Artificial intelligence-based cephalometric landmark annotation and measurements according to Arnett’s analysis: can we trust a bot to do that?

2021 ◽  
pp. 20200548
Author(s):  
Thaísa Pinheiro Silva ◽  
Mariana Mendonça Hughes ◽  
Liciane dos Santos Menezes ◽  
Maria de Fátima Batista de Melo ◽  
Wilton Mitsunari Takeshita ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Intraclass Correlation ◽  
Angular Measurement ◽  
Horizontal Line ◽  
Independent Variables ◽  
Promising Tool ◽  
Angular Measurements ◽  
Belo Horizonte ◽  
Frankfurt Horizontal ◽  
Frankfurt Horizontal Plane

Objective: To assess the reliability of CEFBOT, an artificial intelligence (AI)-based cephalometry software, for cephalometric landmark annotation and linear and angular measurement according to Arnett’s analysis. Methods: Thirty lateral cephalometric radiographs acquired with a Carestream CS 9000 3D unit (Carestream Health Inc., Rochester/NY) were used in this study. The 66 landmarks and the ten selected linear and angular measurements of Arnett’s analysis were identified on each radiograph by a trained human examiner (control) and by CEFBOT (RadioMemory Ltd., Belo Horizonte, Brazil). For both methods, landmark annotations and measurements were duplicated with an interval of 15 days between measurements and the intraclass correlation coefficient (ICC) was calculated to determine reliability. The numerical values obtained with the two methods were compared by a t-test for independent variables. Results: CEFBOT was able to perform all but one of the ten measurements. ICC values > 0.94 were found for the remaining eight measurements, while the Frankfurt horizontal plane - true horizontal line (THL) angular measurement showed the lowest reproducibility (human, ICC = 0.876; CEFBOT, ICC = 0.768). Measurements performed by the human examiner and by CEFBOT were not statistically different. Conclusion: Within the limitations of our methodology, we concluded that the AI contained in the CEFBOT software can be considered a promising tool for enhancing the capacities of human Radiologists.

scholarly journals Structured Reporting of Rectal Cancer Staging and Restaging: A Consensus Proposal

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2135
Author(s):  
Vincenza Granata ◽  
Damiano Caruso ◽  
Roberto Grassi ◽  
Salvatore Cappabianca ◽  
Alfonso Reginelli ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Correlation Coefficient ◽  
Clinical Decision Making ◽  
Intraclass Correlation ◽  
Clinical Decision ◽  
Cancer Staging ◽  
Structured Reporting ◽  
Quality Analysis ◽  
Promising Tool ◽  
Structured Reports

Background: Structured reporting (SR) in oncologic imaging is becoming necessary and has recently been recognized by major scientific societies. The aim of this study was to build MRI-based structured reports for rectal cancer (RC) staging and restaging in order to provide clinicians all critical tumor information. Materials and Methods: A panel of radiologist experts in abdominal imaging, called the members of the Italian Society of Medical and Interventional Radiology, was established. The modified Delphi process was used to build the SR and to assess the level of agreement in all sections. The Cronbach’s alpha (Cα) correlation coefficient was used to assess the internal consistency of each section and to measure the quality analysis according to the average inter-item correlation. The intraclass correlation coefficient (ICC) was also evaluated. Results: After the second Delphi round of the SR RC staging, the panelists’ single scores and sum of scores were 3.8 (range 2–4) and 169, and the SR RC restaging panelists’ single scores and sum of scores were 3.7 (range 2–4) and 148, respectively. The Cα correlation coefficient was 0.79 for SR staging and 0.81 for SR restaging. The ICCs for the SR RC staging and restaging were 0.78 (p < 0.01) and 0.82 (p < 0.01), respectively. The final SR version was built and included 53 items for RC staging and 50 items for RC restaging. Conclusions: The final version of the structured reports of MRI-based RC staging and restaging should be a helpful and promising tool for clinicians in managing cancer patients properly. Structured reports collect all Patient Clinical Data, Clinical Evaluations and relevant key findings of Rectal Cancer, both in staging and restaging, and can facilitate clinical decision-making.

scholarly journals Longitudinal Reproducibility of CO2-Triggered BOLD MRI for the Hemodynamic Evaluation of Adult Patients with Moyamoya Angiopathy

2021 ◽  
pp. 1-7
Author(s):  
Constantin Roder ◽  
Uwe Klose ◽  
Helene Hurth ◽  
Cornelia Brendle ◽  
Marcos Tatagiba ◽  
...  
Keyword(s):  
Intraclass Correlation ◽  
Collateral Flow ◽  
Surgical Revascularization ◽  
Bold Mri ◽  
Promising Tool ◽  
Hemodynamic Evaluation ◽  
Group 2 ◽  
Group 1

<b><i>Background and Purpose:</i></b> Hemodynamic evaluation of moyamoya patients is crucial to decide the treatment strategy. Recently, CO<sub>2</sub>-triggered BOLD MRI has been shown to be a promising tool for the hemodynamic evaluation of moyamoya patients. However, the longitudinal reliability of this technique in follow-up examinations is unknown. This study aims to analyze longitudinal follow-up data of CO<sub>2</sub>-triggered BOLD MRI to prove the reliability of this technique for long-term control examinations in moyamoya patients. <b><i>Methods:</i></b> Longitudinal CO<sub>2</sub> BOLD MRI follow-up examinations of moyamoya patients with and without surgical revascularization have been analyzed for all 6 vascular territories retrospectively. If revascularization was performed, any directly (by the disease or the bypass) or indirectly (due to change of collateral flow after revascularization) affected territory was excluded based on angiography findings (group 1). In patients without surgical revascularization between the MRI examinations, all territories were analyzed (group 2). <b><i>Results:</i></b> Eighteen moyamoya patients with 39 CO<sub>2</sub> BOLD MRI examinations fulfilled the inclusion criteria. The median follow-up between the 2 examinations was 12 months (range 4–29 months). For 106 vascular territories analyzed in group 1, the intraclass correlation coefficient was 0.784, <i>p</i> &#x3c; 0.001, and for group 2 (84 territories), it was 0.899, <i>p</i> &#x3c; 0.001. Within the total follow-up duration of 140 patient months, none of the patients experienced a new stroke. <b><i>Conclusions:</i></b> CO<sub>2</sub> BOLD MRI is a promising tool for mid- and long-term follow-up examinations of cerebral hemodynamics in moyamoya patients. Systematic prospective evaluation is required prior to making it a routine examination.

Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs

2021 ◽  
pp. 20200172
Author(s):  
Münevver Coruh Kılıc ◽  
Ibrahim Sevki Bayrakdar ◽  
Özer Çelik ◽  
Elif Bilgir ◽  
Kaan Orhan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Confusion Matrix ◽  
Forensic Identification ◽  
Deciduous Teeth ◽  
Time Saving ◽  
Panoramic Radiographs ◽  
Intelligence System ◽  
Promising Tool ◽  
Panoramic Images

Objective: This study evaluated the use of a deep-learning approach for automated detection and numbering of deciduous teeth in children as depicted on panoramic radiographs. Methods and materials: An artificial intelligence (AI) algorithm (CranioCatch, Eskisehir-Turkey) using Faster R-CNN Inception v2 (COCO) models were developed to automatically detect and number deciduous teeth as seen on pediatric panoramic radiographs. The algorithm was trained and tested on a total of 421 panoramic images. System performance was assessed using a confusion matrix. Results: The AI system was successful in detecting and numbering the deciduous teeth of children as depicted on panoramic radiographs. The sensitivity and precision rates were high. The estimated sensitivity, precision, and F1 score were 0.9804, 0.9571, and 0.9686, respectively. Conclusion: Deep-learning-based AI models are a promising tool for the automated charting of panoramic dental radiographs from children. In addition to serving as a time-saving measure and an aid to clinicians, AI plays a valuable role in forensic identification.

Radiographic Angles in Hallux Valgus: Differences Between Measurements Made Manually and With a Computerized Program

2006 ◽  
Vol 27 (3) ◽  
pp. 175-180 ◽  
Author(s):  
Carlos Piqué-Vidal ◽  
Ignaci Maled-García ◽  
Juanjo Arabi-Moreno ◽  
Joan Vila
Keyword(s):  
Hallux Valgus ◽  
Measurement Techniques ◽  
Intraclass Correlation ◽  
Intermetatarsal Angle ◽  
Mean Values ◽  
Angle Measurements ◽  
Valgus Angle ◽  
Angular Measurements ◽  
San Rafael ◽  
True Values

Background: The objective of this study was to compare angular measurements in the evaluation of hallux valgus deformities using a goniometer and a computerized program to assess degree of concordance between the two methods and determine the reliability of manual measurements. Methods: Angles measured included the hallux valgus angle (HVA), the intermetatarsal angle (IMA), the distal metatarsal articular angle (DMAA), and the proximal phalangeal articular angle (PPAA), also called the hallux valgus interphalangeus angle or interphalangeal angle. Measurements were made on preoperative weightbearing radiographs in 176 patients with symptomatic hallux valgus. Manual measurements were made with a goniometer by an orthopaedic surgeon. An independent experienced technician used digitized images to perform angular measurements with the Autocad® software program (Autodesk Inc., San Rafael, CA). Results: HVA values obtained with the two techniques were similar. However, significantly higher mean values were obtained with the Autocad® for the IMA and PPAA measurements, and higher mean values were obtained for the DMAA measurement with the manual technique. Whereas differences were more or less randomly distributed for the HVA, in the remaining patients, measurements were clearly related to the measurement technique, i.e., for the DMAA, the manual technique had a tendency to show higher values, and for the IMA and PPAA the manual technique showed lower values than the computer. Correlations between both techniques for the different angular measurements were as follows: HVA, −0.179 ( p = 0.018); DMMA, −0.294 ( p >0.001); PPAA, −0.876 ( p >0.001); and IMA, −0.661 ( p >0.001). The intraclass correlation coefficient (ICC) showed that the concordance between manual and Autocad® angular measurements was excellent for the HVA ( ICC = 0.89) and DMAA ( ICC = 0.80) and very poor for the PPAA ( ICC = 0.11) and IMA ( ICC = 0.42). Conclusions: Angular measurements made on weightbearing radiographs with the Autocad® in patients with hallux valgus deformities were more reliable than those made with a goniometer. Although for large angles, such as HVA and DMAA, results obtained with both measurement techniques were similar. Manual measurements, however, may underestimate the true values of the smaller IMA and PPAA angles.

scholarly journals Socioeconomic deprivation scores as predictors of variations in NHS practice payments: a longitudinal study of English general practices 2013–2017

2019 ◽  
Vol 69 (685) ◽  
pp. e546-e554 ◽  
Author(s):  
Louis S Levene ◽  
Richard Baker ◽  
John Bankart ◽  
Nicola Walker ◽  
Andrew Wilson
Keyword(s):  
Intraclass Correlation ◽  
Large Sample Size ◽  
Cross Sectional ◽  
Independent Variables ◽  
Practice Population ◽  
Longitudinal Variations ◽  
General Practices ◽  
Organisational Factors ◽  
The Impact ◽  
Index Of Multiple Deprivation

BackgroundA previous study found that variables related to population health needs were poor predictors of cross-sectional variations in practice payments.AimTo investigate whether deprivation scores predicted variations in the increase over time of total payments to general practices per patient, after adjustment for potential confounders.Design and settingLongitudinal multilevel model for 2013–2017; 6900 practices (84.4% of English practices).MethodPractices were excluded if total adjusted payments per patient were <£10 or >£500 per patient or if deprivation scores were missing. Main outcome measures were adjusted total NHS payments; calculated by dividing total NHS payments, after deductions and premises payments, by the number of registered patients in each practice. A total of 17 independent variables relating to practice population and organisational factors were included in the model after checking for collinearity.ResultsAfter adjustment for confounders and the logarithmic transformation of the dependent and main independent variables (due to extremely skewed [positive] distribution of payments), practice deprivation scores predicted very weakly longitudinal variations in total payments’ slopes. For each 10% increase in the Index of Multiple Deprivation score, practice payments increased by only 0.06%. The large sample size probably explains why eight of the 17 confounders were significant predictors, but with very small coefficients. Most of the variability was at practice level (intraclass correlation = 0.81).ConclusionThe existing NHS practice payment formula has demonstrated very little redistributive potential and is unlikely to substantially narrow funding gaps between practices with differing workloads caused by the impact of deprivation.

scholarly journals Reproducibility of measurements in tablet-assisted, PC-aided, and manual cephalometric analysis

2013 ◽  
Vol 84 (3) ◽  
pp. 437-442 ◽  
Author(s):  
Cecilia Goracci ◽  
Marco Ferrari
Keyword(s):  
Intraclass Correlation ◽  
Occlusal Plane ◽  
Cephalometric Analysis ◽  
Linear Measurements ◽  
High Agreement ◽  
Landmark Identification ◽  
Lateral Cephalograms ◽  
Angular Measurements ◽  
Cephalometric Measurements ◽  
Good Agreement

ABSTRACT Objective: To assess the reproducibility of cephalometric measurements performed with software for a tablet, with a program for personal computers (PCs), and manually. Materials and Methods: The pretreatment lateral cephalograms of 20 patients that were acquired using the same digital cephalometer were collected. Tracings were performed with NemoCeph for Windows (Nemotec), with SmileCeph for iPad (Glace Software), and by hand. Landmark identification was carried out with a mouse-driven cursor using NemoCeph and with a stylus pen on the iPad screen using SmileCeph. Hand tracings were performed on printouts of the cephalograms, using a 0.3-mm 2H pencil and a protractor. Cephalometric landmarks and linear and angular measurements were recorded. All the tracings were done by the same investigator. To evaluate reproducibility, for each cephalometric measurement the agreement between the value derived from NemoCeph, that given by SmileCeph and that measured manually was assessed with the intraclass correlation coefficient (ICC). Agreement was rated as low for an ICC ≤0.75, and an ICC &gt; 0.75 was considered indicative of good agreement. Also, differences in measurements between each software and manual tracing were statistically evaluated (P &lt; .05). Results: All the measurements had ICC &gt;0.8, indicative of a high agreement among the tracing methods. Relatively lower ICCs occurred for linear measurements related to the occlusal plane and to N perpendicular to the Frankfurt plane. Differences in measurements between both software programs and hand tracing were not statistically significant for any of the cephalometric parameters. Conclusion: Tablet-assisted, PC-aided, and manual cephalometric tracings showed good agreement.

Validation of the Talar–Second Metatarsal Angle as a Standard Measurement for Radiographic Evaluation

2011 ◽  
Vol 101 (6) ◽  
pp. 475-483 ◽  
Author(s):  
Michael E. Graham ◽  
Avanthi Chikka ◽  
Paul C. Jones
Keyword(s):  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Radiographic Evaluation ◽  
Foot Deformities ◽  
Accurate Information ◽  
Intraclass Correlation Coefficients ◽  
First Metatarsal ◽  
Metatarsal Angle ◽  
Second Metatarsal ◽  
Angular Measurements

Background: Radiographs provide valuable information for assessing osseous foot deformities and aid in accurate diagnosis. The radiographic angular measurements can be used to establish a relationship between the forefoot and the hindfoot that will present valuable information about normal versus pathologic alignment of the foot. The talar–first metatarsal (T1M) angle is frequently used as one of these angles in this capacity; however, there are limitations to the anteroposterior T1M angle. We present a more consistent, reproducible, and accurate measurement for determining foot abnormalities in the transverse plane using the T2M angle instead of the T1M angle. Methods: Seventy feet in 35 participants (12 men and 23 women) were considered for this study. Individuals were selected on the basis of the established inclusion and exclusion criteria. Anteroposterior radiographs were taken in the angle and base of gait, the neutral calcaneal stance position (NCSP), and the resting calcaneal stance position (RCSP). Three observers measured these angles using three different methods. Results: The mean ± SD T2M angle was 2.95° ± 7.16° in NCSP and 18.61° ± 7.21° in RCSP. No significant differences were found among the measurements made by the three observers using slightly varying procedures in NCSP and RCSP (P &gt; .05). The intraclass correlation coefficients among the measurements were 0.905 in NCSP and 0.937 in RCSP. Bland-Altman plots showed very good agreement between the measurements made by the three observers. Conclusions: The anteroposterior T2M angle gives a consistent and reproducible measurement that provides accurate information about foot alignment. (J Am Podiatr Med Assoc 101(6): 475–483, 2011)

scholarly journals Testing the Reliability and Construct Validity of Short-Term Assessment of Risk and Treatability (START) in Non-Western Forensic Psychiatric Inpatients

2022 ◽  
Author(s):  
Weeerapong Sanmontree ◽  
Peera Wongupparaj
Keyword(s):  
Construct Validity ◽  
Mental Health Professionals ◽  
Ordinal Data ◽  
Intraclass Correlation ◽  
Asian Population ◽  
Psychiatric Inpatients ◽  
Short Term ◽  
Rater Reliability ◽  
Promising Tool ◽  
Forensic Psychiatric

The Short-Term Assessment of Risk and Treatability (START) is deemed the most appropriate instrument for assessing violence risks and management because of its balanced approach between dynamic risk and protective factors. Although several facets of reliability and predictive validity of this tool were strong, its inter-rater reliability, construct validity, and implementation in Asian population were under-investigated. The objective of this research was to examine the inter-rater reliability and construct validity of the START: Thai version within forensic psychiatric inpatients. The participants consisted of 118 forensic psychiatric inpatients hospitalized at Galya Rajanagarindra Institute in Thailand. Trained mental health professionals (i.e., psychiatrists, forensic nurses, clinical psychologists, social workers, and occupational therapists) assessed each participant across twenty domains of the Thai START. The inter-rater reliability was examined using the intraclass correlation coefficient and a confirmatory factor analysis for ordinal data was used to test the construct validity of the scale. The main finding showed a good-to-excellent inter-rater reliability and supported two relational constructs (i.e., strength vs vulnerability subscales) of the Thai START. The Thai START is a promising tool for using in Thai forensic psychiatric setting but some items were not significant in contributing to the scale. This study also provides the guideline for implementing the tool in non-Western forensic psychiatric populations.

scholarly journals Using Artificial Intelligence Techniques for Prediction and Estimation of Photovoltaic System Output Power

2020 ◽  
Vol 3 (1) ◽  
pp. 15-21
Author(s):  
Deogratias Nurwaha
Keyword(s):  
Artificial Intelligence ◽  
Output Power ◽  
Gene Expression Programming ◽  
Photovoltaic System ◽  
Support Vector ◽  
Independent Variables ◽  
Vector Machines ◽  
System Output ◽  
Two Parameters ◽  
Statistical Metrics

Two artificial intelligence methods, namely, support vector machines (SVM) and gene expression programming (GEP), were explored for prediction and estimation of the Photovoltaic (PV)output power. Measured values of temperature T (°C) and irradiance E (kWh/㎡) were used as inputs (independent variables) and PV output power P (Kw) was used as output (dependent variable). The statistical metrics were used to assess the predictive performances of the methods. The results of the two models were estimated and compared. The results showed that the two techniques performances are better and similar. Using GEP technique, the relationships between the two parameters and output power were established. Importance of each parameter as contributor to PV output power was also investigated. The results indicated that the SVM and GEP would become the powerful tools that could help estimate the PV output power capacity reserve.

scholarly journals Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET

2020 ◽  
Author(s):  
Elisabeth Pfaehler ◽  
Liesbet Mesotten ◽  
Gem Kramer ◽  
Michiel Thomeer ◽  
Karolien Vanhove ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Majority Vote ◽  
Automatic Segmentation ◽  
Intraclass Correlation ◽  
Cancer Staging ◽  
Tumor Segmentation ◽  
Jaccard Coefficient ◽  
Primary Tumors ◽  
Segmentation Methods ◽  
Segmentation Approach

Abstract Background: Positron Emission Tomography (PET) is routinely used for cancer staging and treatment follow up. Metabolic active tumor volume (MATV) as well as total MATV (TMATV - including primary tumor, lymph nodes and metastasis) and/or total lesion glycolysis (TLG) derived from PET images have been identified as prognostic factor or for the evaluation of treatment efficacy in cancer patients. To this end, a segmentation approach with high precision and repeatability is important. However, the implementation of a repeatable and accurate segmentation algorithm remains an ongoing challenge. Methods: In this study, we compare two semi-automatic artificial intelligence (AI) based segmentation methods with conventional semi-automatic segmentation approaches in terms of repeatability. One segmentation approach is based on a textural feature (TF) segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis. Moreover, a Convolutional Neural Network (CNN) is trained. The algorithms are trained, validated and tested using a lung cancer PET dataset. The segmentation accuracy of both segmentation approaches is compared using the Jaccard Coefficient (JC). Additionally, the approaches are externally tested on a fully independent test-retest dataset. The repeatability of the methods is compared with those of two majority vote (MV2, MV3) approaches, 41%SUVMAX, and a SUV>4 segmentation (SUV4). Repeatability is assessed with test-retest coefficients (TRT%) and intraclass correlation coefficient (ICC). An ICC>0.9 was regarded as representing excellent repeatability.Results: The accuracy of the segmentations with the reference segmentation was good (JC median TF: 0.7, CNN: 0.73) Both segmentation approaches outperformed most other conventional segmentation methods in terms of test-retest coefficient (TRT% mean: TF: 13.0%, CNN: 13.9%, MV2: 14.1%, MV3: 28.1%, 41%SUVMAX: 28.1%, SUV4: 18.1% ) and ICC (TF: 0.98, MV2: 0.97, CNN: 0.99, MV3: 0.73, SUV4: 0.81, and 41%SUVMAX: 0.68).Conclusion: The semi-automatic AI based segmentation approaches used in this study provided better repeatability than conventional segmentation approaches. Moreover, both algorithms lead to accurate segmentations for both primary tumors as well as metastasis and are therefore good candidates for PET tumor segmentation.

Sign in / Sign up

Export Citation Format

Share Document