期刊,Robotics & Machine Learning Daily News 2024年卷Feb.28期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Treating liver cancer with microrobots piloted by a magnetic field

1-2页

查看更多>>摘要：Montreal, -Canadian researchers led by Montreal radiologist Gilles Soulez have developed a novel approach to treat liver tumours using magnet-guided microrobots in an MRI device. The idea of injecting microscopic robots into the bloodstream to heal the human body is not new. It's also not science fiction. Guided by an external magnetic field, miniature biocompatible robots, made of magnetizable iron oxide nanoparticles, can theoretically provide medical treatment in a very targeted manner. Until now, there has been a technical obstacle: the force of gravity of these microrobots exceeds that of the magnetic force, which limits their guidance when the tumour is located higher than the injection site. While the magnetic field of the MRI is high, the magnetic gradients used for navigation and to generate MRI images are weaker. "To solve this problem, we developed an algorithm that determines the position that the patient's body should be in for a clinical MRI to take advantage of gravity and combine it with the magnetic navigation force," said Dr. Gilles Soulez, a researcher at the CHUM Research Centre and director of the radiology, radio-oncology and nuclear medicine department at Universite de Montreal.

原文链接:

NETL
NSTL

New Machine Learning Findings from University of Virginia Published (Disentangling CO Chemistry in a Protoplanetary Disk Using Explanatory Machine-learning Techniques)

2-3页

查看更多>>摘要：Research findings on artificial intelligence are discussed in a new report. According to news reporting from Charlottesville, Virginia, by NewsRx journalists, research stated, "Molecular abundances in protoplanetary disks are highly sensitive to the local physical conditions, including gas temperature, gas density, radiation field, and dust properties." Financial supporters for this research include John F. Angle Fellowship; Research Corporation For Science Advancement; David And Lucile Packard Foundation; Nasa. Our news journalists obtained a quote from the research from University of Virginia: "Often multiple factors are intertwined, impacting the abundances of both simple and complex species. We present a new approach to understanding these chemical and physical interdependencies using machine learning. Specifically, we explore the case of CO modeled under the conditions of a generic disk and build an explanatory regression model to study the dependence of CO spatial density on the gas density, gas temperature, cosmic-ray ionization rate, X-ray ionization rate, and UV flux. Our findings indicate that combinations of parameters play a surprisingly powerful role in regulating CO abundance compared to any singular physical parameter. Moreover, in general we find the conditions in the disk are destructive toward CO. CO depletion is further enhanced in an increased cosmic-ray environment and in disks with higher initial C/O ratios."

原文链接:

NETL
NSTL

Shanghai University Reports Findings in Artificial Intelligence (Automated Generation and Analysis of Molecular Images Using Generative Artificial Intelligence Models)

3-4页

查看更多>>摘要：New research on Artificial Intelligence is the subject of a report. According to news reporting originating from Shanghai, People's Republic of China, by NewsRx correspondents, research stated, "The development of scanning probe microscopy (SPM) has enabled unprecedented scientific discoveries through high-resolution imaging. Simulations and theoretical analysis of SPM images are equally important as obtaining experimental images since their comparisons provide fruitful understandings of the structures and physical properties of the investigated systems." Our news editors obtained a quote from the research from Shanghai University, "So far, SPM image simulations are conventionally based on quantum mechanical theories, which can take several days in tasks of large-scale systems. Here, we have developed a scanning tunneling microscopy (STM) molecular image simulation and analysis framework based on a generative adversarial model, CycleGAN. It allows efficient translations between STM data and molecular models. Our CycleGAN-based framework introduces an approach for high-fidelity STM image simulation, outperforming traditional quantum mechanical methods in efficiency and accuracy."

原文链接:

NETL
NSTL

Research Conducted at Hefei University of Technology Has Provided New Information about Machine Learning (Early Detection of Coronary Microvascular Dysfunction Using Machine Learning Algorithm Based On Vectorcardiography and Cardiodynamicsgram ...)

4-5页

查看更多>>摘要：Investigators discuss new findings in Machine Learning. According to news originating from Anhui, People's Republic of China, by NewsRx correspondents, research stated, "As a main etiology of myocardial ischemia, coronary microvascular dysfunction (CMD) can occur in patients with or without obstructive coronary artery disease. Currently, there is a lack of a non-invasive approach for early detection of CMD." Financial supporters for this research include Natural Science Foundation of Ningxia Province, North Minzu University Scientific Research Projects, National Natural Science Foundation of China (NSFC), Major Scientific Project of Zhejiang Laboratory, Key Research and Development Program of Zhejiang Province, Ningxia First-Class Discipline and Scientific Research Projects (Electronic Science and Technology), Innovation Team of Lidar Atmosphere Remote Sensing of Ningxia Province, Key Research and Development Plan in Ningxia Province, Sub-themes of Key and Major Special Projects of Scientific and Technological Innovation of Yinchuan Science and Technology Plan Project, Plan for Leading Talents of the State Ethnic Affairs Commission of the People's Republic of China, High Level Talent Selection and Training Plan of North Minzu University.

原文链接:

NETL
NSTL
Elsevier

Findings from Marquette University Provides New Data about Artificial Intelligence (Detection of Dental Restorations Using No-code Artificial Intelligence)

5-6页

查看更多>>摘要：Investigators publish new report on Artificial Intelligence. According to news reporting originating in Milwaukee, Wisconsin, by NewsRx journalists, research stated, "The purpose of this study was to utilize a no-code computer vision platform to develop, train, and evaluate a model specifically designed for segmenting dental restorations on panoramic radiographs. One hundred anonymized panoramic radiographs were selected for this study." Financial support for this research came from Marquette University Participating Faculty Research Award [FY2022-2023]. The news reporters obtained a quote from the research from Marquette University, "Accurate labeling of dental restorations was performed by calibrated dental faculty and students, with subsequent final review by an oral radiologist. The radiographs were automatically split within the platform into training (70 %), development (20 %), and testing (10 %) subgroups. The model was trained for 40 epochs using a medium model size. Data augmentation techniques available within the platform, namely horizontal and vertical flip, were utilized on the training set to improve the model's predictions. Post-training, the model was tested for independent predictions. The model's diagnostic validity was assessed through the calculation of sensitivity, specificity, accuracy, precision, F1-score by pixel and by tooth, and by ROC-AUC. A total of 1,108 restorations were labeled on 960 teeth. At a confidence threshold of 0.95, the model achieved 86.64 % sensitivity, 99.78 % specificity, 99.63 % accuracy, 82.4 % precision and an F1-score of 0.844 by pixel. The model achieved 98.34 % sensitivity, 98.13 % specificity, 98.21 % accuracy, 98.85 % precision and an F1-score of 0.98 by tooth. ROC curve showed high performance with an AUC of 0.978. The no-code computer vision platform used in this study accurately detected dental restorations on panoramic radiographs. However, further research and validation are required to evaluate the performance of no-code platforms on larger and more diverse datasets, as well as for other detection and segmentation tasks."

原文链接:

NETL
NSTL
Elsevier

Researchers from Russian Academy of Sciences Describe Findings in Machine Learning (Machine Learning Approach for Predicting the Yield of Pyrroles and Dipyrromethanes Condensation Reactions With Aldehydes)

6-7页

查看更多>>摘要：Current study results on Machine Learning have been published. According to news originating from Ivanovo, Russia, by NewsRx correspondents, research stated, "The utilization of machine learning techniques for investigating chemical reactions is both sought after and challenging. While there are now many high-quality paid and free tools available for planning retrosynthesis, predicting the yield of different reaction types has received less attention, even though it is a crucial parameter for improving the synthesis process." Financial support for this research came from Ministry of Science and Higher Education of the Russian Federation. Our news journalists obtained a quote from the research from the Russian Academy of Sciences, "This article aims to contribute to the application of machine learning in forecasting the yield of pyrrole and dipyrromethane condensation reactions with aldehydes. To achieve this, we trained a random forest model with an extended connectivity fingerprint on over 1200 such reactions, resulting in an MAE of 9.6 % and R2 of 0.63."

原文链接:

NETL
NSTL
Elsevier

Researchers at Sorbonne University Have Reported New Data on Machine Learning (Microscopic Mechanism of Thermal Amorphization of Zif-4 and Melting of Zif-zni Revealed via Molecular Dynamics and Machine Learning Techniques)

7-8页

查看更多>>摘要：Current study results on Machine Learning have been published. According to news reporting from Paris, France, by NewsRx journalists, research stated, "We investigate the microscopic mechanism of the thermally induced ambient pressure ordered-disordered phase transitions of two zeolitic imidazolate frameworks of formula Zn(C3H3N2)(2): a porous (ZIF-4) and a dense, non-porous (ZIF-zni) polymorph via a combination of data science and computer simulation approaches. Molecular dynamics simulations are carried out at the atomistic level through the nb-ZIF-FF force field that incorporates ligand-metal reactivity and relies on dummy atoms to reproduce the correct tetrahedral topology around Zn2+ centres." Financial support for this research came from European Research Council (ERC). The news correspondents obtained a quote from the research from Sorbonne University, "The force field is capable of reproducing the structure of ZIF-4, ZIF-zni and the amorphous (ZIF_a) and liquid (ZIF_liq) phases that respectively result when these crystalline materials are heated. Symmetry functions computed over a database of structures of the four phases are used as inputs to train a neural network that predicts the probabilities of belonging to each of the four phases at the local Zn2+ level with 90% accuracy. We apply this methodology to follow the time-evolution of the amorphization of ZIF-4 and the melting of ZIF-zni along a series of molecular dynamics trajectories. We first computed the transition temperature and determined the associated thermodynamic state functions. Subsequently, we studied the mechanisms. Both processes consist of two steps: (ⅰ) for ZIF-4, a low-density amorphous phase is first formed, followed by the final ZIF_a phase while (ⅱ) for ZIF-zni, a ZIF_a-like phase precedes the formation of the liquid phase. These processes involve connectivity changes in the first neighbour ligands around the central Zn2_+ cations."

原文链接:

NETL
NSTL
Royal Soc Chemistry

Reports Outline Machine Learning Study Findings from Taipei Veterans General Hospital (Machine-learning models are superior to severity scoring systems for the prediction of the mortality of critically ill patients in a tertiary medical center)

8-9页

查看更多>>摘要：Investigators publish new report on artificial intelligence. According to news reporting out of the Taipei Veterans General Hospital by NewsRx editors, research stated, "Intensive care unit (ICU) mortality prediction helps to guide therapeutic decision making for critically ill patients. Several scoring systems based on statistical techniques have been developed for this purpose." The news editors obtained a quote from the research from Taipei Veterans General Hospital: "In this study, we developed a machine-learning model to predict patient mortality in the very early stage of ICU admission. This study was performed with data from all patients admitted to the ICUs of a tertiary medical center in Taiwan from 2009 to 2018. The patients' comorbidities, co-medications, vital signs, and laboratory data on the day of ICU admission were obtained from electronic medical records. We constructed random forest (RF) and extreme gradient boosting (XGBoost) models to predict ICU mortality, and compared their performance with that of traditional scoring systems. Data from 12,377 patients was allocated to training (n = 9901) and testing (n = 2476) datasets. The median patient age was 70.0 years; 9210 (74.41%) patients were under mechanical ventilation in the ICU. The areas under receiver operating characteristic curves for the RF and XGBoost models (0.876 and 0.880, respectively) were larger than those for the Acute Physiology and Chronic Health Evaluation Ⅱ score (0.738), Sequential Organ Failure Assessment score (0.747), and Simplified Acute Physiology Score Ⅱ (0.743). The fraction of inspired oxygen on ICU admission was the most important predictive feature across all models."

原文链接:

NETL
NSTL

Study Findings from Shanghai Jiao Tong University Broaden Understanding of Machine Learning (A High-fidelity Comprehensive Framework for the Additive Manufacturing Printability Assessment)

9-10页

查看更多>>摘要：Current study results on Machine Learning have been published. According to news reporting originating in Shanghai, People's Republic of China, by NewsRx journalists, research stated, "Additive manufacturing is capable of fabricating complex and customized components that cannot be easily and economically produced by other techniques. It is of great significance to determine the printability map for the extensive application of the fabricated parts, which has been hindered by the common defects such as interior pores and surface roughness." Funders for this research include National Natural Science Foundation of China (NSFC), Shanghai Sailing Program, Natural Science Foundation of Shanghai, Major Science and Technology Project of Huaibei. The news reporters obtained a quote from the research from Shanghai Jiao Tong University, "Here, a comprehensive framework including multiphysics model, physics-informed machine learning, and experimental data is proposed to predict the printability. The characteristics for different phenomena (lack of fusion, balling and keyhole) are analyzed by the mechanistic model considering high-fidelity powder-scale model, fluid flow, recoil pressure and Marangoni effect, which provides a more accurate thermal history, molten pool dynamics and surface morphology compared to the finite element model. Classification criterion is established by three mechanistic variables based on the molten pool morphology, which divides the process map into four regions. For the first time, the relationship between the solidified-track surface morphology and the interior quality is established, and the optimal surface morphology corresponding to defectfree printing is determined. The printability is predicted by mathematical machine learning classification models via 10-fold cross-validation method, which validates the classification criterion and the comprehensive framework to assess the printability."

原文链接:

NETL
NSTL
Elsevier

Data on Radiation Pneumonitis Reported by Lixia Xu and Colleagues (Predicting radiation pneumonitis in lung cancer: a EUDbased machine learning approach for volumetric modulated arc therapy patients)

10-11页

查看更多>>摘要：New research on Lung Diseases and Conditions - Radiation Pneumonitis is the subject of a report. According to news reporting from Hangzhou, People's Republic of China, by NewsRx journalists, research stated, "This study aims to develop an optimal machine learning model that uses lung equivalent uniform dose (lung EUD to predict radiation pneumonitis (RP) occurrence in lung cancer patients treated with volumetric modulated arc therapy (VMAT). We analyzed a cohort of 77 patients diagnosed with locally advanced squamous cell lung cancer (LASCLC) receiving concurrent chemoradiotherapy with VMAT." Financial support for this research came from Natural Science Foundation of Zhejiang Province. The news correspondents obtained a quote from the research, "Patients were categorized based on the onset of grade Ⅱ or higher radiation pneumonitis (RP 2_+). Dose volume histogram data, extracted from the treatment planning system, were used to compute the lung EUD values for both groups using a specialized numerical analysis code. We identified the parameter a, representing the most significant relative difference in lung EUD between the two groups. The predictive potential of variables for RP2_+, including physical dose metrics, lung EUD, normal tissue complication probability (NTCP) from the Lyman- Kutcher-Burman (LKB) model, and lung EUD-calibrated NTCP for affected and whole lung, underwent both univariate and multivariate analyses. Relevant variables were then employed as inputs for machine learning models: multiple logistic regression (MLR), support vector machine (SVM), decision tree (DT), and K-nearest neighbor (KNN). Each model's performance was gauged using the area under the curve (AUC), determining the best-performing model. The optimal a-value for lung EUD was 0.3, maximizing the relative lung EUD difference between the RP 2_+ and non-RP 2_+ groups. A strong correlation coefficient of 0.929 (P ＜0.01) was observed between lung EUD (a = 0.3) and physical dose metrics. When examining predictive capabilities, lung EUD-based NTCP for the affected lung (AUC: 0.862) and whole lung (AUC: 0.815) surpassed LKB-based NTCP for the respective lungs. The decision tree (DT) model using lung EUDbased predictors emerged as the superior model, achieving an AUC of 0.98 in both training and validation datasets. The likelihood of developing RP 2_+ has shown a significant correlation with the advancements in RT technology. From traditional 3-D conformal RT, lung cancer treatment methodologies have transitioned to sophisticated techniques like static IMRT. Accurately deriving such a dose-effect relationship through NTCP modeling of RP incidence is statistically challenging due to the increased number of degrees-offreedom. To the best of our knowledge, many studies have not clarified the rationale behind setting the a-value to 0.99 or 1, despite the closely aligned calculated lung EUD and lung mean dose MLD. Perfect independence among variables is rarely achievable in real-world scenarios. Four prominent machine learning algorithms were used to devise our prediction models. The inclusion of lung EUD-based factors substantially enhanced their predictive performance for RP 2_+. Our results advocate for the decision tree model with lung EUD-based predictors as the optimal prediction tool for VMAT-treated lung cancer patients."

原文链接:

NETL
NSTL
Frontiers Media Sa