Computed tomographic beam-hardening artefacts: mathematical characterization and analysis.

This paper presents a mathematical characterization and analysis of beam-hardening artefacts in X-ray computed tomography (CT). In the field of dental and medical radiography, metal artefact reduction in CT is becoming increasingly important as artificial prostheses and metallic implants become more widespread in ageing populations. Metal artefacts are mainly caused by the beam-hardening of polychromatic X-ray photon beams, which causes mismatch between the actual sinogram data and the data model being the Radon transform of the unknown attenuation distribution in the CT reconstruction algorithm. We investigate the beam-hardening factor through a mathematical analysis of the discrepancy between the data and the Radon transform of the attenuation distribution at a fixed energy level. Separation of cupping artefacts from beam-hardening artefacts allows causes and effects of streaking artefacts to be analysed. Various computer simulations and experiments are performed to support our mathematical analysis.

Electrical impedance spectroscopy-based defect sensing technique in estimating cracks.

A defect sensing method based on electrical impedance spectroscopy is proposed to image cracks and reinforcing bars in concrete structures. The method utilizes the frequency-dependent behavior of thin insulating cracks: low-frequency electrical currents are blocked by insulating cracks, whereas high-frequency currents can pass through thin cracks to probe the conducting bars. From various frequency-dependent electrical impedance tomography (EIT) images, we can show its advantage in terms of detecting both thin cracks with their thickness and bars. We perform numerical simulations and phantom experiments to support the feasibility of the proposed method.

Design of a microscopic electrical impedance tomography system for 3D continuous non-destructive monitoring of tissue culture.

BACKGROUND: Non-destructive continuous monitoring of regenerative tissue is required throughout the entire period of in vitro tissue culture. Microscopic electrical impedance tomography (micro-EIT) has the potential to monitor the physiological state of tissues by forming three-dimensional images of impedance changes in a non-destructive and label-free manner. We developed a new micro-EIT system and report on simulation and experimental results of its macroscopic model. METHODS: We propose a new micro-EIT system design using a cuboid sample container with separate current-driving and voltage sensing electrodes. The top is open for sample manipulations. We used nine gold-coated solid electrodes on each of two opposing sides of the container to produce multiple linearly independent internal current density distributions. The 360 voltage sensing electrodes were placed on the other sides and base to measure induced voltages. Instead of using an inverse solver with the least squares method, we used a projected image reconstruction algorithm based on a logarithm formulation to produce projected images. We intended to improve the quality and spatial resolution of the images by increasing the number of voltage measurements subject to a few injected current patterns. We evaluated the performance of the micro-EIT system with a macroscopic physical phantom. RESULTS: The signal-to-noise ratio of the developed micro-EIT system was 66 dB. Crosstalk was in the range of -110.8 to -90.04 dB. Three-dimensional images with consistent quality were reconstructed from physical phantom data over the entire domain. From numerical and experimental results, we estimate that at least 20 × 40 electrodes with 120 µm spacing are required to monitor the complex shape of ingrowth neotissue inside a scaffold with 300 µm pore. CONCLUSION: The experimental results showed that the new micro-EIT system with a reduced set of injection current patterns and a large number of voltage sensing electrodes can be potentially used for tissue culture monitoring. Numerical simulations demonstrated that the spatial resolution could be improved to the scale required for tissue culture monitoring. Future challenges include manufacturing a bioreactor-compatible container with a dense array of electrodes and a larger number of measurement channels that are sensitive to the reduced voltage gradients expected at a smaller scale.

Electrical impedance spectroscopy for electro-mechanical characterization of conductive fabrics.

When we use a conductive fabric as a pressure sensor, it is necessary to quantitatively understand its electromechanical property related with the applied pressure. We investigated electromechanical properties of three different conductive fabrics using the electrical impedance spectroscopy (EIS). We found that their electrical impedance spectra depend not only on the electrical properties of the conductive yarns, but also on their weaving structures. When we apply a mechanical tension or compression, there occur structural deformations in the conductive fabrics altering their apparent electrical impedance spectra. For a stretchable conductive fabric, the impedance magnitude increased or decreased under tension or compression, respectively. For an almost non-stretchable conductive fabric, both tension and compression resulted in decreased impedance values since the applied tension failed to elongate the fabric. To measure both tension and compression separately, it is desirable to use a stretchable conductive fabric. For any conductive fabric chosen as a pressure-sensing material, its resistivity under no loading conditions must be carefully chosen since it determines a measurable range of the impedance values subject to different amounts of loadings. We suggest the EIS method to characterize the electromechanical property of a conductive fabric in designing a thin and flexible fabric pressure sensor.

Deep learning-based automated measurement of cervical length in transvaginal ultrasound images of pregnant women.

Cervical length (CL) measurement using transvaginal ultrasound is an effective screening tool to assess the risk of preterm birth. An adequate assessment of CL is crucial, however, manual sonographic CL measurement is highly operator-dependent and cumbersome. Therefore, a reliable and reproducible automatic method for CL measurement is in high demand to reduce inter-rater variability and improve workflow. Despite the increasing use of artificial intelligence techniques in ultrasound, applying deep learning (DL) to analyze ultrasound images of the cervix remains a challenge due to low signal-to-noise ratios and difficulties in capturing the cervical canal, which appears as a thin line and with extremely low contrast against the surrounding tissues. To address these challenges, we have developed CL-Net, a novel DL network that incorporates expert anatomical knowledge to identify the cervix, similar to the approach taken by clinicians. CL-Net captures anatomical features related to CL measurement, facilitating the identification of the cervical canal. It then identifies the cervical canal and automatically provides reproducible and reliable CL measurements. CL-Net achieved a success rate of 95.5% in recognizing the cervical canal, comparable to that of human experts (96.4%). Furthermore, the differences between the CL measurements of CL-Net and ground truth were considerably smaller than those made by non-experts and were comparable to those made by experts (median 1.36 mm, IQR 0.87-2.82 mm, range 0.06-6.95 mm for straight cervix; median 1.31 mm, IQR 0.61-2.65 mm, range 0.01-8.18 mm for curved one).

Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification.

We present a fully automated method of integrating intraoral scan (IOS) and dental cone-beam computerized tomography (CBCT) images into one image by complementing each image's weaknesses. Dental CBCT alone may not be able to delineate precise details of the tooth surface due to limited image resolution and various CBCT artifacts, including metal-induced artifacts. IOS is very accurate for the scanning of narrow areas, but it produces cumulative stitching errors during full-arch scanning. The proposed method is intended not only to compensate the low-quality of CBCT-derived tooth surfaces with IOS, but also to correct the cumulative stitching errors of IOS across the entire dental arch. Moreover, the integration provides both gingival structure of IOS and tooth roots of CBCT in one image. The proposed fully automated method consists of four parts; (i) individual tooth segmentation and identification module for IOS data (TSIM-IOS); (ii) individual tooth segmentation and identification module for CBCT data (TSIM-CBCT); (iii) global-to-local tooth registration between IOS and CBCT; and (iv) stitching error correction for full-arch IOS. The experimental results show that the proposed method achieved landmark and surface distance errors of 112.4µm and 301.7µm, respectively.

Metal artifact reduction in CT by identifying missing data hidden in metals.

There is increasing demand in the field of dental and medical radiography for effective metal artifact reduction (MAR) in computed tomography (CT) because artifact caused by metallic objects causes serious image degradation that obscures information regarding the teeth and/or other biological structures. This paper presents a new MAR method that uses the Laplacian operator to reveal background projection data hidden in regions containing data from metal. In the proposed method, we attempted to decompose the projection data into two parts: data from metal only (metal data), and background data in the absence of metal. Removing metal data from the projections enables us to perform sparsity-driven reconstruction of the metal component and subsequent removal of the metal artifact. The results of clinical experiments demonstrated that the proposed MAR algorithm improves image quality and increases the standard of 3D reconstruction images of the teeth and mandible.

A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography.

Identification of 3D cephalometric landmarks that serve as proxy to the shape of human skull is the fundamental step in cephalometric analysis. Since manual landmarking from 3D computed tomography (CT) images is a cumbersome task even for the trained experts, automatic 3D landmark detection system is in a great need. Recently, automatic landmarking of 2D cephalograms using deep learning (DL) has achieved great success, but 3D landmarking for more than 80 landmarks has not yet reached a satisfactory level, because of the factors hindering machine learning such as the high dimensionality of the input data and limited amount of training data due to the ethical restrictions on the use of medical data. This paper presents a semi-supervised DL method for 3D landmarking that takes advantage of anonymized landmark dataset with paired CT data being removed. The proposed method first detects a small number of easy-to-find reference landmarks, then uses them to provide a rough estimation of the all landmarks by utilizing the low dimensional representation learned by variational autoencoder (VAE). The anonymized landmark dataset is used for training the VAE. Finally, coarse-to-fine detection is applied to the small bounding box provided by rough estimation, using separate strategies suitable for the mandible and the cranium. For mandibular landmarks, patch-based 3D CNN is applied to the segmented image of the mandible (separated from the maxilla), in order to capture 3D morphological features of mandible associated with the landmarks. We detect 6 landmarks around the condyle all at once rather than one by one, because they are closely related to each other. For cranial landmarks, we again use the VAE-based latent representation for more accurate annotation. In our experiment, the proposed method achieved a mean detection error of 2.88 mm for 90 landmarks using only 15 paired training data.

A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT.

Accurate and automatic segmentation of three-dimensional (3D) individual teeth from cone-beam computerized tomography (CBCT) images is a challenging problem because of the difficulty in separating an individual tooth from adjacent teeth and its surrounding alveolar bone. Thus, this paper proposes a fully automated method of identifying and segmenting 3D individual teeth from dental CBCT images. The proposed method addresses the aforementioned difficulty by developing a deep learning-based hierarchical multi-step model. First, it automatically generates upper and lower jaws panoramic images to overcome the computational complexity caused by high-dimensional data and the curse of dimensionality associated with limited training dataset. The obtained 2D panoramic images are then used to identify 2D individual teeth and capture loose- and tight- regions of interest (ROIs) of 3D individual teeth. Finally, accurate 3D individual tooth segmentation is achieved using both loose and tight ROIs. Experimental results showed that the proposed method achieved an F1-score of 93.35 percent for tooth identification and a Dice similarity coefficient of 94.79 percent for individual 3D tooth segmentation. The results demonstrate that the proposed method provides an effective clinical and practical framework for digital dentistry.

A fidelity-embedded learning for metal artifact reduction in dental CBCT.

PURPOSE: Dental cone-beam computed tomography (CBCT) has been increasingly used for dental and maxillofacial imaging. However, the presence of metallic inserts, such as implants, crowns, and dental braces, violates the CT model assumption, which leads to severe metal artifacts in the reconstructed CBCT image, resulting in the degradation of diagnostic performance. In this study, we used deep learning to reduce metal artifacts. METHODS: The metal artifacts, appearing as streaks and shadows, are nonlocal and highly associated with various factors, including the geometry of metallic inserts, energy-dependent attenuation, and energy spectrum of the incident X-ray beam, making it difficult to learn their complicated structures directly. To provide a step-by-step environment in which deep learning can be trained, we propose an iterative learning approach in which the network at each iteration step learns the correction error caused by the previous network, while enforcing the data fidelity in the projection domain. To generate a realistic paired training dataset, metal-free CBCT scans were collected from patients without metallic inserts, and then simulated metal projection data were added to generate the corresponding metal-corrupted projection data. RESULTS: The feasibility of the proposed method was investigated in clinical metal-affected CBCT scans, as well as simulated metal-affected CBCT scans. The results show that the proposed method significantly reduces metal artifacts while preserving the morphological structures near metallic objects and outperforms direct image domain learning. CONCLUSION: The proposed fidelity-embedded learning can effectively reduce metal artifacts in dental CBCT compared with direct image domain learning.

Deep learning method for reducing metal artifacts in dental cone-beam CT using supplementary information from intra-oral scan.

Objective.Recently, dental cone-beam computed tomography (CBCT) methods have been improved to significantly reduce radiation dose while maintaining image resolution with minimal equipment cost. In low-dose CBCT environments, metallic inserts such as implants, crowns, and dental fillings cause severe artifacts, which result in a significant loss of morphological structures of teeth in reconstructed images. Such metal artifacts prevent accurate 3D bone-teeth-jaw modeling for diagnosis and treatment planning. However, the performance of existing metal artifact reduction (MAR) methods in handling the loss of the morphological structures of teeth in reconstructed CT images remains relatively limited. In this study, we developed an innovative MAR method to achieve optimal restoration of anatomical details.Approach.The proposed MAR approach is based on a two-stage deep learning-based method. In the first stage, we employ a deep learning network that utilizes intra-oral scan data as side-inputs and performs multi-task learning of auxiliary tooth segmentation. The network is designed to improve the learning ability of capturing teeth-related features effectively while mitigating metal artifacts. In the second stage, a 3D bone-teeth-jaw model is constructed with weighted thresholding, where the weighting region is determined depending on the geometry of the intra-oral scan data.Main results.The results of numerical simulations and clinical experiments are presented to demonstrate the feasibility of the proposed approach.Significance.We propose for the first time a MAR method using radiation-free intra-oral scan data as supplemental information on the tooth morphological structures of teeth, which is designed to perform accurate 3D bone-teeth-jaw modeling in low-dose CBCT environments.

Automatic detection and segmentation of lumbar vertebrae from X-ray images for compression fracture evaluation.

For compression fracture detection and evaluation, an automatic X-ray image segmentation technique that combines deep-learning and level-set methods is proposed. Automatic segmentation is much more difficult for X-ray images than for CT or MRI images because they contain overlapping shadows of thoracoabdominal structures including lungs, bowel gases, and other bony structures such as ribs. Additional difficulties include unclear object boundaries, the complex shape of the vertebra, inter-patient variability, and variations in image contrast. Accordingly, a structured hierarchical segmentation method is presented that combines the advantages of two deep-learning methods. Pose-driven learning is used to selectively identify the five lumbar vertebrae in an accurate and robust manner. With knowledge of the vertebral positions, M-net is employed to segment the individual vertebra. Finally, fine-tuning segmentation is applied by combining the level-set method with the previously obtained segmentation results. The performance of the proposed method was validated by 160 lumbar X-ray images, resulting in a mean Dice similarity metric of 91.60±2.22%. The results show that the proposed method achieves accurate and robust identification of each lumbar vertebra and fine segmentation of individual vertebra.

Deep learning-based solvability of underdetermined inverse problems in medical imaging.

Recently, with the significant developments in deep learning techniques, solving underdetermined inverse problems has become one of the major concerns in the medical imaging domain, where underdetermined problems are motivated by the willingness to provide high resolution medical images with as little data as possible, by optimizing data collection in terms of minimal acquisition time, cost-effectiveness, and low invasiveness. Typical examples include undersampled magnetic resonance imaging(MRI), interior tomography, and sparse-view computed tomography(CT), where deep learning techniques have achieved excellent performances. However, there is a lack of mathematical analysis of why the deep learning method is performing well. This study aims to explain about learning the causal relationship regarding the structure of the training data suitable for deep learning, to solve highly underdetermined problems. We present a particular low-dimensional solution model to highlight the advantage of deep learning methods over conventional methods, where two approaches use the prior information of the solution in a completely different way. We also analyze whether deep learning methods can learn the desired reconstruction map from training data in the three models (undersampled MRI, sparse-view CT, interior tomography). This paper also discusses the nonlinearity structure of underdetermined linear systems and conditions of learning (called M-RIP condition).

Automated ultrasound assessment of amniotic fluid index using deep learning.

The estimation of antenatal amniotic fluid (AF) volume (AFV) is important as it offers crucial information about fetal development, fetal well-being, and perinatal prognosis. However, AFV measurement is cumbersome and patient specific. Moreover, it is heavily sonographer-dependent, with measurement accuracy varying greatly depending on the sonographer's experience. Therefore, the development of accurate, robust, and adoptable methods to evaluate AFV is highly desirable. In this regard, automation is expected to reduce user-based variability and workload of sonographers. However, automating AFV measurement is very challenging, because accurate detection of AF pockets is difficult owing to various confusing factors, such as reverberation artifact, AF mimicking region and floating matter. Furthermore, AF pocket exhibits an unspecified variety of shapes and sizes, and ultrasound images often show missing or incomplete structural boundaries. To overcome the abovementioned difficulties, we develop a hierarchical deep-learning-based method, which consider clinicians' anatomical-knowledge-based approaches. The key step is the segmentation of the AF pocket using our proposed deep learning network, AF-net. AF-net is a variation of U-net combined with three complementary concepts - atrous convolution, multi-scale side-input layer, and side-output layer. The experimental results demonstrate that the proposed method provides a measurement of the amniotic fluid index (AFI) that is as robust and precise as the results from clinicians. The proposed method achieved a Dice similarity of 0.877±0.086 for AF segmentation and achieved a mean absolute error of 2.666±2.986 and mean relative error of 0.018±0.023 for AFI value. To the best of our knowledge, our method, for the first time, provides an automated measurement of AFI.

Learning-based local-to-global landmark annotation for automatic 3D cephalometry.

The annotation of three-dimensional (3D) cephalometric landmarks in 3D computerized tomography (CT) has become an essential part of cephalometric analysis, which is used for diagnosis, surgical planning, and treatment evaluation. The automation of 3D landmarking with high-precision remains challenging due to the limited availability of training data and the high computational burden. This paper addresses these challenges by proposing a hierarchical deep-learning method consisting of four stages: 1) a basic landmark annotator for 3D skull pose normalization, 2) a deep-learning-based coarse-to-fine landmark annotator on the midsagittal plane, 3) a low-dimensional representation of the total number of landmarks using variational autoencoder (VAE), and 4) a local-to-global landmark annotator. The implementation of the VAE allows two-dimensional-image-based 3D morphological feature learning and similarity/dissimilarity representation learning of the concatenated vectors of cephalometric landmarks. The proposed method achieves an average 3D point-to-point error of 3.63 mm for 93 cephalometric landmarks using a small number of training CT datasets. Notably, the VAE captures variations of craniofacial structural characteristics.

Multi-frequency time-difference complex conductivity imaging of canine and human lungs using the KHU Mark1 EIT system.

We evaluated the performance of the lately developed electrical impedance tomography (EIT) system KHU Mark1 through time-difference imaging experiments of canine and human lungs. We derived a multi-frequency time-difference EIT (mftdEIT) image reconstruction algorithm based on the concept of the equivalent homogeneous complex conductivity. Imaging experiments were carried out at three different frequencies of 10, 50 and 100 kHz with three different postures of right lateral, sitting (or prone) and left lateral positions. For three normal canine subjects, we controlled the ventilation using a ventilator at three tidal volumes of 100, 150 and 200 ml. Three human subjects were asked to breath spontaneously at a normal tidal volume. Real- and imaginary-part images of the canine and human lungs were reconstructed at three frequencies and three postures. Images showed different stages of breathing cycles and we could interpret them based on the understanding of the proposed mftdEIT image reconstruction algorithm. Time series of images were further analyzed by using the functional EIT (fEIT) method. Images of human subjects showed the gravity effect on air distribution in two lungs. In the canine subjects, the morphological change seems to dominate the gravity effect. We could also observe that two different types of ventilation should have affected the results. The KHU Mark1 EIT system is expected to provide reliable mftdEIT images of the human lungs. In terms of the image reconstruction algorithm, it would be worthwhile including the effects of three-dimensional current flows inside the human thorax. We suggest clinical trials of the KHU Mark1 for pulmonary applications.

MREIT conductivity imaging of the postmortem canine abdomen using CoReHA.

Magnetic resonance electrical impedance tomography (MREIT) is a new bio-imaging modality providing cross-sectional conductivity images from measurements of internal magnetic flux densities produced by externally injected currents. Recent experimental results of postmortem and in vivo imaging of the canine brain demonstrated its feasibility by showing conductivity images with meaningful contrast among different brain tissues. MREIT image reconstructions involve a series of data processing steps such as k-space data handling, phase unwrapping, image segmentation, meshing, modelling, finite element computation, denoising and so on. To facilitate experimental studies, we need a software tool that automates these data processing steps. In this paper, we summarize such an MREIT software package called CoReHA (conductivity reconstructor using harmonic algorithms). Performing imaging experiments of the postmortem canine abdomen, we demonstrate how CoReHA can be utilized in MREIT. The abdomen with a relatively large field of view and various organs imposes new technical challenges when it is chosen as an imaging domain. Summarizing a few improvements in the experimental MREIT technique, we report our first conductivity images of the postmortem canine abdomen. Illustrating reconstructed conductivity images, we discuss how they discern different organs including the kidney, spleen, stomach and small intestine. We elaborate, as an example, that conductivity images of the kidney show clear contrast among cortex, internal medulla, renal pelvis and urethra. We end this paper with a brief discussion on future work using different animal models.

Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning.

This paper presents a new approach to automatic three-dimensional (3D) cephalometric annotation for diagnosis, surgical planning, and treatment evaluation. There has long been considerable demand for automated cephalometric landmarking, since manual landmarking requires considerable time and experience as well as objectivity and scrupulous error avoidance. Due to the inherent limitation of two-dimensional (2D) cephalometry and the 3D nature of surgical simulation, there is a trend away from current 2D to 3D cephalometry. Deep learning approaches to cephalometric landmarking seem highly promising, but there exist serious difficulties in handling high dimensional 3D CT data, dimension referring to the number of voxels. To address this issue of dimensionality, this paper proposes a shadowed 2D image-based machine learning method which uses multiple shadowed 2D images with various lighting and view directions to capture 3D geometric cues. The proposed method using VGG-net was trained and tested using 2700 shadowed 2D images and corresponding manual landmarkings. Test data evaluation shows that our method achieved an average point-to-point error of 1.5 mm for the seven major landmarks.

Automatic evaluation of fetal head biometry from ultrasound images using machine learning.

OBJECTIVE: Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are frequently used to evaluate gestational age and diagnose fetal central nervous system pathology. Because manual measurements are operator-dependent and time-consuming, much research is being actively conducted on automated methods. However, the existing automated methods are still not satisfactory in terms of accuracy and reliability, owing to difficulties dealing with various artefacts in ultrasound images. APPROACH: Using the proposed method, a labeled dataset containing 102 ultrasound images was used for training, and validation was performed with 70 ultrasound images. MAIN RESULTS: A success rate of 91.43% and 100% for HC and BPD estimations, respectively, and an accuracy of 87.14% for the plane acceptance check. SIGNIFICANCE: This paper focuses on fetal head biometry and proposes a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability.

Three-dimensional measurement and registration accuracy of a third-generation optical tracking system for navigational maxillary orthognathic surgery.

OBJECTIVE: The purpose of this study was to evaluate the accuracy of an optical tracking system during reference point localization, measurement, and registration of skull models for navigational maxillary orthognathic surgery. STUDY DESIGN: Accuracy was first evaluated on the basis of the position recording discrepancy at a static point and at 2 points of fixed lengths. Ten reference points were measured on a skull model at 7 different locations, and their measurements were compared with predicted positions by using 4 registration methods. Finally, positional tracking of reference points for simulated maxillary surgery was performed and compared with laser scan data. RESULTS: The average linear measurement discrepancy was 0.28 mm, and the mean measurement discrepancy with the 5 registered cranial points was 1.53 mm. The average measurement discrepancy after maxillary surgery was 1.91 mm (for impaction) and 1.56 mm (for advancement). The registration discrepancy in jitter and point registration on the y-axis was significantly greater than on the other axes. CONCLUSIONS: The optical tracking system seems clinically acceptable for precise tracking of the maxillary position during navigational orthognathic surgery, notwithstanding the chance of greater measurement error on the y-axis.