Objective: Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs).
Methods: Three CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with 1000 and 200 images, respectively. Four clinical raters with different levels of experience with ultrasound tested the networks using the other 200 images. In addition to the comparison of the best approach with each rater, we also employed the simultaneous truth and performance level estimation (STAPLE) algorithm to estimate a ground truth based on all labelings by four clinical raters. The final CEJ location estimate was obtained by taking the first moment of the posterior probability computed using the STAPLE algorithm. The study also computed the machine learning-measured CEJ-alveolar bone crest distance.
Results: Quantitative evaluations of the 200 images showed that the comparison of the best approach with the STAPLE-estimate yielded a mean difference (MD) of 0.26 mm, which is close to the comparison with the most experienced nonclinical rater (MD=0.25 mm) but far better than the comparison with clinical raters (MD=0.27-0.33 mm). The machine learning-measured CEJ-alveolar bone crest distances correlated strongly (R = 0.933, p < 0.001) with the manual clinical labeling and the measurements were in good agreement with the 95% Bland-Altman's lines of agreement between -0.68 and 0.57 mm.
Conclusions: The study demonstrated the feasible use of machine learning methodology to localize CEJ in ultrasound images with clinically acceptable accuracy and reliability. Likelihood-weighted ground truth by combining multiple labels by the clinical experts compared favorably with the predictions by the best deep CNN approach.
Clinical Significance: Identification of CEJ and its distance from the alveolar bone crest play an important role in the evaluation of periodontal status. Machine learning algorithms can learn from complex features in ultrasound images and have potential to provide a reliable and accurate identification in subsecond. This will greatly assist dental practitioners to provide better point-of-care to patients and enhance the throughput of dental care.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.jdent.2021.103752 | DOI Listing |
Anal Methods
January 2025
School of Future Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, China.
Near-infrared (NIR) spectroscopy, with its advantages of non-destructive analysis, simple operation, and fast detection speed, has been widely applied in various fields. However, the effectiveness of current spectral analysis techniques still relies on complex preprocessing and feature selection of spectral data. While data-driven deep learning can automatically extract features from raw spectral data, it typically requires large amounts of labeled data for training, limiting its application in spectral analysis.
View Article and Find Full Text PDFAnal Chem
January 2025
Research Center for Analytical Sciences, Department of Chemistry, College of Sciences, Northeastern University, Box 332, Shenyang 110819, China.
The advancement of lanthanide fingerprint sensors characterized by targeted emission responses and low self-fluorescence interference for the detection of biothiols is of considerable importance for the early diagnosis and treatment of cancer. Herein, the lanthanide "personality function tailoring" HOF composite sensor array is designed for the specific discrimination of biothiols (GSH, Cys, and Hcy) based on the activation of various luminescent molecules, such as r-AuNCs/luminol via HOF surface proximity. Lumi-HOF@Ce serves as a versatile platform for catalyzing the oxidation of -phenylenediamine (OPD) to generate yellow fluorescent oligomers, accompanied by the fluorescence attenuation of luminol.
View Article and Find Full Text PDFAm J Cancer Res
December 2024
Department of Reproductive Medicine, The First Affiliated Hospital, Jinan University Guangzhou 510000, Guangdong, China.
This study aims to construct and optimize risk prediction models for lymph node metastasis (LNM) in endometrial carcinoma (EC) patients, thus improving the identification of patients at high risk of LNM and further providing accurate support for clinical decision-making. This retrospective analysis included 541 cases of EC treated at The First Affiliated Hospital, Jinan University between January 2017 and January 2022. Various clinical and pathological variables were incorporated, including age, body mass index (BMI), pathological grading, myometrial invasion, lymphovascular space invasion (LVSI), estrogen receptor (ER) and progesterone receptor (PR) levels, and tumor size.
View Article and Find Full Text PDFHeart Rhythm O2
December 2024
Pfizer Inc, New York, New York.
Background: Prediction models for atrial fibrillation (AF) may enable earlier detection and guideline-directed treatment decisions. However, model bias may lead to inaccurate predictions and unintended consequences.
Objective: The purpose of this study was to validate, assess bias, and improve generalizability of "UNAFIED-10," a 2-year, 10-variable predictive model of undiagnosed AF in a national data set (originally developed using the Indiana Network for Patient Care regional data).
A significant advancement in synthetic biology is the development of synthetic gene circuits with predictive Boolean logic. However, there is no universally accepted or applied statistical test to analyze the performance of these circuits. Many basic statistical tests fail to capture the predicted logic (OR, AND, etc.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!