Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

The risk assessment of arsenic contamination in the urbanized coastal aquifer of Rayong groundwater basin, Thailand using the machine learning approach.

In Ecotoxicology and environmental safety ; h5-index 67.0

The rapid expansion of urbanization has resulted in an insufficient of groundwater resource. In order to use groundwater more efficiently, a risk assessment of groundwater pollution should be proposed. The present study used machine learning with three algorithms consisting of Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN) to locate risk areas of arsenic contamination in Rayong coastal aquifers, Thailand and selected the suitable model based on model performance and uncertainty for risk assessment. The parameters of 653 groundwater wells (Deep=236, Shallow=417) were selected based on the correlation of each hydrochemical parameters with arsenic concentration in deep and shallow aquifer environments. The models were validated with arsenic concentration collected from 27 well data in the field. The model's performance indicated that the RF algorithm has the highest performance as compared to those of SVM and ANN in both deep and shallow aquifers (Deep: AUC=0.72, Recall=0.61, F1 =0.69; Shallow: AUC=0.81, Recall=0.79, F1 =0.68). In addition, the uncertainty from the quantile regression of each model confirmed that the RF algorithm has the lowest uncertainty (Deep: PICP=0.20; Shallow: PICP=0.34). The result of the risk map obtained from the RF reveals that the deep aquifer, in the northern part of the Rayong basin has a higher risk for people to expose to As. In contrast, the shallow aquifer revealed that the southern part of the basin has a higher risk, which is also supported by the location of the landfill and industrial estates in the area. Therefore, health surveillance is important in monitoring the toxic effects on the residents who use groundwater from these contaminated wells. The outcome of this study can help policymakers in regions to manage the quality of groundwater resources and enhance the sustainable use of groundwater resources. The novelty process of this research can be used to further study other groundwater aquifers contaminated and increase the effectiveness of groundwater quality management.

Sumdang Narongpon, Chotpantarat Srilert, Cho Kyung Hwa, Thanh Nguyen Ngoc

2023-Feb-28

Arsenic, Groundwater contamination, Groundwater risk assessment, Machine learning, Spatial probability model, Thailand

Radiology Radiology

RSU-Net: U-net based on residual and self-attention mechanism in the segmentation of cardiac magnetic resonance images.

In Computer methods and programs in biomedicine

BACKGROUND : Automated segmentation techniques for cardiac magnetic resonance imaging (MRI) are beneficial for evaluating cardiac functional parameters in clinical diagnosis. However, due to the characteristics of unclear image boundaries and anisotropic resolution anisotropy produced by cardiac magnetic resonance imaging technology, most of the existing methods still have the problems of intra-class uncertainty and inter-class uncertainty. However, due to the irregularity of the anatomical shape of the heart and the inhomogeneity of tissue density, the boundaries of its anatomical structures become uncertain and discontinuous. Therefore, fast and accurate segmentation of cardiac tissue remains a challenging problem in medical image processing.

METHODOLOGY : We collected cardiac MRI data from 195 patients as training set and 35patients from different medical centers as external validation set. Our research proposed a U-net network architecture with residual connections and a self-attentive mechanism (Residual Self-Attention U-net, RSU-Net). The network relies on the classic U-net network, adopts the U-shaped symmetric architecture of the encoding and decoding mode, improves the convolution module in the network, introduces skip connections, and improves the network's capacity for feature extraction. Then for solving locality defects of ordinary convolutional networks. To achieve a global receptive field, a self-attention mechanism is introduced at the bottom of the model. The loss function employs a combination of Cross Entropy Loss and Dice Loss to jointly guide network training, resulting in more stable network training.

RESULTS : In our study, we employ the Hausdorff distance (HD) and the Dice similarity coefficient (DSC) as metrics for assessing segmentation outcomes. Comparsion was made with the segmentation frameworks of other papers, and the comparison results prove that our RSU-Net network performs better and can make accurate segmentation of the heart. New ideas for scientific research.

CONCLUSION : Our proposed RSU-Net network combines the advantages of residual connections and self-attention. This paper uses the residual links to facilitate the training of the network. In this paper, a self-attention mechanism is introduced, and a bottom self-attention block (BSA Block) is used to aggregate global information. Self-attention aggregates global information, and has achieved good segmentation results on the cardiac segmentation dataset. It facilitates the diagnosis of cardiovascular patients in the future.

Li Yuan-Zhe, Wang Yi, Huang Yin-Hui, Xiang Ping, Liu Wen-Xi, Lai Qing-Quan, Gao Yi-Yuan, Xu Mao-Sheng, Guo Yi-Fan

2023-Feb-21

Cardiac MRI, Deep learning, Image segmentation, Residual, Self-attention, U-net

General General

Automatic placental and fetal volume estimation by a convolutional neural network.

In Placenta ; h5-index 40.0

INTRODUCTION : We aimed to develop an artificial intelligence (AI) deep learning algorithm to efficiently estimate placental and fetal volumes from magnetic resonance (MR) scans.

METHODS : Manually annotated images from an MRI sequence was used as input to the neural network DenseVNet. We included data from 193 normal pregnancies at gestational week 27 and 37. The data were split into 163 scans for training, 10 scans for validation and 20 scans for testing. The neural network segmentations were compared to the manual annotation (ground truth) using the Dice Score Coefficient (DSC).

RESULTS : The mean ground truth placental volume at gestational week 27 and 37 was 571 cm3 (Standard Deviation (SD) 293 cm3) and 853 cm3 (SD 186 cm3), respectively. Mean fetal volume was 979 cm3 (SD 117 cm3) and 2715 cm3 (SD 360 cm3). The best fitting neural network model was attained at 22,000 training iterations with mean DSC 0.925 (SD 0.041). The neural network estimated mean placental volumes at gestational week 27-870 cm3 (SD 202 cm3) (DSC 0.887 (SD 0.034), and to 950 cm3 (SD 316 cm3) at gestational week 37 (DSC 0.896 (SD 0.030)). Mean fetal volumes were 1292 cm3 (SD 191 cm3) and 2712 cm3 (SD 540 cm3), with mean DSC of 0.952 (SD 0.008) and 0.970 (SD 0.040). The time spent for volume estimation was reduced from 60 to 90 min by manual annotation, to less than 10 s by the neural network.

CONCLUSION : The correctness of neural network volume estimation is comparable to human performance; the efficiency is substantially improved.

Kulseng Carl Petter Skaar, Hillestad Vigdis, Eskild Anne, Gjesdal Kjell-Inge

2023-Feb-27

Artificial intelligence, Deep learning, Fetus, Magnetic resonance imaging, Placenta, Pregnancy, Volume

General General

Predicting the risk of fetal growth restriction by radiomics analysis of the placenta on T2WI: A retrospective case-control study.

In Placenta ; h5-index 40.0

INTRODUCTION : Fetal growth restriction (FGR) is associated with placental abnormalities, and its precise diagnosis is challenging. This study aimed to explore the role of radiomics based on placental MRI in predicting FGR.

METHODS : A retrospective study using T2-weighted placental MRI data were conducted. A total of 960 radiomic features were automatically extracted. Features were selected using three-step machine learning methods. A combined model was constructed by combining MRI-based radiomic features and ultrasound-based fetal measurements. The receiver operating characteristic curves (ROC) were conducted to assess model performance. Additionally, decision curves and calibration curves were performed to evaluate prediction consistency of different models.

RESULTS : Among the study participants, pregnant women who delivered from January 2015 to June 2021 were randomly divided into training (n = 119) and test (n = 40) sets. Forty-three other pregnant women who delivered from July 2021 to December 2021 were used as the time-independent validation set. After training and testing, three radiomic features that were strongly correlated with FGR were selected. The area under the ROC curves (AUCs) of the MRI-based radiomics model reached 0.87 (95% confidence interval [CI]: 0.74-0.96) and 0.87 (95% CI: 0.76-0.97) in the test and validation sets, respectively. Moreover, the AUCs for the model comprising MRI-based radiomic features and ultrasound-based measurements were 0.91 (95% CI: 0.83-0.97) and 0.94 (95% CI: 0.86-0.99) in the test and validation sets, respectively.

DISCUSSION : MRI-based placental radiomics could accurately predict FGR. Moreover, combining placental MRI-based radiomic features with ultrasound indicators of the fetus could improve the diagnostic accuracy of FGR.

Song Fuzhen, Li Ruikun, Lin Jing, Lv Mingli, Qian Zhaoxia, Wang Lisheng, Wu Weibin

2023-Feb-24

Fetal growth restriction, Machine learning, Magnetic resonance imaging, Radiomics, Ultrasound

General General

Machine Learning Full NMR Chemical Shift Tensors of Silicon Oxides with Equivariant Graph Neural Networks.

In The journal of physical chemistry. A

The nuclear magnetic resonance (NMR) chemical shift tensor is a highly sensitive probe of the electronic structure of an atom and furthermore its local structure. Recently, machine learning has been applied to NMR in the prediction of isotropic chemical shifts from a structure. Current machine learning models, however, often ignore the full chemical shift tensor for the easier-to-predict isotropic chemical shift, effectively ignoring a multitude of structural information available in the NMR chemical shift tensor. Here we use an equivariant graph neural network (GNN) to predict full 29Si chemical shift tensors in silicate materials. The equivariant GNN model predicts full tensors to a mean absolute error of 1.05 ppm and is able to accurately determine the magnitude, anisotropy, and tensor orientation in a diverse set of silicon oxide local structures. When compared with other models, the equivariant GNN model outperforms the state-of-the-art machine learning models by 53%. The equivariant GNN model also outperforms historic analytical models by 57% for isotropic chemical shift and 91% for anisotropy. The software is available as a simple-to-use open-source repository, allowing similar models to be created and trained with ease.

Venetos Maxwell C, Wen Mingjian, Persson Kristin A

2023-Mar-02

Surgery Surgery

Artificial Intelligence Modeling to Predict Periprosthetic Infection and Explantation Following Implant-Based Reconstruction.

In Plastic and reconstructive surgery ; h5-index 62.0

BACKGROUND : Despite improvements in prosthesis design and surgical techniques, periprosthetic infection and explantation rates following implant-based reconstruction (IBR) remain relatively high. Artificial intelligence is an extremely powerful predictive tool that involves machine learning (ML) algorithms. We sought to develop, validate, and evaluate the use of ML algorithms to predict complications of IBR.

METHODS : A comprehensive review of patients who underwent IBR from January 2018 to December 2019 was conducted. Nine supervised ML algorithms were developed to predict periprosthetic infection and explantation. Patient data were randomly divided into training (80%) and testing (20%) sets.

RESULTS : We identified 481 patients (694 reconstructions) with a mean (± SD) age of 50.0 ± 11.5 years, mean (± SD) body mass index of 26.7 ± 4.8 kg/m 2, and median follow-up time of 16.1 months (11.9-23.2 months). Periprosthetic infection developed with 16.3% (n = 113) of the reconstructions, and explantation was required with 11.8% (n = 82) of them. ML demonstrated good discriminatory performance in predicting periprosthetic infection and explantation (area under the receiver operating characteristic curve, 0.73 and 0.78, respectively), and identified 9 and 12 significant predictors of periprosthetic infection and explantation, respectively.

CONCLUSIONS : ML algorithms trained using readily available perioperative clinical data accurately predicts periprosthetic infection and explantation following IBR. Our findings support incorporating ML models into perioperative assessment of patients undergoing IBR to provide data-driven, patient-specific risk assessment to aid individualized patient counseling, shared decision-making, and presurgical optimization.

Hassan Abbas M, Biaggi-Ondina Andrea, Asaad Malke, Morris Natalie, Liu Jun, Selber Jesse C, Butler Charles E

2023-Mar-03