (0.72-0.85), high robustness to seed-selection variability and anatomical accuracy of 90% to the clinical postoperative MRI report. We presented a novel user-friendly open-source GUI that implements a semiautomated segmentation pipeline specifically optimized to generate resection models and their anatomical reports from epilepsy surgery patients, while minimizing user interaction.

Automatic upper airway segmentation in static and dynamic MRI via anatomy-guided convolutional neural networks

PURPOSE

Upper airway segmentation on MR images is a prerequisite step for quantitatively studying the anatomical structure and function of the upper airway and surrounding tissues. However, the complex variability of intensity and shape of anatomical structures and different modes of image acquisition commonly used in this application makes automatic upper airway segmentation challenging. In this paper, we develop and test a comprehensive deep learning-based segmentation system for use on MR images to address this problem.

MATERIALS AND METHODS

In our study, both static and dynamic MRI data sets are utilized, including 58 axial static 3D MRI studies, 22 mid-retropalatal dynamic 2D MRI studies, 21 mid-retroglossal dynamic 2D MRI studies, 36 mid-sagittal dynamic 2D MRI studies, and 23 isotropic dynamic 3D MRI studies, involving a total of 160 subjects and over 20 000 MRI slices. Samples of static and 2D dynamic MRI data sets were randomly divided into training, validation, and test sets by an approximate ratio of 5:2:3. Considering that the variability of annotation data among 3D dynamic MRIs was greater than for other MRI data sets, we increased the ratio of training data for these data to improve the robustness of the model. We designed a unified framework consisting of the following procedures. For static MRI, a generalized region-of-interest (GROI) strategy is applied to localize the partitions of nasal cavity and other portions of upper airway in axial data sets as two separate subobjects. Subsequently, the two subobjects are segmented by two separate 2D U-Nets. The two segmentation results are combined as the whole upper airway structure. The GROI strategy is also applied to other MRI modes. To minimize false-positive and false-negative rates in the segmentation results, we employed a novel loss function based explicitly on these rates to train the segmentation networks. An inter-reader study is conducted to test the performance of our system in comparison to human variability in ground truth (GT) segmentation of these challenging structures.

RESULTS

The proposed approach yielded mean Dice coefficients of 0.84±0.03, 0.89±0.13, 0.84±0.07, and 0.86±0.05 for static 3D MRI, mid-retropalatal/mid-retroglossal 2D dynamic MRI, mid-sagittal 2D dynamic MRI, and isotropic dynamic 3D MRI, respectively. The quantitative results show excellent agreement with manual delineation results. The inter-reader study results demonstrate that the segmentation performance of our approach is statistically indistinguishable from manual segmentations considering the inter-reader variability in GT.

CONCLUSIONS

The proposed method can be utilized for routine upper airway segmentation from static and dynamic MR images with high accuracy and efficiency. The proposed approach has the potential to be employed in other dynamic MRI-related applications, such as lung or heart segmentation.

Fully automatic segmentation of sinonasal cavity and pharyngeal airway based on convolutional neural networks

INTRODUCTION

This study aimed to test the accuracy of a new automatic deep learning-based approach on the basis of convolutional neural networks (CNN) for fully automatic segmentation of the sinonasal cavity and the pharyngeal airway from cone-beam computed tomography (CBCT) scans.

METHODS

Forty CBCT scans from healthy patients (20 women and 20 men; mean age, 23.37 ± 3.34 years) were collected, and manual segmentation of the sinonasal cavity and pharyngeal subregions were carried out by using Mimics software (version 20.0; Materialise, Leuven, Belgium). Twenty CBCT scans from the total sample were randomly selected and used for training the artificial intelligence model file. The remaining 20 CBCT segmentation masks were used to test the accuracy of the CNN fully automatic method by comparing the segmentation volumes of the 3-dimensional models obtained with automatic and manual segmentations. The accuracy of the CNN-based method was also assessed by using the Dice score coefficient and by the surface-to-surface matching technique. The intraclass correlation coefficient and Dahlberg's formula were used to test the intraobserver reliability and method error, respectively. Independent Student t test was used for between-groups volumetric comparison.

RESULTS

Measurements were highly correlated with an intraclass correlation coefficient value of 0.921, whereas the method error was 0.31 mm³. A mean difference of 1.93 ± 0.73 cm³ was found between the methodologies, but it was not statistically significant (P >0.05). The mean matching percentage detected was 85.35 ± 2.59 (tolerance 0.5 mm) and 93.44 ± 2.54 (tolerance 1.0 mm). The differences, measured as the Dice score coefficient in percentage, between the assessments done with both methods were 3.3% and 5.8%, respectively.

CONCLUSIONS

The new deep learning-based method for automated segmentation of the sinonasal cavity and the pharyngeal airway in CBCT scans is accurate and performs equally well as an experienced image reader.

Intuitionistic Fuzzy C-Means Algorithm Based on Membership Information Transfer-Ring and Similarity Measurement

The fuzzy C-means clustering (FCM) algorithm is used widely in medical image segmentation and suitable for segmenting brain tumors. Therefore, an intuitionistic fuzzy C-means algorithm based on membership information transferring and similarity measurements (IFCM-MS) is proposed to segment brain tumor magnetic resonance images (MRI) in this paper. The original FCM lacks spatial information, which leads to a high noise sensitivity. To address this issue, the membership information transfer model is adopted to the IFCM-MS. Specifically, neighborhood information and the similarity of adjacent iterations are incorporated into the clustering process. Besides, FCM uses simple distance measurements to calculate the membership degree, which causes an unsatisfactory result. So, a similarity measurement method is designed in the IFCM-MS to improve the membership calculation, in which gray information and distance information are fused adaptively. In addition, the complex structure of the brain results in MRIs with uncertainty boundary tissues. To overcome this problem, an intuitive fuzzy attribute is embedded into the IFCM-MS. Experiments performed on real brain tumor images demonstrate that our IFCM-MS has low noise sensitivity and high segmentation accuracy.

Kernel-Based Robust Bias-Correction Fuzzy Weighted C-Ordered-Means Clustering Algorithm

The spatial constrained Fuzzy C-means clustering (FCM) is an effective algorithm for image segmentation. Its background information improves the insensitivity to noise to some extent. In addition, the membership degree of Euclidean distance is not suitable for revealing the non-Euclidean structure of input data, since it still lacks enough robustness to noise and outliers. In order to overcome the problem above, this paper proposes a new kernel-based algorithm based on the Kernel-induced Distance Measure, which we call it Kernel-based Robust Bias-correction Fuzzy Weighted C-ordered-means Clustering Algorithm (KBFWCM). In the construction of the objective function, KBFWCM algorithm comprehensively takes into account that the spatial constrained FCM clustering algorithm is insensitive to image noise and involves a highly intensive computation. Aiming at the insensitivity of spatial constrained FCM clustering algorithm to noise and its image detail processing, the KBFWCM algorithm proposes a comprehensive algorithm combining fuzzy local similarity measures (space and grayscale) and the typicality of data attributes. Aiming at the poor robustness of the original algorithm to noise and outliers and its highly intensive computation, a Kernel-based clustering method that includes a class of robust non-Euclidean distance measures is proposed in this paper. The experimental results show that the KBFWCM algorithm has a stronger denoising and robust effect on noise image.

The use of drug-induced sleep endoscopy in England and Belgium

Purpose

The purpose of this international survey is to ascertain the current practice of drug-induced sleep endoscopy (DISE) for patients with sleep-disordered breathing (SDB) by Otolaryngologists in the United Kingdom and Belgium. We compare the results with recommendations from the European Position Paper on drug-induced sleep endoscopy.

Methods

An online questionnaire was circulated to Consultant Otolaryngologists, independent practitioners, and trainees across the two countries. Eleven questions were used in total.

Results

181 responses from the UK and 117 responses from Belgium were received, mostly from consultants and independent practitioners. SDB was a common presentation to ENT practice, seen by over 90% of clinicians. The use of DISE varied greatly between the two countries (72.9% Belgium, 26.1% UK). 54.1% of Belgian respondents use DISE on over 50% of their patients, compared to only 32.4% of British clinicians. Attitudes of surgeons towards the diagnostic value of DISE varied; in Belgium, the majority (54%) gave a rating of 3 or more (1 = useless to 5 = essential), with no respondents giving a score of 0 (useless). In the UK only 16% of respondents felt DISE had useful clinical value, with 25 respondents deeming it ’useless’. The majority opt for DISE when non-surgical therapies fail (51.4% UK, 61.3% Belgium). The majority of participants do not use objective measures for depth of sedation (75.7% UK, 66.7% Belgium), with a marked variation on anaesthetic methods. 62.2% of UK clinicians do not use a classification system, whereas in Belgium the majority of clinicians (60.8%) use the VOTE grading system.

Conclusions

Clinicians in Belgium were more favourable to using DISE than in the UK. Differences in its clinical effectiveness were apparent between the two countries. A consensus on patient selection, method of sedation and an effective classification system seemed to be lacking from both countries. Further education is required to raise awareness for the use of DISE.

Image enhancement variational methods for enabling strong cost reduction in OLED-based point-of-care immunofluorescent diagnostic systems

Immunofluorescence diagnostic systems cost is often dominated by high-sensitivity, low-noise CCD-based cameras that are used to acquire the fluorescence images. In this paper, we investigate the use of low-cost CMOS sensors in a point-of-care immunofluorescence diagnostic application for the detection and discrimination of 4 different serotypes of the Dengue virus in a set of human samples. A 2-phase postprocessing software pipeline is proposed, which consists in a first image-enhancement stage for resolution increasing and segmentation and a second diagnosis stage for the computation of the output concentrations. We present a novel variational coupled model for the joint super-resolution and segmentation stage and an automatic innovative image analysis for the diagnosis purpose. A specially designed forward backward-based numerical algorithm is introduced, and its convergence is proved under mild conditions. We present results on a cheap prototype CMOS camera compared with the results of a more expensive CCD device, for the detection of the Dengue virus with a low-cost OLED light source. The combination of the CMOS sensor and the developed postprocessing software allows to correctly identify the different Dengue serotype using an automatized procedure. The results demonstrate that our diagnostic imaging system enables camera cost reduction up to 99%, at an acceptable diagnostic accuracy, with respect to the reference CCD-based camera system. The correct detection and identification of the Dengue serotypes have been confirmed by standard diagnostic methods (RT-PCR and ELISA).

Real-time multislice MRI during continuous positive airway pressure reveals upper airway response to pressure change

PURPOSE

To determine if a real-time magnetic resonance imaging (RT-MRI) method during continuous positive airway pressure (CPAP) can be used to measure neuromuscular reflex and/or passive collapsibility of the upper airway in individual obstructive sleep apnea (OSA) subjects.

MATERIALS AND METHODS

We conducted experiments on four adolescents with OSA and three healthy controls, during natural sleep and during wakefulness. Data were acquired on a clinical 3T scanner using simultaneous multislice (SMS) RT-MRI during CPAP. CPAP pressure level was alternated between therapeutic and subtherapeutic levels. Segmented airway area changes in response to rapid CPAP pressure drop and restoration were used to estimate 1) upper airway loop gain (UALG), and 2) anatomical risk factors, including fluctuation of airway area (FAA).

RESULTS

FAA significantly differed between OSA patients (2-4× larger) and healthy controls (Student's t-test, P < 0.05). UALG and FAA measurements indicate that neuromuscular reflex and passive collapsibility varied among the OSA patients, suggesting the presence of different OSA phenotypes. Measurements had high intrasubject reproducibility (intraclass correlation coefficient r > 0.7).

CONCLUSION

SMS RT-MRI during CPAP can reproducibly identify physiological traits and anatomical risk factors that are valuable in the assessment of OSA. This technique can potentially locate the most collapsible airway sites. Both UALG and FAA possess large variation among OSA patients.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2017;46:1400-1408.