Mean Pearson Correlation Research Articles

Using CT images to assist the segmentation of MR images via generalization: Segmentation of the renal parenchyma of renal carcinoma patients.

Developing deep learning models for segmenting medical images in multiple modalities with less data and annotation is an attractive and challenging task, which was previously discussed as being accomplished by complex external frameworks for bridging the gap between different modalities. Exploring the generalization ability of networks in medical images in different modalities could provide more simple and accessible methods, yet comprehensive testing could still be needed. To explore the feasibility and robustness of using computed tomography (CT) images to assist the segmentation of magnetic resonance (MR) images via the generalization, in the segmentation of renal parenchyma of renal cell carcinoma (RCC) patients. Nephrographic CT images and fat-suppressed T2-weighted (fs-T2W) images were retrospectively collected. The pure CT dataset included 116 CT images. Additionally, 240 MR images were randomly divided into subsets A and B. From subset A, three training datasets were constructed, each containing 40, 80, and 120 images, respectively. Similarly, three datasets were constructed from subset B. Subsequently, datasets with mixed modality were created by combining these pure MR datasets with the 116 CT images. The 3D-UNET models for segmenting the renal parenchyma in two steps were trained using these 13 datasets: segmenting kidneys and then the renal parenchyma. These models were evaluated in internal MR (n=120), CT (n=65) validation datasets, and an external validation dataset of CT (n=79), using the mean of the dice similarity coefficient (DSC). To demonstrate the robustness of generalization ability over different proportions of modalities, we compared the models trained with mixed modality in three different proportions and pure MR, using repeated measures analysis of variance (RM-ANOVA). We developed a renal parenchyma volume quantification tool by the trained models. The mean differences and Pearson correlation coefficients between the model segmentation volume and the ground truth segmentation volume were calculated for its evaluation. The mean DSCs of models trained with 116 data in CT in the validation of MR were 0.826, 0.842, and 0.953, respectively, for the predictions of kidney segmentation model on whole image, renal parenchymal segmentation model on kidneys with RCC and without RCC. For all models trained with mixed modality, the means of DSC were above 0.9, in all validations of CT and MR. According to the results of the comparison between models trained with mixed modality and pure MR, the means of DSC of the former were significantly greater or equal to the latter, at all three different proportions of modalities. The differences of volumes were all significantly lower than one-third of the volumetric quantification error of a previous method, and the Pearson correlation coefficients of volumes were all above 0.96 on kidneys with and without RCC of three validations. CT images could be used to assist the segmentation of MR images via the generalization, with or without the supervision of MR data. This ability showed acceptable robustness. A tool for accurately measuring renal parenchymal volume on CT and MR images was established.

Accurate evaluation on peak shaving capacity of combined-heat-and-power thermal power units based on physical information neural network

The high proportion of new energy requires the power system to have sufficient flexibility and peak shaving capacity. The combined-heat-and-power thermal power unit is one of the main flexibility resources. Accurately evaluating the peak shaving capability from thermal power units is of great significance for power system scheduling. However, there are some problems in the previous evaluation models. Fully mechanistic models may exhibit poor accuracy due to component degradation and other reasons, while fully data-driven models may exhibit poor generalization performance due to limited training conditions. To address these issues, this paper first uses physical information neural network to fuse thermal power mechanisms and operational data, and constructs a high-precision and strong-generalization power output evaluation model. Then, error indicators and generalization indicators are used to validate the effectiveness and superiority of the model. In the test set, the mean absolute error, root mean square error and Pearson correlation coefficient of the model are1.633 MW, 1.971 MW and 0.9643, respectively. Based on this model, the peak shaving capacity range of the target thermal power plant under different heating demands is calculated. Finally, the experiment analyzed the real-time peak shaving capability and peak shaving margin.

Average Wind Speed Prediction in Giresun-Kümbet Plateau Region with Artificial Neural Networks

In order to estimate the electricity generation capacity and schedule the supply for vendor needs, wind speed prediction is crucial for wind power plant frameworks. Prior to the installation of the wind power plants, a reliable wind behaviour model is neccesary. To have such a model, wind data is recorded periodically. In this study, hourly recorded meteorological data of actual pressure, relative humidity, temperature, wind direction and average wind speed for the year 2023 were obtained from the General Directorate of Meteorology for the Kümbet plateau region of Giresun province. The data is used to accurately predict the future wind speed for the region. Matlab Artificial Neural Networks (ANN) is utilized. Actual pressure, relative humidity, temperature and wind direction parameters are defined as input in the prediction process. 85% of the data set is used as training data and remainin 15% data set is used for testing data. An optimization process is applied to determine the number of hidden layers to have the prediction value with the smallest error. Bayesian Regularization training process was performed by seeing that the hidden layer has the lowest error at 90 neurons. Performance evaluations are performed with Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Pearson Correlation Coefficient (R) metrics. The values of the metrics for the test data are 26.7137, 5.1685, 3.5055 and 0.7457 respectively. The results show that, ANN based model is useful for the wind speed prediction over the region.

Improving GNSS-IR Sea Surface Height Accuracy Based on a New Ionospheric Stratified Elevation Angle Correction Model

Approximately 71% of the Earth’s surface is covered by vast oceans. With the exacerbation of global climate change, high-precision monitoring of sea surface height variations is of vital importance for constructing global ocean gravity fields and preventing natural disasters in the marine system. Global Navigation Satellite System Interferometry Reflectometry (GNSS-IR) sea surface altimetry is a method of inferring sea surface height based on the signal-to-noise ratio of satellite signals. It enables the retrieval of sea surface height variations with high precision. However, navigation satellite signals are influenced by the ionosphere during propagation, leading to deviations in the measured values of satellite elevation angles from their true values, which significantly affects the accuracy of GNSS-IR sea surface altimetry. Based on this, the contents of this paper are as follows: Firstly, a new ionospheric stratified elevation angle correction model (ISEACM) was developed by integrating the International Reference Ionosphere Model (IRI) and ray tracing methods. This model aims to improve the accuracy of GNSS-IR sea surface altimetry by correcting the ionospheric refraction effects on satellite elevation angles. Secondly, four GNSS stations (TAR0, PTLD, GOM1, and TPW2) were selected globally, and the corrected sea surface height values obtained using ISEACM were compared with observed values from tide gauge stations. The calculated average Root Mean Square Error (RMSE) and Pearson Correlation Coefficient (PCC) were 0.20 m and 0.83, respectively, indicating the effectiveness of ISEACM in sea surface height retrieval. Thirdly, a comparative analysis was conducted between sea surface height retrieval before and after correction using ISEACM. The optimal RMSE and PCC values with tide gauge station observations were 0.15 m and 0.90, respectively, representing a 20.00% improvement in RMSE and a 4.00% improvement in correlation coefficient compared to traditional GNSS-IR retrieval heights. These experimental results demonstrate that correction with ISEACM can effectively enhance the precision of GNSS-IR sea surface altimetry, which is crucial for accurate sea surface height measurements.

Non-invasive measurement of wall shear stress in microfluidic chip for osteoblast cell culture using improved depth estimation of defocus particle tracking method.

The development of a non-invasive method for measuring the internal fluid behavior and dynamics of microchannels in microfluidics poses critical challenges to biological research, such as understanding the impact of wall shear stress (WSS) in the growth of a bone-forming osteoblast. This study used the General Defocus Particle Tracking (GDPT) technique to develop a non-invasive method for quantifying the fluid velocity profile and calculated the WSS within a microfluidic chip. The GDPT estimates particle motion in a three-dimensional space by analyzing two-dimensional images and video captured using a single camera. However, without a lens to introduce aberration, GDPT is prone to error in estimating the displacement direction for out-of-focus particles, and without knowing the exact refractive indices, the scaling from estimated values to physical units is inaccurate. The proposed approach addresses both challenges by using theoretical knowledge on laminar flow and integrating results obtained from multiple analyses. The proposed approach was validated using computational fluid dynamics (CFD) simulations and experimental video of a microfluidic chip that can generate different WSS levels under steady-state flow conditions. By comparing the CFD and GDPT velocity profiles, it was found that the Mean Pearson Correlation Coefficient is 0.77 (max = 0.90) and the Mean Intraclass Correlation Coefficient is 0.66 (max = 0.82). The densitometry analysis of osteoblast cells cultured on the designed microfluidic chip for four days revealed that the cell proliferation rate correlates positively with the measured WSS values. The proposed analysis can be applied to quantify the laminar flow in microfluidic chip experiments without specialized equipment.

Teachers’ Capacity Building Through Professional Development Training Program: A Perceived Perspective of New Appointed Faculty of Ghazi University

This research on teachers' capacity building through professional development training programs is crucial as it addresses the evolving needs of newly appointed faculty at Ghazi University. In a rapidly changing educational landscape, professional development is key to enhancing teaching effectiveness, fostering pedagogical innovation, and improving student outcomes. The leadership of Ghazi University decided to organize the training session for newly appointed faculty to update their professionalism for the quality work at work place. This responsibility was given to the department of education, Ghazi University to conduct the capacity building session. Insightful support was ensured by the university bodies i.e. director ORIC, director QEC, director FAD, director academic, director IT, controller examinations and registrar office of the university. Population was confined to newly appointed faculty at Ghazi University in 2021 that was 133 in total. The census sampling technique was used to collect the data as the whole population was approached. Self-developed questionnaire at five point Likert type scale was used to gather the information. Cronbach alpha value of the tool was 0.948. Only 100 respondents responded. Analysis was done by applying mean score, standard deviation, Pearson correlation and multiple regression analysis. There was positive and significant correlation of teachers’ capacity building through professional development training program at university level. It was recommended that such training program must be conducted at university level for effective quality work.

Impact of Emerging Deep Learning-Based MR Image Reconstruction Algorithms on Abdominal MRI Radiomic Features.

This study aims to evaluate, on one MRI vendor's platform, the impact of deep learning (DL)-based reconstruction techniques on MRI radiomic features compared to conventional image reconstruction techniques. Under IRB approval and informed consent, we prospectively collected undersampled coronal T2-weighted MR images of the abdomen (1.5 T; Philips Healthcare) from 17 pediatric and adult subjects and reconstructed them using a conventional image reconstruction technique (compressed sensitivity encoding [C-SENSE]) and two DL-based reconstruction techniques (SmartSpeed [Philips Healthcare, US FDA cleared] and SmartSpeed with Super Resolution [SmartSpeed-SuperRes, not US FDA cleared to date]). Eight regions of interest (ROIs) across organs/tissues (liver, spleen, kidney, pancreas, fat, and muscle) were manually placed. Eighty-six MRI radiomic features were then extracted. Pearson's correlation coefficients (PCCs) and intraclass correlation coefficients (ICCs) were calculated between (A) C-SENSE versus SmartSpeed, and (B) C-SENSE versus SmartSpeed-SuperRes. To quantify the impact from the perspective of the whole MR image, cross-ROI mean PCCs and ICCs were calculated for individual radiomic features. The impact of image reconstruction on individual radiomic features in different organs/tissues was evaluated using ANOVA analyses. According to cross-ROI mean PCCs, 50 out of 86 radiomic features were highly correlated (PCC, ≥0.8) between SmartSpeed and C-SENSE, whereas only 15 radiomic features were highly correlated between SmartSpeed-SuperRes and C-SENSE reconstructions. According to cross-ROI mean ICCs, 58 out of 86 radiomic features had high agreements (ICC ≥0.75) between SmartSpeed and C-SENSE, whereas only 9 radiomic features had high agreements between SmartSpeed-SuperRes and C-SENSE reconstructions. For SmartSpeed reconstruction, the psoas muscle ROI appeared to be impacted most with the lowest median (IQR) correlation of 0.57 (0.25). The circular liver ROI was impacted most by SmartSpeed-SuperRes (PCC, 0.60 [0.22]). ANOVA analyses suggest that the impact of DL reconstruction algorithms on radiomic features varies significantly among different organs/tissues (P < 0.001). MRI radiomic features are significantly altered by DL-based reconstruction compared to a conventional reconstruction technique. The impact of DL reconstruction algorithms on radiomic features varies significantly between different organs/tissues.

SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia.

&#xD;Monitoring the depth of anaesthesia (DOA) during surgery is of critical importance. However, accurate and real-time estimation of DOA remains a challenging task. In this paper, we proposed a signal quality index (SQI) network (SQINet) for assessing the electroencephalogram (EEG) signal quality and a DOA network (DOANet) for analyzing EEG signals to precisely estimate DOA. The two networks are termed SQI-DOANet.&#xD;Approach:&#xD;The SQINet contained a shallow convolutional neural network to quickly determine the quality of the EEG signal. The DOANet comprised a feature extraction module for extracting features, a dual attention module for fusing multi-channel and multi-scale information, and a gated multilayer perceptron module for extracting temporal information. The performance of the SQI-DOANet model was validated by training and testing the model on the large VitalDB database, with the bispectral index (BIS) as the reference standard.&#xD;Main results:&#xD;The proposed DOANet yielded a Pearson correlation coefficient with the BIS score of 0.88 in the 5-fold cross-validation, with a mean absolute error (MAE) of 4.81. The mean Pearson correlation coefficient of SQI-DOANet with the BIS score in the 5-fold cross-validation was 0.82, with an MAE of 5.66.&#xD;Significance:&#xD;The SQI-DOANet model outperformed three compared methods. The proposed SQI-DOANet may be used as a new deep learning method for DOA estimation. The code of the SQI-DOANet will be made available publicly at https://github.com/YuRui8879/SQI-DOANet.&#xD.

Generating realistic infrared spectra using artificial neural networks

AbstractArtificial spectra were generated to match the different acid solubility properties of the rocks. The purpose of generating artificial spectra was to increase the number of samples available for future data processing with a convolutional neural network. The samples were collected from different geological matrices during targeted rock tests to support industrial applications. The inherent characteristics of the samples are their uneven distribution in the parameter space of the features and their limited availability for data‐intensive studies. Both data set characteristics constrain the prediction performance of the machine learning methods to estimate the unknown solubility of samples in the chosen acids. If the sample multiplication techniques are performed without considering the relationship between solubility of samples and their infrared spectra, the synthetic samples adversely impact the efficacy of the prediction method. By utilizing a dimensionality reduction technique (principal component analysis) and a neural network, we established a relationship between the solubility of the samples and their infrared spectra. Infrared spectra of the samples used for learning the model could be efficiently reproduced and infrared spectra of created samples could be generated. The reliability of the applied method has been shown by the comparison of the original and artificial spectra through a mean Pearson correlation coefficient and by comparing the closest neighbors to each other. This method can be used to create new samples and their infrared spectra, where different constraints must be met and the samples must be connected to the infrared spectrum.

The Correlation between Vocabulary Learning Strategies and Vocabulary Mastery

The purpose of this study is to determine the correlation between vocabulary learning strategies and vocabulary mastery. A questionnaire was distributed to students of class VIII A, B, C and D of SMP Advent Airmadidi to determine the level of use of vocabulary learning strategies and vocabulary mastery. To answer the research questions, descriptive mean analysis and Pearson Correlation Coefficient Correlation were used to answer the research questions. The research findings revealed that: (1) the level of students' vocabulary learning strategies was 3.41, indicating a moderate level; (2) the level of students' vocabulary mastery was 82.44 indicating good vocabulary mastery; and (3) the p value = 0.781, and r = 0.028, indicating that there was no significant correlation between vocabulary learning strategies and vocabulary mastery. The interpretation of the research findings shows that although there is no significant correlation between vocabulary learning strategies and vocabulary mastery, the use of various vocabulary learning strategies still contributes positively to students' vocabulary mastery. Therefore, teachers can expand the vocabulary learning strategies they use in the classroom, as well as provide more focused support to students in choosing and applying strategies that suit their individual learning strategies

Assimilating ASCAT normalized backscatter and slope into the land surface model ISBA-A-gs using a Deep Neural Network as the observation operator: Case studies at ISMN stations in western Europe

ASCAT normalized backscatter (σ40o) and slope (σ′) contain valuable information about soil moisture and vegetation. While σ40o has been assimilated to constrain soil moisture, sometimes together with Leaf Area Index (LAI), this study is the first to assimilate σ′ directly to constrain vegetation states. Here, we assimilate σ40o and slope σ′ into the ISBA-A-gs LSM using the Simplified Extended Kalman Filter (SEKF) using a Deep Neural Network (DNN) as the observation operator. The performances of the data assimilation (DA) and open loop (OL) are evaluated against in-situ soil moisture observations from the International Soil Moisture Network (ISMN), and LAI observations from the Copernicus Global Land Service (CGLS). Given an accurate and physically plausible observation operator, along with well-defined model and observation errors, the data assimilation system should yield improved estimates of the model states. However, results show that the DA performance is neutral compared to the OL in terms of the median unbiased root mean square error (ubRMSE) and Pearson correlation coefficient (ρ) across all validation sites. In addition, an analysis of the residuals and innovations confirms that DA had limited or no impact. This poor performance is perplexing. Furthermore, given the growing interest in the use of machine-learning-based observation operators, it is essential to understand the role that the use of the DNN may be playing in this poor performance. While representativeness errors and error specification play some part, it is demonstrated that the key factor constraining the efficacy of the SEKF is the correct estimation of the Jacobians that control the degree to which the observations update the states in the SEKF. It is argued that the DNN relating model states to satellite observations must have physically-plausible and robust Jacobians for the DNN to be effective in a data assimilation framework.

High-resolution reconstruction and correction of FY-4A precipitable water vapor in China using back propagation neural network

Precipitable water vapor (PWV) with high spatial and temporal resolution is essential for a deeper understanding of the study area's hydrological cycle and climate change. This study uses the European Center for Medium-Range Weather Forecasts Reanalysis 5 (ERA5) PWV as auxiliary verification data and proposes a reconstruction method based on back propagation neural network (BPNN) downscaling. Combining with high temporal resolution meteorological elements, digital elevation model (DEM), location, and time, reconstructed the Fengyun-4A (FY-4A) PWV data set with high spatial and temporal resolution in China was obtained. Subsequently, using the characteristics of FY-4A PWV with DEM, location, and time, a BPNN-based correction method is proposed to correct the reconstructed FY-4A PWV using the high-precision global navigation satellite system (GNSS) PWV. The results showed that the root mean square error (RMSE), Bias, and Pearson correlation coefficient (R) of the reconstructed model with respect to the FY-4A PWV are 1.32 mm, 0 mm, and 0.99, respectively. Compared with the auxiliary verification data ERA5 PWV, the RMSE, Bias, and R of the reconstructed FY-4A PWV are 0.85 mm, 0.18 mm, and 0.99, respectively. Compared with the GNSS PWV, the RMSE of the corrected FY-4A PWV is 2.44 mm, which is 28.86% lower than that of the reconstructed FY-4A PWV, the Bias is improved from −1.46 mm to 0 mm, and the R is enhanced from 0.98 to 0.99. The reconstruction and correction method of FY-4A PWV with high spatial and temporal resolution proposed in this study dramatically improves the completeness and accuracy of FY-4A PWV in China. It lays the foundation for studying rapid changes in China's hydrological cycle and climate.

A Data-Driven Model for Predictive Modeling of Vortex-Induced Vibrations of a Long-Span Bridge

Vortex-induced vibration (VIV) of long-span bridges can be of large amplitude, which can influence serviceability. Therefore, it is important to predict the response of vortex-induced vibration to aid the management of long-span bridges. A novel data-driven model is proposed to predict the time history of the dynamic response of VIV events. Specifically, the proposed model consists of gated recurrent unit (GRU) neural networks and the Newmark-beta method. GRU neural networks can perform accurate sequential prediction, and the Newmark-beta method can complement the physical meaning of the middle output of the proposed model. To aid the accurate prediction of the amplitude of VIV events, the proposed model employs weighted mean square error as the loss function, which can put more emphasis on the amplitude. The proposed model is validated on measured VIV events of a long-span suspension bridge. The weighted mean absolute percentage error and Pearson correlation coefficient of the trained model indicate the effectiveness of the proposed model.

A Fast Calibration Method for an sEMG-Based Lower Limb Joint Torque Estimation Model

The joint torque estimation model based on surface electromyography (sEMG) signals needs to recalibrate the model parameters when used for joint torque estimation at different volunteers. However, the feature transferability drops significantly in higher task-specific layers, which reduce the performance of the model. The generalization of joint torque estimation models among different volunteers has become a challenge. In this paper, a fast calibration method based on a deep adaptive regression network is proposed to reduce the frequency and time of model recalibration when volunteers change. The proposed method associates source domain (SD) data with target domain (TD) data through migration learning. The maximum mean difference (MMD) adaptive method is used to migrate the model trained in the SD dataset to the TD dataset, which avoids the recalibration required in the joint torque estimation model. The experimental results show that the proposed method can improve the migration ability of the model used for estimating joint torque and achieve the generalization application of the model on different volunteer datasets. Moreover, the proposed method can reduce the calibration operations and iterations of the model caused by volunteer changes and improve the speed of joint torque estimation. The optimal normalized root mean square error (NRMSE) and Pearson correlation coefficient (ρ) of knee extension/flexion joint torque estimation reached 0.02198/0.02565 and 0.9892/0.9839, respectively.

Effects of camera external parameters error on measurement accuracy in monocular vision

Monocular vision is widely employed in industrial measurement scenarios due to its low cost, flexibility, mature algorithms, and high reliability. However, in actual production line monocular vision measurement systems, the measured plane may be affected by motion mechanisms or device vibrations, causing it to deviate from the system calibration plane and resulting in measurement errors. Current research primarily focuses on analyzing the influence of camera internal parameters and feature extraction algorithms on measurement errors, with limited quantitative analysis of the impact of camera external parameters. To address this issue, our paper derives a mathematical expression for measurement error when rotational and translational motion occurs between the measurement and calibration planes. Theoretical analysis reveals that when the camera optical axis is perpendicular to the measurement plane, measurement error is independent of the main point coordinates of the camera’s optical axis, translation component in the measurement plane, and rotation angle around the camera’s optical axis. Instead, it exhibits a linear relationship with the translation component in the direction of the camera’s optical axis and is inversely proportional to the normalized focal length of the camera. When the optical axis of the camera is not perpendicular to the calibration plane, the measurement error exhibits a nonlinear relationship with camera’s internal and external parameters. To verify our theoretical derivation’s accuracy, we conduct measurement experiments using both industrial and telecentric lenses and analyzed rotation and translation of the measured plane separately. The measurement data was evaluated by Root Mean Square Error and Pearson Correlation Coefficient, which demonstrates that experimental and theoretical function images exhibit consistent trends, verifying our theoretical derivation’s correctness and providing a theoretical guide for improving actual visual measurement accuracy.

Nutritional and Functional Properties of Quinoa (Chenopodium quinoa Willd.) Chimborazo Ecotype: Insights into Chemical Composition

Quinoa is known for its high nutritional value and adaptability; however, there is a lack of data about the chemical composition of quinoa produced in Ecuador, especially the Chimborazo ecotype. Our research aims to evaluate the nutritional components of Chimborazo quinoa. This knowledge (chemical composition) can help to improve cultivation and farmers’ understanding. Samples were collected from 49 plots at four altitude ranges (3000–3200; 3201–3300; 3301–3400; 3401–3533) m.a.s.l. Each sample of 2 kg quinoa was cleaned, dried (32 °C/15 h), and stored at −20 °C before analyzing water activity, proximate composition, mineral content, antioxidant activity, and functional compounds. The data were analyzed using ANOVA and mean comparison, Pearson correlation, and principal component analysis. The Chimborazo ecotype shows protein content comparable to or exceeding other global quinoa cultivars. Statistical analysis revealed that altitude had a minimal influence on quinoa’s chemical composition, resulting in overlapping altitude-based clusters. Complex relationships between quinoa variables were identified, which varied with altitude. These findings suggest that cultivation of high-quality quinoa across a range of altitudes is feasible without compromising its intrinsic quality. Moreover, the extensive and diverse results from our study provide a solid foundation for further plant breeding and the development of specialized quinoa varieties.

Predicting the band gap of lead-free inorganic double perovskites using modified parallel residual network

The rapid and precise screening of appropriate inorganic perovskite materials poses a formidable challenge in the field of materials science. Traditional methods for material screening are not only time-consuming but also demand a substantial workforce. In this study, we introduce a modified parallel residual network (PRN) for the purpose of predicting the band gap of lead-free inorganic double perovskite materials, utilizing the atomic composition as the input data. The predictive performance of PRN is assessed using root mean square error (RMSE) and Pearson correlation coefficient ( r) as evaluation metrics. The PRN model yields a band gap prediction with an RMSE of 0.402 eV and an r value of 0.962, respectively. Notably, PRN outperforms various alternative models, including random forest regression (RFR), kernel ridge regression (KRR), support vector regression (SVR), extreme gradient boosting regression (XGBR), one-layer residual variant network (OLRN), and three-layer parallel residual variant network (TLPRN), clearly demonstrating its superior predictive accuracy.

Hierarchical Optimization for Personalized Hand and Wrist Musculoskeletal Modeling and Motion Estimation.

Surface electromyography (sEMG) driven musculoskeletal models are promising to be applied in the field of human-computer interaction. However, due to the individual-specific physiological characteristics, generic models often fail to provide accurate motion estimation. This study optimized the general model to build a personalized model and improve the accuracy of motion estimation. Inspired by the coupling effect of wrist/hand movement, a hierarchical optimization approach for personalizing musculoskeletal models (HOPE-MM) is proposed, which aligns with the physiological characteristics of the human wrist and hand. To verify the effectiveness of personalized musculoskeletal model, single joint motions and simultaneous joint motions are estimated. In addition, Sobol sensitivity analysis is conducted to identify the key parameters of musculoskeletal model, providing guidance for model simplification. The mean pearson correlation coefficient between the predicted joint angles and the measured joint angles are 0.95 ± 0.03 and 0.93 ± 0.01 for simultaneous wrist and metacarpophalangeal (MCP) joint movements, respectively, which have a significant improvement compared with the stateof- the-art works. By optimizing only the key parameters including tendon slack length, maximal isometric force and optimal fiber length, the performances of simplified model are comparable to the full-parameter model. These results provide insights into the effects of muscletendon parameters on musculoskeletal model, and musculoskeletal models personalized using hierarchical optimization methods can improve the accuracy of motion estimates. These findings facilitate the clinical application of musculoskeletal models in rehabilitation and robotic control.

Simultaneous Estimation of Digit Tip Forces and Hand Postures in a Simulated Real-Life Condition With High-Density Electromyography and Deep Learning.

In myoelectric control, continuous estimation of multiple degrees of freedom has an important role. Most studies have focused on estimating discrete postures or forces of the human hand but for a practical prosthetic system, both should be considered. In daily life activities, hand postures vary for grasping different objects and the amount of force exerted on each fingertip depends on the shape and weight of the object. This study aims to investigate the feasibility of continuous estimation of multiple degrees of freedom. We proposed a reach and grasp framework to study both absolute fingertip forces and hand movement types using deep learning techniques applied to high-density surface electromyography (HD-sEMG). Four daily life grasp types were examined and absolute fingertip forces were simultaneously estimated while grasping various objects, along with the grasp types. We showed that combining a 3-dimensional Convolutional Neural Network (3DCNN) with a Long Short-term Memory (LSTM) can reliably and continuously estimate the digit tip forces and classify different hand postures in human individuals. The mean absolute error (MAE) and Pearson correlation coefficient (PCC) results of the force estimation problem across all fingers and subjects were 0.46 ± 0.23 and 0.90 ± 0.03% respectively and for the classification problem, they were 0.04 ± 0.01 and 0.97 ± 0.02%. The results demonstrated that both absolute digit tip forces and hand postures can be successfully estimated through deep learning and HD-sEMG.

Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.

Background Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited. Purpose To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience. Results Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range, <.001 to .04). Conclusions Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Omoumi and Richiardi in this issue.