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.

In a pilot study, automated real-time systematic review updates were feasible, accurate, and work-saving.

OBJECTIVES: The aim of this study is to describe and pilot a novel method for continuously identifying newly published trials relevant to a systematic review, enabled by combining artificial intelligence (AI) with human expertise. STUDY DESIGN AND SETTING: We used RobotReviewer LIVE to keep a review of COVID-19 vaccination trials updated from February to August 2021. We compared the papers identified by the system with those found by the conventional manual process by the review team. RESULTS: The manual update searches (last search date July 2021) retrieved 135 abstracts, of which 31 were included after screening (23% precision, 100% recall). By the same date, the automated system retrieved 56 abstracts, of which 31 were included after manual screening (55% precision, 100% recall). Key limitations of the system include that it is limited to searches of PubMed/MEDLINE, and considers only randomized controlled trial reports. We aim to address these limitations in future. The system is available as open-source software for further piloting and evaluation. CONCLUSION: Our system identified all relevant studies, reduced manual screening work, and enabled rolling updates on publication of new primary research.

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.

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.

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.

Human transcriptome analysis of acute responses to glucose ingestion reveals the role of leukocytes in hyperglycemia-induced inflammation.

Glucose ingestion-induced hyperglycemia has been known to induce inflammation, which is related to the pathogenesis of diabetic complications. To examine acute gene expression responses to physiological oral glucose ingestion in human circulating leukocytes, we conducted a microarray study of human circulating leukocytes sampled before, 1 h after, and 2 h after glucose ingestion in community-based participants without previous histories of diabetes (n = 60). Ingestion of 75 g glucose successfully induced acute hyperglycemia (glucose concentration 91.6 ± 5.3 mg/dl for fasting and 180.7 ± 48.5 mg/dl for 1 h after glucose ingestion). Oral glucose ingestion significantly increased the expressions of 23 genes and decreased the expressions of 13 genes [false discovery rate (FDR) P value <0.05]. These genes are significantly involved in immunity by way of natural killer cell-mediated immunity, granulocyte-mediated immunity, and the cytokine-mediated signaling pathway (FDR P value <0.05). The present study demonstrated 36 genes that showed acute gene expression change in human leukocytes within 1 h after glucose ingestion, suggesting that leukocytes participate in the inflammatory process induced by acute hyperglycemia. We believe that these results will provide some basic insight into the role of leukocytes in hyperglycemia-induced inflammation and the pathogenesis of diabetic complications.

Functions of metallothionein generating interleukin-10-producing regulatory CD4+ T cells potentiate suppression of collagen-induced arthritis.

Metallothionein, a cysteine-rich stress response protein that is naturally induced by a variety of immunologic stressors, has been shown to suppress autoimmune disorders through mechanisms not yet fully defined. In the present study, we examined the underlying mechanisms by which metallothionein might mediate such regulation of autoimmunity. Naïve CD4+ T cells from metallothionein-deficient mice differentiated to produce significantly less IL-10, TGF-gamma, and repressor of GATA, but more IFN-gamma and T-bet, when compared with those from wild-type mice. The levels of IL-4 and GATA-3 production were not different between the two groups of mice. Conversely, treatment with exogenous metallothionein during the priming phase drove naïve wild-type CD4+ T cells to differentiate into cells producing more IL-10 and TGF-beta, but less IFN-gamma than untreated cells. Metallothionein-primed cells were hyporesponsive to restimulation, and suppressive to T cell proliferation in an IL-10-dependent manner. Lymphocytes from metallothionein-deficient mice displayed significantly elevated levels of AP-1 and JNK activities in response to stimulation compared with those from wild-type controls. Importantly, transgenic mice overexpressing metallothionein exhibited significantly reduced susceptibility to collagen-induced arthritis and enhanced IL-10 level in the serum, relative to their nontransgenic littermates. Taken together, these data suggest that metallothionein is able to promote the generation of IL-10- and TGF-beta-producing type 1 regulatory T-like cells by downregulating JNK-dependent AP-1 activity. Thus, metallothionein may play an important role in the regulation of Th1-dependent autoimmune arthritis, and may represent both a potential target for therapeutic manipulation and a critical element in the diagnostic assessment of disease potential.

New cyclooxygenase-2 inhibitor DFU regulates vascular endothelial growth factor expression in rheumatoid synoviocytes.

Vascular endothelial growth factor (VEGF) plays an important role in angiogenesis in rheumatoid synoviocytes. In the present study, whether DFU, a tetrasubstituted furanone initially identified as a selective inhibitor of cyclooxygenase (COX)-2, interferes with transforming growth factor (TGF)-beta-mediated induction of VEGF was determined. Fibroblast-like synoviocytes (FLS) isolated from the synovial tissue of patients with rheumatoid arthritis were stimulated with TGF-beta in the presence or absence of DFU, followed by RT-PCR and ELISA assays to quantify the level of VEGF transcript and its product, respectively. DFU was found to elicit diverse activities on FLS, including inhibition of COX-2 and VEGF expression as well as COX-2 activity. The inhibition of TGF-beta-induced VEGF production by DFU was dose-dependent and abolished by exogenous prostaglandin E2. DFU was more potent than indomethacin to inhibit the VEGF production. These results suggest an in vivo potential for DFU to regulate both processes of inflammation and angiogenesis which collaboratively play important roles in the progression and perpetuation of rheumatoid arthritis.

Beneficial effects of rosmarinic acid on suppression of collagen induced arthritis.

OBJECTIVE: To assess the therapeutic potential of rosmarinic acid (RosA) in an inflammatory autoimmune arthritis model. METHODS: Collagen induced arthritis is established in male DBA/1 mice. Mice were administered daily with 50 mg/kg/day of RosA for 15 days from Day 21 post-immunization and inspected daily to determine the progression of arthritis. After termination of injection, affected hindpaws were subjected to histopathological analyses and immunohistochemical assays for cyclooxygenase-2 (COX-2) expression. RESULTS: Repeated administration of RosA dramatically reduced the arthritic index and number of affected paws. Histopathologic observations closely paralleled clinical data, showing that RosA treated mice retained nearly normal architecture of synovial tissues, whereas control mice exhibited severe synovitis. Synovial tissues from RosA treated mice exhibited remarkably reduced frequency of COX-2-expressing cells, compared to those from untreated mice. CONCLUSION: RosA suppressed synovitis in a murine collagen induced arthritis model; this effect may be beneficial for treatment of rheumatoid arthritis in clinical settings.