Cancer screening and diagnosis with the utilization of innovative Artificial Intelligence tools improved the treatment strategies and patients' survival. With the rapid development of imaging technologies and the ...
详细信息
Cancer screening and diagnosis with the utilization of innovative Artificial Intelligence tools improved the treatment strategies and patients' survival. With the rapid development of imaging technologies and the rise of artificial intelligence (ai), there is a significant opportunity to improve cancer diagnostics through the combination of image analysis and ai algorithms. This article provides a comprehensive review of studies that have investigated the application of ai-assisted image processing in cancer diagnosis. We searched the Web of Science and Scopus databases to identify relevant studies published between 2014 and January 2024. The search strategy utilized targeted keywords such as cancer diagnostics, image analysis, artificial intelligence, and advanced imaging techniques. We limited the review to articles written in English and using ai-assisted image processing in cancer diagnosis. The results show that by leveraging machine learning algorithms, including deep learning, computer-aided diagnosis systems have been developed that are efficient in detecting tumors, thereby facilitating early cancer detection. Additionally, various authors have explored the integration of personalized treatment approaches and precision medicine, allowing for the development of treatment plans tailored to individual patient characteristics and needs. The review emphasizes the potential of ai-assisted image processing in revolutionizing cancer diagnostics. The insights gained from this study contribute to the current understanding of the field and pave the way for future research and development aimed at advancing cancer diagnostics using image analysis and artificial intelligence.
aim: This study evaluates the comparative effectiveness of pathologists versus artificial intelligence (ai) algorithms in scoring PD-L1 expression in non-small cell lung carcinoma (NSCLC). Immune-checkpoint inhibitors...
详细信息
aim: This study evaluates the comparative effectiveness of pathologists versus artificial intelligence (ai) algorithms in scoring PD-L1 expression in non-small cell lung carcinoma (NSCLC). Immune-checkpoint inhibitors have revolutionized NSCLC treatment, with PD-L1 expression, measured as the tumour proportion score (TPS), serving as a critical predictive biomarker for therapeutic response. Methods and Results: In our analysis, 51 SP263-stained NSCLC cases were scored by six pathologists using light microscopy and whole-slide images (WSI), alongside evaluations by two commercially available software tools: uPath software (Roche) and the PD-L1 Lung Cancer TME application (Visiopharm). The study examined intra- and interobserver agreement among pathologists at TPS cutoffs of 1% and 50%, revealing moderate interobserver agreement (Fleiss' kappa 0.558) for TPS <1% and almost perfect agreement (Fleiss' kappa 0.873) for TPS >= 50%. Intraobserver consistency was high, with Cohen's kappa ranging from 0.726 to 1.0. Comparisons between the ai algorithms and the median pathologist scores showed fair agreement for uPath (Fleiss' kappa 0.354) and substantial agreement for the Visiopharm application (Fleiss' kappa 0.672) at the 50% TPS cutoff. Conclusion: These results indicate that while there is strong interobserver concordance among pathologists at higher TPS levels, the performance of ai algorithms is less consistent. The study underscores the need for further refinement of ai tools to match the reliability of expert human evaluation, particularly in critical clinical decision-making contexts.
Windscreen optical quality is an important aspect of any advanced driver assistance system, and also for future autonomous driving, as today at least some cameras of the sensor suite are situated behind the windscreen...
详细信息
ISBN:
(纸本)9798350399462
Windscreen optical quality is an important aspect of any advanced driver assistance system, and also for future autonomous driving, as today at least some cameras of the sensor suite are situated behind the windscreen. Automotive mass production processes require measurement systems that characterize the optical quality of the windscreens in a meaningful way, which for modern perception stacks implies meaningful for artificial intelligence (ai) algorithms. The measured optical quality needs to be linked to the performance of these algorithms, such that performance limits - and thus production tolerance limits - can be defined. In this article we demonstrate that the main metric established in the industry - refractive power - is fundamentally not capable of capturing relevant optical properties of windscreens. Further, as the industry is moving towards the modulation transfer function (MTF) as an alternative, we mathematically show that this metric cannot be used on windscreens alone, but that the windscreen forms a novel optical system together with the optics of the camera system. Hence, the required goal of a qualification system that is installed at the windscreen supplier and independently measures the optical quality cannot be achieved using MTF. We propose a novel concept to determine the optical quality of windscreens and to use simulation to link this optical quality to the performance of ai algorithms, which can hopefully lead to novel inspection systems.
Gastric cancer is a prevalent and deadly malignancy, and the response to immunotherapy varies among patients. This study aimed to develop a prognostic model for gastric cancer patients and investigate immune escape me...
详细信息
Gastric cancer is a prevalent and deadly malignancy, and the response to immunotherapy varies among patients. This study aimed to develop a prognostic model for gastric cancer patients and investigate immune escape mechanisms using deep machine learning and single-cell sequencing analysis. Data from public databases were analysed, and a prediction model was constructed using 101 algorithms. The high-aiDPS group, characterized by increased aiDPS expression, exhibited worse survival, genomic variations and immune cell infiltration. These patients also showed immunotherapy tolerance. Treatment strategies targeting the high-aiDPS group identified three potential drugs. Additionally, distinct cluster groups and upregulated aiDPS-associated genes were observed in gastric adenocarcinoma cell lines. Inhibition of GHRL expression suppressed cancer cell activity, inhibited M2 polarization in macrophages and reduced invasiveness. Overall, aiDPS plays a critical role in gastric cancer prognosis, genomic variations, immune cell infiltration and immunotherapy response, and targeting GHRL expression holds promise for personalized treatment. These findings contribute to improved clinical management in gastric cancer.
Buildings' heating and cooling systems account for an important part of total energy consumption. The EU's directives and engagements motivate building owners and relevant stakeholders in the energy and constr...
详细信息
Buildings' heating and cooling systems account for an important part of total energy consumption. The EU's directives and engagements motivate building owners and relevant stakeholders in the energy and construction sectors towards net zero energy buildings by maximizing the use of renewable energy sources, ICT, and automation systems. However, the high costs of investment for the renovation of buildings, in situ use of renewable energy production, and installation of expensive ICT infrastructure and automation systems in small-medium range buildings are the main obstacles for the wide adoption of EU building directives in small- and medium-range buildings. On the other hand, the concept of sharing computational and data storage resources among various buildings can be an alternative approach to achieving smart buildings and smart cities where the main control power resides on a server. Unlike other studies that focus on the implementation of ai techniques in a building or separated buildings with local processing resources and data storage, in this work a corporate server was employed to control the heating systems in three building typologies and to examine the potential benefits of controlling existing buildings in a unified energy-savings platform. The key finding of this work is that the ai algorithms incorporated into the proposed system achieved significant energy savings in the order of 20-40% regardless of building typology, building functionality, and type of heating system, despite the COVID-19 measures for frequent ventilation of the buildings, even in cases with older-type heating systems.
Purpose The current and on-going coronavirus (COVID-19) has disrupted many human lives all over the world and seems very difficult to confront this global crisis as the infection is transmitted by physical contact. As...
详细信息
Purpose The current and on-going coronavirus (COVID-19) has disrupted many human lives all over the world and seems very difficult to confront this global crisis as the infection is transmitted by physical contact. As no vaccine or medical treatment made available till date, the only solution is to detect the COVID-19 cases, block the transmission, isolate the infected and protect the susceptible population. In this scenario, the pervasive computing becomes essential, as it is environment-centric and data acquisition via smart devices provides better way for analysing diseases with various parameters. Design/methodology/approach For data collection, Infrared Thermometer, Hikvision's Thermographic Camera and Acoustic device are deployed. Data-imputation is carried out by principal component analysis. A mathematical model susceptible, infected and recovered (SIR) is implemented for classifying COVID-19 cases. The recurrent neural network (RNN) with long-term short memory is enacted to predict the COVID-19 disease. Findings Machine learning models are very efficient in predicting diseases. In the proposed research work, besides contribution of smart devices, Artificial Intelligence detector is deployed to reduce false alarms. A mathematical model SIR is integrated with machine learning techniques for better classification. Implementation of RNN with Long Short Term Memory (LSTM) model furnishes better prediction holding the previous history. Originality/value The proposed research collected COVID -19 data using three types of sensors for temperature sensing and detecting the respiratory rate. After pre-processing, 300 instances are taken for experimental results considering the demographic features: Sex, Patient Age, Temperature, Finding and Clinical Trials. Classification is performed using SIR mode and finally predicted 188 confirmed cases using RNN with LSTM model.
Regularity in musical structure is experienced as a strongly structured texture with repeated and periodic patterns, with the musical ideas presented in an appreciable shape to the human mind. We recently showed that ...
详细信息
Regularity in musical structure is experienced as a strongly structured texture with repeated and periodic patterns, with the musical ideas presented in an appreciable shape to the human mind. We recently showed that manipulation of musical content (i.e., deviation of musical structure) affects the perception of music. These deviations were detected by musical experts, and the musical pieces containing them were labelled as irregular. In this study, we replace the human expert involved in detection of (ir)regularity with artificial intelligence algorithms. We evaluated eight variables measuring entropy and information content, which can be analysed for each musical piece using the computational model called Information Dynamics of Music and different viewpoints. The algorithm was tested using 160 musical excerpts. A preliminary statistical analysis indicated that three of the eight variables were significant predictors of regularity (E_cpitch, IC_cpintfref, and E_cpintfref). Additionally, we observed linear separation between regular and irregular excerpts;therefore, we employed support vector machine and artificial neural network (ANN) algorithms with a linear kernel and a linear activation function, respectively, to predict regularity. The final algorithms were capable of predicting regularity with an accuracy ranging from 89% for the ANN algorithm using only the most significant predictor to 100% for the ANN algorithm using all eight prediction variables.
This paper investigates the application of Gradient Boosting Model (GBM), Gaussian Process (GP), and Decision Tree (DT) algorithms to analyze and predict the progression of crater tool wear (CTW) in CNC turning proces...
详细信息
This paper investigates the application of Gradient Boosting Model (GBM), Gaussian Process (GP), and Decision Tree (DT) algorithms to analyze and predict the progression of crater tool wear (CTW) in CNC turning processes. Experiments were conducted using tungsten carbide cutting tools on 7075 aluminum alloy, focusing on the effects of corner radius, cutting speed, depth of cut, and feed rate on tool crater wear. CTW measurements were obtained using an optical microscope. A total of 45 experiments were performed, with 36 used to train the models and the remaining 9 for evaluation. Additionally, a validation experiment was carried out under different cutting conditions to assess the accuracy of the selected model. The novelty of this study lies in its results, which outperform previous literature, and it is the first to evaluate three distinct ai models in the context of tool wear analysis. The findings show that the GBM model provided the most accurate predictions, with performance indices of R2 = 0.986, RAE = 0.015, MAE = 0.004, RMSE = 0.065, and RSE = 0.046, and an average difference of 5.02% between the predicted and actual CTW values. These forecasts can help manufacturing companies prevent tool failure, boost productivity, and optimize costs by balancing cycle time with tool adjustment and replacement expenses.
Comfortable treatment of malignant tumors is the clinical orientation of cancer therapy at present, which puts forward a high demand for non-invasive, portable and high-frequency monitoring status of tumor in the trea...
详细信息
Comfortable treatment of malignant tumors is the clinical orientation of cancer therapy at present, which puts forward a high demand for non-invasive, portable and high-frequency monitoring status of tumor in the treatment. Unlike traditional blood and X-ray technique, here we have developed hydrogel-based wearable sweat sensors, equipped with multiple molecular receptors for surface enhanced Raman spectroscopy (SERS) monitoring treatment effects of lung cancer. The SERS technique was utilized in combination with multiple artificial intelligence (ai) algorithms (LGB GNB, LDA, RF, and SVM) to develop a novel and precise diagnostic model for monitoring the treatment effect. Based on 12617 SERS spectras from clinical patients, the results successfully diagnosed three treatment effects (progressive disease, partial response, and no change) with an accuracy of 89.7 %. Benefiting from data mining in ai algorithms, key Raman spectra features in clinical spectra are identified to explore characteristic biomarkers of lung cancer associated with various comorbidities. The clinical data suggest that carbonyl biomarkers in sweat might be crucial for understanding complications such as diabetes and hypertension. Our results not only offer a novel and comfortable monitoring technique but also enable personalized treatment of lung cancer with complications, presenting significant potential for clinical application.
This study focuses on slope stability analysis, a critical process for understanding the conditions, durability, mass properties, and failure mechanisms of slopes. The research specifically addresses rotational-type f...
详细信息
This study focuses on slope stability analysis, a critical process for understanding the conditions, durability, mass properties, and failure mechanisms of slopes. The research specifically addresses rotational-type failure, the primary instability mechanism affecting earth slopes. Identifying and understanding key factors such as slope height, slope angle, density, cohesion, friction, water pore pressure, and tensile cracks are essential for effective stabilization strategies. The objective of this study is to develop accurate predictive models for slope stability analysis using advanced intelligent techniques, including data mining mapping and complex decision tree regression (DTR). The models were validated using performance metrics such as mean absolute error (MAE), mean squared error (MSE), root mean square error (RMSE), and the coefficient of determination (R-2). Additionally, overall accuracy was assessed using a confusion matrix. The predictive model was tested on a dataset of 120 slope cases, achieving an accuracy of approximately 91.07% with DTR. The error rates for the training set were MAE = 0.1242, MSE = 0.1722, and RMSE = 0.1098, demonstrating the model's capability to effectively analyze and predict slope stability in earth slopes and embankments. The study concludes that these intelligent techniques offer a reliable approach for stability analysis, contributing to safer and more efficient slope management.
暂无评论