Suli Guo, Hu Chen, Yaopeng Zhang, Li Gao, Feng Wu, Yuchun Sun
{"title":"Establishment and evaluation of a 3D quantitative analysis method for dental plaque based on an intraoral scanner technique.","authors":"Suli Guo, Hu Chen, Yaopeng Zhang, Li Gao, Feng Wu, Yuchun Sun","doi":"10.3290/j.ijcd.b4000009","DOIUrl":"10.3290/j.ijcd.b4000009","url":null,"abstract":"<p><strong>Aim: </strong>Quantitative dental plaque evaluation is necessary for clinical and scientific work. The present study aimed to examine the reliability of a 3D image analysis method by digitally analyzing the color 3D images obtained from an intraoral scanner (IOS) and then detecting and quantifying the plaque information and comparing it with the clinical examination results.</p><p><strong>Materials and methods: </strong>A total of 140 teeth from five subjects with a standard dentition were enrolled. Plaque examination was performed at two different time points: after 24 h without oral hygiene (T1), and after habitual brushing (T2). At each time point, the Quigley-Hein Plaque Index (PI) of each tooth surface was recorded separately, followed by color 3D images obtained using an IOS, and image analysis and calculation using Geomagic Wrap 2021 software.</p><p><strong>Results: </strong>The percentage of plaque staining area calculated from the 3D image analysis correlated well with the PI recorded during the clinical examination: the Spearman correlation coefficients were 0.9136 and 0.9061 (P < 0.001) for all tooth surfaces at T1 and T2, respectively. The measurements of the three investigators were in good agreement, with intraclass correlation coefficients of 0.989 and 0.992 (P < 0.001) for the vestibular and lingual surfaces at T1, respectively, and 0.964 and 0.983 (P < 0.001) for the vestibular and lingual surfaces at T2, respectively.</p><p><strong>Conclusion: </strong>In the present study, a digital 3D evaluation system of dental plaque suitable for research and clinical practice was initially developed and its reliability demonstrated.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"141-149"},"PeriodicalIF":1.7,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9214328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jonathan C Fleiner, Johan P Woelber, Anja C Kürschner, Hans-Christian Lux, Dirk Schulze, Christian Hannig
{"title":"Software-supported periodontal diagnostics with 3D CBCT compared with conventional 2D panoramic imaging and clinical diagnostics: a prospective study.","authors":"Jonathan C Fleiner, Johan P Woelber, Anja C Kürschner, Hans-Christian Lux, Dirk Schulze, Christian Hannig","doi":"10.3290/j.ijcd.b4170267","DOIUrl":"10.3290/j.ijcd.b4170267","url":null,"abstract":"<p><strong>Aim: </strong>The objective of the present study was the software-supported evaluation of the measurement accuracy between CBCT and panoramic radiographs in the assessment of the periodontal bone level in patients with periodontitis, and the comparison of this with clinical periodontal parameters.</p><p><strong>Materials and methods: </strong>Twenty patients with severe periodontitis (stage III to IV) were evaluated clinically and radiographically (panoramic radiographs and CBCT). Diagnostic interpretation comprised three blinded investigators with different levels of experience. Specific software-basing measurement procedure evaluated radiologic distances for the mesial, central, and distal bone levels on the oral and vestibular sides of the teeth investigated and furcation upper and lower boundary. Jaw localization, anatomical region of interest, the number of roots, and the experience of the observers were evaluated. All measurements were carried out twice by the same observers within a 6-week interval.</p><p><strong>Results: </strong>Slightly higher measurement deviations (SD) in the range of 0.47 (0.40) mm were found for CBCT evaluation compared with panoramic imaging. Pearson correlation analysis showed statistically strong positive correlation for the mesial and distal aspects, and moderate positive correlation was found for the investigated furcations between both radiographic modalities. Compared with the clinical reference, the mean total error of measurement (SD) was larger for panoramic imaging (0.66 [0.48] mm) than for CBCT (0.27 [0.08] mm) for all three observers.</p><p><strong>Conclusions: </strong>Software-supported CBCT analysis delivers better diagnostic information about the bony periodontal conditions of the patient compared with 2D radiographs. However, it remains unclear if this additional information leads to better periodontal outcomes.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"151-159"},"PeriodicalIF":1.7,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9672997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The analogous intraoral judgement of the abutment preparation angle is almost impossible! At least avoid undercuts.","authors":"Felix H Blankenstein, Jelka Plake","doi":"10.3290/j.ijcd.b4110975","DOIUrl":"10.3290/j.ijcd.b4110975","url":null,"abstract":"<p><strong>Aim: </strong>A total occlusal convergence (TOC) angle (ϕ) of 6 degrees is a typical crown preparation requirement. It has been shown that this is difficult to achieve clinically. The present study therefore aims to compare the ability of students to judge different steepnesses, including a -1-degree undercut of prepared canines and molars, under clinical conditions with different analog tools.</p><p><strong>Materials and methods: </strong>The complete dentures of a patient were duplicated without denture teeth 16, 23, 33, and 46. For each of these gaps, six crown stumps were milled with ϕ/2 = -1, 3, 6, 9, 12, and 15 degrees, each of which was insertable using mini-magnets. A total of 144 dental students, 48 students each from the 1st, 6th, or 9th semester, estimated these angles intraorally with various aiding tools: In addition to basic dental instruments, they used a parallelometer mirror, an analog clock dial with a 6-degree visualization, and a scale of tooth stumps with ϕ/2 between -1 and 15 degrees.</p><p><strong>Results: </strong>The widely demanded 3 degrees were hardly recognized, but assumed to be steeper or even undercut. In contrast, the -1-degree divergent stump walls were predominantly estimated as parallel-walled or slightly conical. With increasing taper, the stumps tended to be classified as steeper, ie, \"better.\" The additional tools did not result in a general improvement of the estimation performance. Students from higher semesters did not achieve better results.</p><p><strong>Conclusion: </strong>The present authors question the objectivity of an exclusively visual assessment of crown stump taper. It appears that dental training should at least focus on avoiding undercuts as the minimal prerequisite for an accurate intraoral scanning procedure. Digital control of the preparation angle by an intraoral scan and immediate clinical implementation of these results could help to produce appropriate preparations.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"169-177"},"PeriodicalIF":1.7,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9491608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sofya Sadilina, Franz J Strauss, Ronald E Jung, Tim Joda, Marc Balmer
{"title":"Use of optical see-through head-mounted devices in dentistry - a scoping review.","authors":"Sofya Sadilina, Franz J Strauss, Ronald E Jung, Tim Joda, Marc Balmer","doi":"10.3290/j.ijcd.b5394865","DOIUrl":"10.3290/j.ijcd.b5394865","url":null,"abstract":"<p><strong>Aim: </strong>The aim of this scoping review was to identify the scientific evidence related to the utilization of Optical See- Through Head-Mounted Display (OST-HMD) in dentistry, and to determine future research needs.</p><p><strong>Methods: </strong>The research question was formulated using the "Population" (P), "Concept" (Cpt), and "Context" (Cxt) framework for scoping reviews. Existing literature was designated as P, OST-HMD as Cpt, and Dentistry as Cxt. An electronic search was conducted in PubMed, Embase, Web of Science, and CENTRAL. Two authors independently screened titles and abstracts and performed the full-text analysis.</p><p><strong>Results: </strong>The search identified 286 titles after removing duplicates. Nine studies, involving 138 participants and 1760 performed tests were included in this scoping review. Seven of the articles were preclinical studies, one was a survey, and one was a clinical trial. The included manuscripts covered various dental fields: three studies in orthodontics, two in oral surgery, two in conservative dentistry, one in general dentistry, and the remaining one in prosthodontics. Five articles focused on educational purposes. Two brands of OST-HMD were used: in eight studies HoloLens Microsoft was used, while Google Glass was utilized in one article.</p><p><strong>Conclusions: </strong>The overall number of included studies was low; therefore, the available data from this review cannot yet support an evidence-based recommendation for the clinical use of OST-HMDs. However, the existing preclinical data indicate a significant capacity for clinical and educational implementation. Further adoption of these devices will facilitate more reliable and objective quality and performance assessments, as well as more direct comparisons with conventional workflows. More clinical studies must be conducted to substantiate the potential benefits and reliability for patients and clinicians.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"1-35"},"PeriodicalIF":1.8,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141155750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automated detection of anterior crossbite on intraoral images and videos utilizing deep learning.","authors":"Zhaowu Chai, Zhengyu Wu, Chao Zhang, Jinlin Song","doi":"10.3290/j.ijcd.b5290567","DOIUrl":"10.3290/j.ijcd.b5290567","url":null,"abstract":"<p><strong>Aim: </strong>Malocclusion has emerged as a burgeoning global public health concern. Individuals with an anterior crossbite face an elevated risk of exhibiting characteristics such as a concave facial profile, negative overjet, and poor masticatory efficiency. In response to this issue, we proposed a convolutional neural network (CNN)-based model designed for the automated detection and classification of intraoral images and videos.</p><p><strong>Materials and methods: </strong>A total of 1865 intraoral images were included in this study, 1493 (80%) of which were allocated for training and 372 (20%) for testing the CNN. Additionally, we tested the models on 10 videos, spanning a cumulative duration of 124 seconds. To assess the performance of our predictions, metrics including accuracy, sensitivity, specificity, precision, F1-score, area under the precision-recall (AUPR) curve, and area under the receiver operating characteristic (ROC) curve (AUC) were employed.</p><p><strong>Results: </strong>The trained model exhibited commendable classification performance, achieving an accuracy of 0.965 and an AUC of 0.986. Moreover, it demonstrated superior specificity (0.992 vs. 0.978 and 0.956, P < 0.05) in comparison to assessments by two orthodontists. Conversely, the CNN model displayed diminished sensitivity (0.89 vs. 0.96 and 0.92, P < 0.05) relative to the orthodontists. Notably, the CNN model accomplished a perfect classification rate, successfully identifying 100% of the videos in the test set.</p><p><strong>Conclusion: </strong>The deep learning (DL) model exhibited remarkable classification accuracy in identifying anterior crossbite through both intraoral images and videos. This proficiency holds the potential to expedite the detection of severe malocclusions, facilitating timely classification for appropriate treatment and, consequently, mitigating the risk of complications.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"0"},"PeriodicalIF":1.8,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140872173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fabio Rizzante, Edgar Maenosono, Ana Flávia Borges, Juliana Bombonatti, Sorin Teich, Adilson Furuse, Sérgio Ishikiriama
{"title":"Influence of thickness and restorative system on the mechanical behavior of CAD/CAM minimally invasive occlusal veneers - in vitro study.","authors":"Fabio Rizzante, Edgar Maenosono, Ana Flávia Borges, Juliana Bombonatti, Sorin Teich, Adilson Furuse, Sérgio Ishikiriama","doi":"10.3290/j.ijcd.b5290647","DOIUrl":"10.3290/j.ijcd.b5290647","url":null,"abstract":"<p><strong>Aim: </strong>The aim of this study was to evaluate the physical-mechanical behavior of the occlusal veneers when subjected to thermomechanical cycling.</p><p><strong>Materials and methods: </strong>Sixty specimens were divided into 04 groups (n=15 per group), according with the different restorative materials and thicknesses: material - lithium dissilicate LD (IPS e.max CAD, Ivoclar Vivadent) and nano- ceramic-resins NCR (ESPE Lava Ultimate, 3M); thickness - 0.6 and 1.2mm. The occlusal veneers were bonded over human flattened fresh extracted molars with dual-polymerizing luting agent (Variolink N, Ivoclar Vivadent and RelyX Ultimate 3M) using the respective adhesive system following the selective-etch technique (self-etch in dentin and total etch in enamel). The resin cement was light cured for 40 seconds each face, using a LED light cure equipment (BlueStar II, Microdont, 1100 mW/cm2). The response variables consisted of veneer survival rates (crack formation, catastrophic cracks and debonding) when subjected to thermal cycling from 5° to 55° C and simultaneous mechanical cycling performed at load intensities of 100, 200, 300, 400 and 450N for 20,000 cycles each.</p><p><strong>Result: </strong>Data were submitted to the Kruskall Wallis test and Pairwise Comparison, adopting a significance level of 5%. NCRs presented a lower incidence of failures (p<0.05) when compared to LD. According to thickness factor, 1.2mm thick occlusal veneers withstand higher cycling loads.</p><p><strong>Conclusion: </strong>NCR occlusal veneers with 1.2mm thickness presented superior physical-mechanical behavior than lithium disilicate and 0.6mm restorations.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"0"},"PeriodicalIF":1.8,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140874959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ozden Melis Durmaz Yilmaz, Murat Tasyurek, Hasan Onder Gumus
{"title":"Evaluation of different color measurement methods for determining tooth color.","authors":"Ozden Melis Durmaz Yilmaz, Murat Tasyurek, Hasan Onder Gumus","doi":"10.3290/j.ijcd.b5290621","DOIUrl":"10.3290/j.ijcd.b5290621","url":null,"abstract":"<p><strong>Aim: </strong>The purpose of this study is to develop software at a low cost that enables the detection of tooth colors by capturing photographs using various devices, and to compare its effectiveness with existing expensive methods.</p><p><strong>Material and methods: </strong>A total of 60 anterior central incisor teeth from 30 individuals were included in the study. The CIELAB values (L,a,b) of each tooth were measured using a spectrophotometer, which is considered the gold standard. Subsequently, photographs of the teeth were taken using four different smartphones (iPhone- Xiaomi) and one digital camera (Canon). These images were then subjected to image processing techniques and compared with measurements obtained through computer-based analysis in order to assess the correlation. Data with three or more groups, the Kruskal-Wallis H test was utilized, and multiple comparisons were conducted using the Dunn test. A significance level of p<0.05 was considered.</p><p><strong>Results: </strong>Upon examining the results of multiple comparisons, a statistically significant difference was observed (p<0.001) between the DeltaE values obtained from the camera of the iPhone and those obtained from the Canon DSLR and Xiaomi cameras. The iPhone cameras yielded result values ranging from 2.68 to 2.90 for DeltaE.</p><p><strong>Conclusions: </strong>It is reported that color determination methods based on image processing of photographs taken with iPhone mobile phones could potentially gain an advantageous position in routine clinical practice, as compared to spectrophotometry.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"0"},"PeriodicalIF":1.8,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140852488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maria Sykara, Panagiotis Ntovas, Nikolaos Markou, Phoebus Madianos, Spyridon Vassilopoulos
{"title":"Individualized digitally designed surgical template for guided soft tissue surgery in cases with severe gingival enlargement: A clinical application in hereditary gingival fibromatosis.","authors":"Maria Sykara, Panagiotis Ntovas, Nikolaos Markou, Phoebus Madianos, Spyridon Vassilopoulos","doi":"10.3290/j.ijcd.b5004083","DOIUrl":"10.3290/j.ijcd.b5004083","url":null,"abstract":"<p><strong>Aim: </strong>The purpose of this study was to present the use of computer-assisted periodontal surgery utilizing a novel surgical guide for cases with severe gingival enlargement through a clinical application in a patient with hereditary gingival fibromatosis.</p><p><strong>Materials and methods: </strong>The treatment plan included nonsurgical periodontal therapy, surgical periodontal treatment, and regular periodontal maintenance before the initiation of orthodontic treatment. Due to the increased soft tissue thickness, a surgical guide with a novel design was fabricated to facilitate the periodontal surgery since most of the patient's teeth were malpositioned and underexposed due to fibromatosis. For this purpose, the patient's intraoral scan was merged with a CBCT image in order to plan surgical excisions based on the anatomy of the teeth and the bone contour.</p><p><strong>Results: </strong>The customized surgical guide facilitated the gingivectomy by controlling not only the shape of the initial incisions but also their orientation toward the level of the cementoenamel junction, improving the efficiency of the clinical time compared with freehand surgery and assisting in the verification of the final soft tissue shape, based on the treatment plan.</p><p><strong>Conclusion: </strong>Digital technology through the superimposition of multiple data sets can assist in the diagnosis and multidisciplinary management of cases with gingival fibromatosis. The proposed design of the surgical guide can facilitate soft tissue surgery based on the digital treatment plan, leading to more predictable management of the soft tissue, especially in patients with severe gingival enlargement, as in cases with hereditary gingival fibromatosis or drug-induced gingival overgrowth.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"27 1","pages":"99-107"},"PeriodicalIF":1.7,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140289348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Younghoo Lee, Youngchul Jung, Yeawon Choi, Yuyeon Kim, Sangbaek Kim, Seoung-Jin Hong, HyeongSeob Kim, Ahran Pae
{"title":"Accuracy of impression methods through the comparison of 3D deviation between implant fixtures.","authors":"Younghoo Lee, Youngchul Jung, Yeawon Choi, Yuyeon Kim, Sangbaek Kim, Seoung-Jin Hong, HyeongSeob Kim, Ahran Pae","doi":"10.3290/j.ijcd.b3836589","DOIUrl":"10.3290/j.ijcd.b3836589","url":null,"abstract":"<p><strong>Aim: </strong>To compare the accuracy of three impression methods by comparing the distance between the reference points of the implant fixture, especially in curved maxillary anterior teeth.</p><p><strong>Materials and methods: </strong>Implant fixtures were placed in the maxillary central incisor and canine regions. A maxillary master cast was made using a model scanner and 3D printer. Ten impressions were taken from the three experimental groups constructed (group P: pick-up impression coping; group I: scan body with an intraoral scanner; group B: bite impression coping). The distance between the reference points, the angle between the scan bodies, and displacement of the 3D surface area were measured.</p><p><strong>Results: </strong>The distances between the reference points were significantly different between groups I and B in the maxillary incisors, and between group P and the other two groups in the maxillary canines. Group P had the least amount of displacement in both fixtures. Both fixtures showed the highest displacement in group B. Displacement of the 3D surface area in the maxillary incisors showed no significant difference between the groups. There was a significant difference in the maxillary canines between groups P and I.</p><p><strong>Conclusions: </strong>In the present study, all three implant impression methods showed changes in the position and angle of the fixture compared with the master cast. The highest accuracy was shown by the impression method using the pick-up impression coping, but the impression method using the intraoral scanner also showed clinically acceptable accuracy. It should be noted that errors may occur when taking impressions using a bite impression coping.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"9-18"},"PeriodicalIF":1.7,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10613841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Paul Hofmann, Andreas Kunz, Franziska Schmidt, Florian Beuer, Dirk Duddeck
{"title":"Segmentation of process-related contaminations on two-piece abutments using pixel-based machine learning: a new quantification approach?","authors":"Paul Hofmann, Andreas Kunz, Franziska Schmidt, Florian Beuer, Dirk Duddeck","doi":"10.3290/j.ijcd.b3916799","DOIUrl":"10.3290/j.ijcd.b3916799","url":null,"abstract":"<p><strong>Purpose: </strong>A reference method for quantifying contaminations on two-piece abutments manufactured using CAD/CAM has not yet been established. In the present in vitro study, a pixel--based machine learning (ML) method for detecting contamination on customized two-piece abutments was investigated and embedded in a semiautomated quantification pipeline.</p><p><strong>Materials and methods: </strong>Forty-nine CAD/CAM zirconia abutments were fabricated and bonded to a prefabricated titanium base. All samples were analyzed for contamination by scanning electron microscopy (SEM) imaging followed by pixel--based ML and thresholding (SW) for contamination detection; quantification was performed in the postprocessing pipeline. Wilcoxon signed-rank test and Bland-Altmann plot were applied to compare both methods. The contaminated area fraction was recorded as a percentage.</p><p><strong>Results: </strong>There was no statistically significant difference between the percentages of contamination areas (median = 0.004) measured with ML (median = 0.008) and with SW (median = 0.012), asymptotic Wilcoxon test: P = 0.22. The Bland-Altmann plot demonstrated a mean difference of -0.006% (95% confidence interval [CI] from -0.011% to 0.0001%) with increased values from a contamination area fraction of > 0.03% for ML.</p><p><strong>Conclusion: </strong>Both segmentation methods showed comparable results in evaluating surface cleanliness; pixel-based ML is a promising assessment tool for detecting external contaminations on zirconia abutments. Further studies are required to investigate the clinical performance of this tool.</p>","PeriodicalId":48666,"journal":{"name":"International Journal of Computerized Dentistry","volume":"0 0","pages":"89-97"},"PeriodicalIF":1.7,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10754785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}