Search

The magnetically controlled growing rod technique is an effective surgical treatment for children who have early-onset scoliosis. The length of the instrumented growing rods is adjusted regularly to compensate for the normal growth of these patients. Manual measurement of rod length on posteroanterior spine radiographs is subjective and time-consuming. A machine learning (ML) system using a deep learning approach was developed to automatically measure the adjusted rod length. Three ML models-rod model, 58 mm model, and head-piece model-were developed to extract the rod length from radiographs. Three-hundred and eighty-seven radiographs were used for model development, and 60 radiographs with 118 rods were separated for final testing. The average precision (AP), the mean absolute difference (MAD) ± standard deviation (SD), and the inter-method correlation coefficient (ICC [2,1] ) between the manual and artificial intelligence (AI) adjustment measurements were used to evaluate the developed method. The AP of the 3 models were 67.6%, 94.8%, and 86.3%, respectively. The MAD ± SD of the rod length change was 0.98 ± 0.88 mm, and the ICC [2,1] was 0.90. The average time to output a single rod measurement was 6.1 s. The developed AI provided an accurate and reliable method to detect the rod length automatically., (© 2024. International Federation for Medical and Biological Engineering.)

Objective: To develop and validate machine learning algorithms to automatically extract the rod length of the magnetically controlled growing rod from ultrasound images (US) in a pilot study., Methods: Two machine-learning (ML) models, called the "Boundary model" and "Rod model," were developed to identify specific rod segments on ultrasound images. The models were developed utilizing Mask Regional Convolutional Neural Networks (Mask RCNN). Ninety US images were acquired from 23 participants who had early onset scoliosis (EOS) surgeries; among those, 70 were used for model development, including training and validation, and 20 were used for testing by comparing the AI-based vs. manual measurements., Results: The average precision (AP) of the ML models was 88.5% and 60.2%, respectively. The inter-method correlation coefficient (ICC) was 0.98, and the mean absolute difference ± standard deviation (MAD ± SD) between AI and manual measurements was 0.86 ± 1.0 mm. The Bland-Altman analysis showed no bias, and 90% of the data were within the 95% confidence interval. The automated method was reliable, accurate, and fast. Measurements were displayed in 4.6 seconds after the US image was inputted., Conclusion: This was the first AI-based method to measure the MCGR rod length on US images automatically., Competing Interests: Conflict of interest The authors assert that they do not have any conflicting interests., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

Innovative intraoral ultrasound devices with smart artificial intelligence-based identification for dento-anatomy could provide crucial information for oral health diagnosis and treatment and shed light on real-time detection of developmental dentistry. However, the grand challenge is that the current ultrasound technologies are meant for external use due to their bulkiness and low frequency. We report a compact versatile ultrasound intraoral device that consists of a rotational probe head robustly pivoted around a hand-held and portable handle for real-time imaging of intraoral anatomy using high-frequency ultrasonography (up to 25 MHz). The intraoral ultrasound device that could be adjusted for various orientations of the imaging planes by rotating the head provides real-time, high-resolution ultrasonograms of intraoral structures, including dento-periodontium of most tooth types and maxillary palate. Machine learning-based algorithms are integrated to automate the identification of important structures, including alveolar bone and cementum-enamel junction. The intraoral ultrasound device smartened with artificial intelligence could innovate oral health diagnosis and treatment plans toward precision health and patient care.

Measuring the kyphotic angle (KA) and lordotic angle (LA) on lateral radiographs is important to truly diagnose children with adolescent idiopathic scoliosis. However, it is a time-consuming process to measure the KA because the endplate of the upper thoracic vertebra is normally difficult to identify. To save time and improve measurement accuracy, a machine learning algorithm was developed to automatically extract the KA and LA. The accuracy and reliability of the T1-T12 KA, T5-T12 KA, and L1-L5 LA were reported. A convolutional neural network was trained using 100 radiographs with data augmentation to segment the T1-L5 vertebrae. Sixty radiographs were used to test the method. Accuracy and reliability were reported using the percentage of measurements within clinical acceptance (≤9°), standard error of measurement (SEM), and inter-method intraclass correlation coefficient (ICC 2,1 ). The automatic method detected 95 % (57/60), 100 %, and 100 % for T1-T12 KA, T5-T12 KA, and L1-L5 LA, respectively. The clinical acceptance rate, SEM, and ICC 2,1 for T1-T12 KA, T5-T12 KA, and L1-L5 LA were (98 %, 0.80°, 0.91), (75 %, 4.08°, 0.60), and (97 %, 1.38°, 0.88), respectively. The automatic method measured quickly with an average of 4 ± 2 s per radiograph and illustrated how measurements were made on the image, allowing verifications by clinicians., Competing Interests: Declaration of competing interest The authors have no conflicts of interest to declare., (Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Delineation of alveolar bone aids the diagnosis and treatment of periodontal diseases. In current practice, conventional 2D radiography and 3D cone-beam computed tomography (CBCT) imaging are used as the non-invasive approaches to image and delineate alveolar bone structures. Recently, high-frequency ultrasound imaging is proposed as an alternative to conventional imaging methods to prevent the harmful effects of ionizing radiation. However, the manual delineation of alveolar bone from ultrasound imaging is time-consuming and subject to inter and intraobserver variability. This study proposes to use a convolutional neural network-based machine learning framework to automatically segment the alveolar bone from ultrasound images. The proposed method consists of a homomorphic filtering based noise reduction and a u-net machine learning framework for automated delineation. The proposed method was evaluated over 15 ultrasound images of tooth acquired from procine specimens. The comparisons against manual ground truth delineations performed by three experts in terms of mean Dice score and Hausdorff distance values demonstrate that the proposed method yielded an improved performance over a recent state of the art graph cuts based method.

• A precision feeding system sometimes records anomalous real-time body weight data. • A supervised learning method was developed for anomaly detection. • Data distribution and features regarding the feeding activity were considered. • This method was more effective than 4 other common anomaly detection methods. A precision feeding (PF) system is an intelligent computer-controlled feeding system that can be used to feed individual broilers, breeders or layers automatically based on measuring real-time body weight (BW). Vast amounts of real-time BW data can be generated every day when birds visit a PF station. However, anomalous observations occurred in real-time BW observations, which were caused by multiple birds entering the station at the same time, upward or downward variation in scale measurement in the recorded data due to the movement of the bird, or a misread for radio frequency identification tag. Known anomalous data should be removed because they have a negative impact on the interpretation of the data. Manually cleaning the anomalies is accurate, but it is time-consuming and labor-intensive. Statistical methods and unsupervised machine learning methods are effective in detecting anomalies to some extent because they just check data distribution. The current study reported a supervised machine learning method to detect anomalies in real-time BW recorded by the PF system. Real-time BW data of 5 broiler breeders from day 15 to 306 were checked and the anomalies were manually labeled. Variables regarding the statistical distribution of data and features regarding the feeding activity recorded by the PF system in each day were extracted from the dataset. Among the 4 machine learning algorithms including k-nearest neighbor (KNN), random forest classifier (RF), support vector machine (SVM), and artificial neural network (ANN), RF produced the highest F1 score (0.9712) and area under the precision-recall curve (0.9948). Compared with 4 other common anomaly detection methods including Z-scores, interquartile range (IQR), density-based spatial clustering of applications with noise (DBSCAN), and local outlier factor (LOF), RF had a higher average F1 score (0.9448), which indicated that RF was a more effective anomaly detection algorithm for this type of data. [ABSTRACT FROM AUTHOR]

Migration percentage (MP) is the gold standard to assess the severity of hip displacement in children with cerebral palsy, which is measured on anteroposterior hip radiographs. Recently, the ultrasound (US) method has been developed as a safe alternative imaging modality to image and monitor children’s hips. However, measuring MP on US images (MPUS) is time-consuming, challenging, and user-dependent. This study aimed to develop machine learning algorithms to automatically measure MPUS and validate the algorithms with MPXray. A combination of signal filtering, convolution neural networks (CNNs), and UNets was applied to segment the regions of interest (ROI), detect edges or feature points, and select the desired US frames. A total of 62 hips including both coronal and transverse scans per hip were acquired, out of which 36 with applying augmentation method were utilized for training, 8 for validation, and 18 for testing. The intraclass correlation coefficient (ICC2,1) and the mean absolute difference (MAD) between the automated MPUS versus manual MPXray were 0.86 and 6.5% ± 5.5%, respectively. To report the MPUS, it took an average of 104 s/hip. This preliminary result demonstrated that MPUS was able to extract automatically within 2 min with a clinical acceptance accuracy (10%).Graphical Abstract: Migration percentage (MP) is the gold standard to assess the severity of hip displacement in children with cerebral palsy, which is measured on anteroposterior hip radiographs. Recently, the ultrasound (US) method has been developed as a safe alternative imaging modality to image and monitor children’s hips. However, measuring MP on US images (MPUS) is time-consuming, challenging, and user-dependent. This study aimed to develop machine learning algorithms to automatically measure MPUS and validate the algorithms with MPXray. A combination of signal filtering, convolution neural networks (CNNs), and UNets was applied to segment the regions of interest (ROI), detect edges or feature points, and select the desired US frames. A total of 62 hips including both coronal and transverse scans per hip were acquired, out of which 36 with applying augmentation method were utilized for training, 8 for validation, and 18 for testing. The intraclass correlation coefficient (ICC2,1) and the mean absolute difference (MAD) between the automated MPUS versus manual MPXray were 0.86 and 6.5% ± 5.5%, respectively. To report the MPUS, it took an average of 104 s/hip. This preliminary result demonstrated that MPUS was able to extract automatically within 2 min with a clinical acceptance accuracy (10%). [ABSTRACT FROM AUTHOR]

• A machine learning method was used to predict oviposition events. • A random forest classification model was developed for prediction. • Birds were fed by a precision feeding system which can record visiting information. • Egg laying events were linked to real-time behaviour of free-run broiler breeders. • The overall accuracy of the prediction model was around 85%. In group-housed poultry, hormone and environment modulated variability in the processes of follicle maturation and egg formation make it difficult to predict a daily egg-laying event (oviposition). Recording daily egg laying events has required individual cages or expensive technology such as RFID equipped nests or labor intensive trap nests. The current study implemented the random forest classification algorithm to predict oviposition events of 202 free run Ross 708 broiler breeder hens fed by a precision feeding system from week 21 to 55, based on a dataset recording information of all visits to the station. The raw dataset from the precision feeding system was processed for 6 classes of features (34 features in total) in relation to feeding activity and real-time body weight of birds. The dataset of the features was then combined with a corresponding daily individual oviposition record. The processed data were shuffled and separated into 2 subsets: 90% for training, and 10% for testing. Important features were selected using random forest-recursive feature elimination with 5-fold cross-validation, and 28 features were selected to build a random forest classification model. Overall accuracy of the model using the testing samples was 0.8482, and out-of-bag score was 0.8510. Precision (a measure of purity in retrieving) of no egg-laying and egg-laying, recall (a measure of completeness in retrieving) of no egg-laying and egg-laying were 0.8814, 0.8090, 0.8520 and 0.8453, respectively. The Kappa coefficient of the model was 0.6931, indicating substantial agreement (substantial agreement range: 0.61–0.80). This model was able to identify whether a free run broiler breeder laid an egg or not on a certain day during the laying period with around 85% accuracy. [ABSTRACT FROM AUTHOR]

• Fully automatic axial vertebral rotation measurements on radiographs. • 81% of the measurements are within clinical acceptance error (5°). • It only takes 8.8 s to detect vertebral rotation per vertebra. Adolescent idiopathic scoliosis is a 3D lateral spinal curvature coupled with axial vertebral rotation (AVR). Measuring AVR during clinic is important because it affects treatment options and predicts the risk of scoliosis progression. However, manual measurements are time consuming and have high inter-rater and intra-rater errors. This study aimed to develop a machine learning algorithm based on convolutional neural networks (CNNs) to automatically calculate AVR on posteroanterior radiographs using three different segmentations including spinal column, individual vertebra, and pedicles. Separate labeling and training processes were performed on each of the developed segmentation algorithms. The final machine learning software was tested on 221 vertebrae from 17 spinal radiographs. An experienced rater with over 25 years of experience measured the 221 vertebral rotations manually. By comparing the manual and the fully automatic measurements, 81% (178/221) of the automatic measurements were within the clinical acceptance error (±5°). The mean absolute difference and the standard deviation between the manual and automatic measurements was 4.3° ± 5.7°. Based on the Bland-Altman plot, the manual and automatic measurements had a strong correlation and no bias. The error did not relate to the severity of the rotation. This method is fully automatic, and the result is comparable to others. [ABSTRACT FROM AUTHOR]