scholarly journals Machine Learning in Orthodontics: Introducing a 3d Auto-segmentation and Auto-landmark Finder of Cbct Images To Assess Maxillary Constriction in Unilateral Impacted Canine patients

2019 ◽  
Vol 90 (1) ◽  
pp. 77-84 ◽  
Author(s):  
Si Chen ◽  
Li Wang ◽  
Gang Li ◽  
Tai-Hsien Wu ◽  
Shannon Diachina ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Automatic Segmentation ◽  
Three Dimensional ◽  
Control Group ◽  
Midsagittal Plane ◽  
Linear Measurements ◽  
Structure Variation ◽  
Significant Difference ◽  
Maxillary Constriction

ABSTRACT Objectives To (1) introduce a novel machine learning method and (2) assess maxillary structure variation in unilateral canine impaction for advancing clinically viable information. Materials and Methods A machine learning algorithm utilizing Learning-based multi-source IntegratioN frameworK for Segmentation (LINKS) was used with cone-beam computed tomography (CBCT) images to quantify volumetric skeletal maxilla discrepancies of 30 study group (SG) patients with unilaterally impacted maxillary canines and 30 healthy control group (CG) subjects. Fully automatic segmentation was implemented for maxilla isolation, and maxillary volumetric and linear measurements were performed. Analysis of variance was used for statistical evaluation. Results Maxillary structure was successfully auto-segmented, with an average dice ratio of 0.80 for three-dimensional image segmentations and a minimal mean difference of two voxels on the midsagittal plane for digitized landmarks between the manually identified and the machine learning–based (LINKS) methods. No significant difference in bone volume was found between impaction ([2.37 ± 0.34] 104 mm3) and nonimpaction ([2.36 ± 0.35] 104 mm3) sides of SG. The SG maxillae had significantly smaller volumes, widths, heights, and depths (P < .05) than CG. Conclusions The data suggest that palatal expansion could be beneficial for those with unilateral canine impaction, as underdevelopment of the maxilla often accompanies that condition in the early teen years. Fast and efficient CBCT image segmentation will allow large clinical data sets to be analyzed effectively.

scholarly journals Three-dimensional evaluation of upper airway following rapid maxillary expansion: A CBCT study

2013 ◽  
Vol 84 (2) ◽  
pp. 265-273 ◽  
Author(s):  
Hakan El ◽  
Juan Martin Palomo
Keyword(s):  
Three Dimensional ◽  
Upper Airway ◽  
Rapid Maxillary Expansion ◽  
Control Group ◽  
Nasal Passage ◽  
Maxillary Expansion ◽  
Oropharyngeal Airway ◽  
Significant Difference ◽  
Group A ◽  
Maxillary Constriction

ABSTRACT Objectives: To evaluate, by using cone beam computed tomography, the skeletal, dental, oropharyngeal (OP) airway volume, and nasal passage (NP) volume changes that occur after rapid maxillary expansion (RME). Materials and Methods: Two groups were selected, each with 35 patients (15 males, 20 females), an RME group (mean age, 14.02 ± 1.46 years) and a control group (mean age, 14.10 ± 1.44 years). The RME group consisted of patients with maxillary constriction who were treated with Hyrax palatal expanders, and the control group comprised age- and sex-matched patients who underwent comprehensive orthodontic treatment without the use of a rapid maxillary expander. Results: All of the transverse skeletal (medial orbital width, lateral nasal width, maxillary width, and mandibular width) and interdental (intermolar, interpremolar, and intercanine) parameters were significantly enlarged in the RME group. A statistically significant increase in airway variables was seen in both groups between pretreatment (T0) and final records (T1). The mean increase of NP airway volume for the RME group (1719.9 ± 1510.7 mm3) was twofold compared with the control group (813.6 ± 1006.7 mm3), and no intergroup significant difference was found for the OP volume. Conclusions: Rapid maxillary expansion creates a significant increase in nasal passage airway volume but no significant change in the oropharyngeal airway volume.

scholarly journals Changes in the Upper and Lower Pharyngeal Airway Spaces Associated with Rapid Maxillary Expansion

2012 ◽  
Vol 2012 ◽  
pp. 1-5 ◽  
Author(s):  
Fitin Aloufi ◽  
Charles B. Preston ◽  
Khalid H. Zawawi
Keyword(s):  
Orthodontic Treatment ◽  
Upper Airway ◽  
Rapid Maxillary Expansion ◽  
Lower Airway ◽  
Control Group ◽  
Maxillary Expansion ◽  
Pharyngeal Airway ◽  
Significant Difference ◽  
And Gender ◽  
Maxillary Constriction

Objectives. The primary objectives of this retrospective study were first to compare the upper and lower pharyngeal airway spaces between orthodontic patients with and without maxillary constriction and second to evaluate the effect of rapid maxillary expansion (RME) on these airway spaces. A secondary objective was to compare the mode of breathing between groups. Materials and Methods. The experimental (RME) group consisted of 30 patients (mean age, years, 16 boys and 14 girls) with maxillary constriction who were treated with hyrax-type RME. The control group comprised the records of age- and gender matched patients (mean age, years, 16 boys and 14 girls) with no maxillary constriction but requiring nonextraction comprehensive orthodontic treatment. Cephalometric measurements in the sagittal dimension of upper and lower airway spaces for the initial and final records were recorded. Mode of breathing and length of treatment were also compared. Results. The sagittal dimension of the upper airway increased significantly in the RME group ( mm) compared to the control group ( mm), . However, there was no significant difference in the lower pharyngeal airway measurement between the RME group () and the control group (), . There was no significant difference with respect to mode of breathing between the two groups (). Conclusion. Rapid maxillary expansion (RME) during orthodontic treatment may have a positive effect on the upper pharyngeal airway, with no significant change on the lower pharyngeal airway.

scholarly journals Enabling Technology for Remote Prosthetic Alignment Tuning

2021 ◽  
Vol 186 (Supplement_1) ◽  
pp. 659-664
Author(s):  
David A Boone ◽  
Sarah R Chang
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Coordinate Measuring Machine ◽  
Software Application ◽  
Prosthetic Socket ◽  
Prosthetic Alignment ◽  
Prosthesis Alignment ◽  
Alignment Tool ◽  
Measuring Machine

ABSTRACT Introduction This research has resulted in a system of sensors and software for effectively adjusting prosthetic alignment with digital numeric control. We called this suite of technologies the Prosthesis Smart Alignment Tool (ProSAT) system. Materials and Methods The ProSAT system has three components: a prosthesis-embedded sensor, an alignment tool, and an Internet-connected alignment expert system application that utilizes machine learning to analyze prosthetic alignment. All components communicate via Bluetooth. Together, they provide for numerically controlled prosthesis alignment adjustment. The ProSAT components help diagnose and guide the correction of very subtle, difficult-to-see imbalances in dynamic gait. The sensor has been cross-validated against kinetic measurement in a gait laboratory, and bench testing was performed to validate the performance of the tool while adjusting a prosthetic socket based on machine learning analyses from the software application. Results The three-dimensional alignment of the prosthetic socket was measured pre- and postadjustment from two fiducial points marked on the anterior surface of the prosthetic socket. A coordinate measuring machine was used to derive an alignment angular offset from vertical for both conditions: pre- and postalignment conditions. Of interest is the difference in the angles between conditions. The ProSAT tool is only controlling the relative change made to the alignment, not an absolute position or orientation. Target alignments were calculated by the machine learning algorithm in the ProSAT software, based on input of kinetic data samples representing the precondition and where a real prosthetic misalignment condition was known a priori. Detected misalignments were converted by the software to a corrective adjustment in the prosthesis alignment being tested. We demonstrated that a user could successfully and quickly achieve target postalignment change within an average of 0.1°. Conclusions The accuracy of a prototype ProSAT system has been validated for controlled alignment changes by a prosthetist. Refinement of the ergonomic form and technical function of the hardware and clinical usability of the mobile software application are currently being completed with benchtop experiments in advance of further human subject testing of alignment efficiency, accuracy, and user experience.

scholarly journals 1187 Evaluation of left and right ventricular functions with 3D speckle tracking in patients with mitral stenosis

2020 ◽  
Vol 21 (Supplement_1) ◽  
Author(s):  
O Seckin ◽  
S Unlu ◽  
G Tacoy
Keyword(s):  
Right Ventricular ◽  
Mitral Stenosis ◽  
Speckle Tracking ◽  
Longitudinal Strain ◽  
Global Longitudinal Strain ◽  
Three Dimensional ◽  
Left Ventricular ◽  
Control Group ◽  
Free Wall ◽  
Significant Difference

Abstract Background The function of both ventricles have been suggested to be affected in patients with mitral stenosis. In this study, it was aimed to investigate deformation properties of right (RV) and left ventricles (LV) in mild and moderate rheumatic mitral stenosis (MS) patients with three-dimensional speckle tracking echocardiography (3D-STE). Methods A total of 60 patients were included in the study (20 patients with mild MS diagnosis, 20 patients with moderate MS diagnosis and 20 healthy volunteers). Three-dimensional echocardiography datasets were obtained for both ventricles in all patients. An example for RV assessment is shown in Figure 1. LV global longitudinal strain (GLS), LV torsion, RV free wall (FW) LS and interventricular septal (IVS) LS measurements were analyzed. Results The LV ejection fraction (EF), RV fractional area change and tricuspid annular plane systolic excursion values were statistically similar and in the normal range. The LV GLS measurements were significantly different among the groups by being highest in the control group and least in the moderate stenosis group (ANOVA,p < 0.001) (Table 1). Patients with MS showed higher torsional values, correlated with MS severity (ANOVA,p < 0.001) (Table 1). IVS LS, RVFW LS values obtained by RV analysis also differed significantly among groups. The FW-GLS values only showed significant difference between the control group and moderate MS group (Table 1). Conclusion Patients with mitral stenosis showed lower LV-GLS and higher LV torsion values. Although the LV GLS is affected; the LV EF was detected to be normal due to increase in LV torsion. RV deformation indices showed signıficant decrease in correlation with the severity of the mitral stenosis. In conclusion, our data suggest that subclinical LV and RV systolic dysfunction is present in mild-moderate MS patients and this dysfunction can be detected by 3D-STE. Table 1 Parameters Control group Mild MS Moderate MS P LV GLS (%) 23.3 ± 2.08 18.9 ± 1.3 17.5 ± 1.8 <0.001 LV torsion 1.5 ± 0.6 2.1 ± 0.6 2.6 ± 0.5 <0.001 IVS LS (%) 23 ± 3.0% 20 ± 2.6 17.1 ± 2.9 <0.001 RV FW LS (%) 25.4 ± 5 22.7 ± 3.2 21.1 ± 4.8 <0.001 FW; free-wall, GLS; global longitudinal strain, IVS; interventricular septum, LV; left ventricular, RV; right ventricular Abstract 1187 Figure 1

Contactless Li-Ion Battery Voltage Detection by Using Walabot and Machine Learning

2019 ◽  
Author(s):  
Yanan Wang ◽  
Haoyu Niu ◽  
Tiebiao Zhao ◽  
Xiaozhong Liao ◽  
Lei Dong ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gradient Descent ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Lithium Ion ◽  
Principal Component ◽  
Stochastic Gradient Descent ◽  
Li Ion Battery ◽  
Linear Discriminant ◽  
Li Ion

Abstract This paper has proposed a contactless voltage classification method for Lithium-ion batteries (LIBs). With a three-dimensional radio-frequency based sensor called Walabot, voltage data of LIBs can be collected in a contactless way. Then three machine learning algorithm, that is, principal component analysis (PCA), linear discriminant analysis (LDA), and stochastic gradient descent (SGD) classifiers, have been employed for data processing. Experiments and comparison have been conducted to verify the proposed method. The colormaps of results and prediction accuracy show that LDA may be most suitable for LIBs voltage classification.

scholarly journals Relationship between formulaic breast volume and risk of breast cancer based on linear measurements

BMC Cancer ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Xiaoxia Li ◽  
Chunlan Zhou ◽  
Yanni Wu ◽  
Xiaohong Chen
Keyword(s):  
Breast Cancer ◽  
Logistic Regression ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Conditional Logistic Regression ◽  
Control Group ◽  
Case Group ◽  
Breast Volume ◽  
Linear Measurements ◽  
Significant Difference

Abstract Background Whether breast volume is a risk factor for breast cancer is controversial. This study aimed to evaluate whether a significant association between breast volume and risk of breast cancer, based on linear measurements, was present by applying propensity score matching (PSM). Methods The study was designed as a hospital-based case-control study. Between March 2018 and May 2019, 208 cases and 340 controls were retrospectively reviewed. Information on menarche, smoking, feeding mode, oral contraceptives, reproductive history and family history was obtained through a structured questionnaire. Breast volume was calculated using a formula based on linear measurements of breast parameters. Cox regression and PSM were used to estimate odds ratios and 95% confidence intervals for breast cancer using risk factors adjusted for potential confounders. Results There was a significant difference in breast volume between the two groups before propensity score matching (P = 0.014). Binary logistic regression showed that the risk of breast cancer was slightly higher in the case group with larger breast volumes than in the control group(P = 0.009, OR = 1.002, 95%CI:1.000 ~ 1.003). However, there was no significant statistical difference between the two groups using an independent sample Mann-Whitney U test (P = 0.438) or conditional logistic regression (P = 0.446). Conclusions After PSM for potential confounding factors, there is no significant difference in breast volume estimated by BREAST-V formula between the case group and the control group. The risk of breast cancer may not be related to breast volume in Chinese women.

AUTONOMOUS BEHAVIORS OF GRAPHICAL AVATARS BASED ON MACHINE LEARNING

2012 ◽  
Vol 26 (02) ◽  
pp. 1251002
Author(s):  
YUESHENG HE ◽  
YUAN YAN TANG
Keyword(s):  
Machine Learning ◽  
Hierarchical Structure ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Research Area ◽  
Machine Learning Techniques ◽  
3D Animation ◽  
Graphical Environment ◽  
Novel Approach ◽  
The Difference

Graphical avatars have gained popularity in many application domains such as three-dimensional (3D) animation movies and animated simulations for product design. However, the methods to edit avatars' behaviors in the 3D graphical environment remained to be a challenging research topic. Since the hand-crafted methods are time-consuming and inefficient, the automatic actions of the avatars are required. To achieve the autonomous behaviors of the avatars, artificial intelligence should be used in this research area. In this paper, we present a novel approach to construct a system of automatic avatars in the 3D graphical environments based on the machine learning techniques. Specific framework is created for controlling the behaviors of avatars, such as classifying the difference among the environments and using hierarchical structure to describe these actions. Because of the requirement of simulating the interactions between avatars and environments after the classification of the environment, Reinforcement Learning is used to compute the policy to control the avatar intelligently in the 3D environment for the solution of the problem of different situations. Thus, our approach has solved problems such as where the levels of the missions will be defined and how the learning algorithm will be used to control the avatars. In this paper, our method to achieve these goals will be presented. The main contributions of this paper are presenting a hierarchical structure to control avatars automatically, developing a method for avatars to recognize environment and presenting an approach for making the policy of avatars' actions intelligently.

Adoption of Ultrasonic Imaging Diagnosis Under Machine Learning Algorithm in Treatment of Pregnancy-Induced Hypertension and Nursing

2021 ◽  
Vol 11 (1) ◽  
pp. 268-275
Author(s):  
Wei Gao ◽  
Ani Zhou
Keyword(s):  
Machine Learning ◽  
Pregnant Women ◽  
Learning Algorithm ◽  
Resistance Index ◽  
Nursing Intervention ◽  
Control Group ◽  
Pregnancy Induced Hypertension ◽  
Induced Hypertension ◽  
Omaha System ◽  
Ultrasonic Images

In order to study the application of doppler ultrasound in monitoring the changes of important vascular hemodynamic indexes in pregnant women with Pregnancy-induced Hypertension (PIH) during pregnancy under the Omaha systematic nursing intervention (NI), in this study, 83 PIH pregnant women were taken as the study object. First, 60 normal pregnant women were taken as the control group (CG). Ultrasonic images of the uterine artery (UA) and middle cerebral artery (MCA) were collected. The machine learning (ML) algorithm was used to detect the edge of the target vessel in the UA image. The hemodynamic indexes of UA and MCA were compared between the two groups. Then, according to the routine NI and the NI method based on the Omaha system, 83 PIH pregnant women were divided into the routine group (RG) (n = 35) and the observation group (OG) (n = 48). The differences in UA hemodynamic parameters and quality of life (QOL) scores were compared between the two groups at 6 d after surgery. The results showed that pre-pregnancy BMI, mean artery pressure (MAP), and uric acid content in the CG were significantly lower than those in the PIH group (P < 0.05); the content of serum albumin in the CG was significantly higher than that in the PIH group (P < 0.05); compared with Sobel operator, edge detection (ED) based on ML algorithm was more coherent; in the CG, the systolic peak velocity (PSV), acceleration index (AI), pulse index (PI), and resistance index (RI) were significantly lower than those in the PIH group (P < 0.05); the values of PI and RI in MCA of CG were significantly higher than those in PIH group (P < 0.05); after NI, PSV, PI, RI, and AI values in the OG were significantly lower than those in the RG (P < 0.05); the health status, trunk pain, social function, emotional function, vitality, mental health, and total score of the OG were significantly higher than that of the RG (P < 0.05), which indicated that ultrasonic detection based on ML algorithm can be used in monitoring the changes of hemodynamic indexes of PIH pregnant women during NI, and the NI based on the Omaha system can effectively improve the QOL of PIH pregnant women.

Effect of personalized wrist orthosis for wrist pain with three-dimensional scanning and printing technique: A preliminary, randomized, controlled, open-label study

2018 ◽  
Vol 42 (6) ◽  
pp. 636-643 ◽  
Author(s):  
Sang Jun Kim ◽  
Sung Jae Kim ◽  
Yong Ho Cha ◽  
Keun Ho Lee ◽  
Jeong-Yi Kwon
Keyword(s):  
Hand Function ◽  
Three Dimensional ◽  
Wrist Pain ◽  
Control Group ◽  
Open Label ◽  
Open Label Study ◽  
Label Study ◽  
High Satisfaction ◽  
Significant Difference ◽  
Experimental Group

Background: Three-dimensional printer technology can produce the personalized orthosis in various forms. Objective: To develop a personalized wrist orthosis using a three-dimensional scanner and three-dimensional printer for patients with wrist pain. Study design: A preliminary, prospective, randomized, open-label study. Methods: A total of 22 patients with wrist pain were randomly assigned to the control and experimental groups. The control group wore a cock-up orthosis and the experimental group wore a three-dimensional-printed wrist orthosis for 1 week. The Patient-Rated Wrist Evaluation, Jebsen Hand Function Test, and Orthotics and Prosthetics Users’ Survey were checked before and 1 week after the application. Results: The Patient-Rated Wrist Evaluation showed significant pain relief in both groups. Two items of the 28 Orthotics and Prosthetics Users’ Survey questions, “Put toothpaste on brush and brush teeth” and “Dial a touch tone phone,” showed high satisfaction scores, with statistically significant difference in the experimental group ( p = 0.036 and 0.004). Conclusion: The three-dimensional-printed wrist orthosis was superior to the cock-up orthosis for two items of the Orthotics and Prosthetics Users’ Survey. Wrist pain was reduced in the group wearing the three-dimensional-printed wrist orthosis as well as the group wearing the cock-up orthosis, so the three-dimensional-printed wrist orthosis could possibly play the same role as the cock-up orthosis. Clinical relevance A three-dimensional-printed wrist orthosis can be a substitute for a conventional ready-made wrist orthosis for patients with wrist pain with more satisfaction.

scholarly journals Hypodontia Patterns and Variations in Craniofacial Morphology in Japanese Orthodontic Patients

2006 ◽  
Vol 76 (6) ◽  
pp. 996-1003 ◽  
Author(s):  
Toshiya Endo ◽  
Rieko Ozoe ◽  
Sugako Yoshino ◽  
Shohachi Shimooka
Keyword(s):  
Craniofacial Morphology ◽  
Occlusal Plane ◽  
Control Group ◽  
Missing Teeth ◽  
Linear Measurements ◽  
Posterior Group ◽  
Lateral Cephalograms ◽  
Significant Difference ◽  
Orthodontic Patients ◽  
Anterior Posterior

Abstract Objective: The purpose of this study was to explore the association of hypodontia patterns and variations in craniofacial morphology in Japanese orthodontic patients. Materials and Methods: A total of 50 girls with hypodontia (the total group) were selected and categorized into anterior, posterior, and anterior-posterior groups according to the location of the congenitally missing teeth. By using the lateral cephalograms of each subject, 28 angular and 37 linear measurements were made. The cephalometric data were statistically analyzed and compared among the groups and with the Japanese cephalometric standards from 36 age-matched female subjects without hypodontia or malocclusion (the control group). Results: Every hypodontia group showed shorter anterior and overall cranial base lengths, shorter maxillary length, greater retroclination and elongation of mandibular incisors, and a larger interincisal angle than the control group. The total and anterior-posterior groups especially exhibited a significantly more prognathic mandible, larger retroclination of maxillary incisors, and a more counterclockwise-rotated occlusal plane. Furthermore, these skeletal and dental deviations were more remarkable in the anterior-posterior group than in either the anterior or the posterior group. Anterior hypodontia exerted as much influence on craniofacial morphology as posterior hypodontia. Conclusions: When orthodontic treatment is performed on patients with hypodontia, not only the number but also the distribution of missing teeth should be taken into consideration, though there was no significant difference in craniofacial morphology between anterior hypodontia and posterior hypodontia.

Sign in / Sign up

Export Citation Format

Share Document