Optimizing Deep Learning for Computer-Aided Diagnosis of Lung Diseases: An Automated Method Combining Evolutionary Algorithm, Transfer Learning, and Model Compression

Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.

Computer-Aided Diagnosis for Tuberculosis Classification with Water Strider Optimization Algorithm

Computer-aided diagnosis(CAD)models exploit artificial intelligence(AI)for chest X-ray(CXR)examination to identify the presence of tuberculosis(TB)and can improve the feasibility and performance of CXR for TB screening and triage.At the same time,CXR interpretation is a time-consuming and subjective process.Furthermore,high resemblance among the radiological patterns of TB and other lung diseases can result in misdiagnosis.Therefore,computer-aided diagnosis(CAD)models using machine learning(ML)and deep learning(DL)can be designed for screening TB accurately.With this motivation,this article develops a Water Strider Optimization with Deep Transfer Learning Enabled Tuberculosis Classification(WSODTL-TBC)model on Chest X-rays(CXR).The presented WSODTL-TBC model aims to detect and classify TB on CXR images.Primarily,the WSODTL-TBC model undergoes image filtering techniques to discard the noise content and U-Net-based image segmentation.Besides,a pre-trained residual network with a two-dimensional convolutional neural network(2D-CNN)model is applied to extract feature vectors.In addition,the WSO algorithm with long short-term memory(LSTM)model was employed for identifying and classifying TB,where the WSO algorithm is applied as a hyperparameter optimizer of the LSTM methodology,showing the novelty of the work.The performance validation of the presented WSODTL-TBC model is carried out on the benchmark dataset,and the outcomes were investigated in many aspects.The experimental development pointed out the betterment of the WSODTL-TBC model over existing algorithms.

Computer-Aided Diagnosis Model Using Machine Learning for Brain Tumor Detection and Classification

The Brain Tumor(BT)is created by an uncontrollable rise of anomalous cells in brain tissue,and it consists of 2 types of cancers they are malignant and benign tumors.The benevolent BT does not affect the neighbouring healthy and normal tissue;however,the malignant could affect the adjacent brain tissues,which results in death.Initial recognition of BT is highly significant to protecting the patient’s life.Generally,the BT can be identified through the magnetic resonance imaging(MRI)scanning technique.But the radiotherapists are not offering effective tumor segmentation in MRI images because of the position and unequal shape of the tumor in the brain.Recently,ML has prevailed against standard image processing techniques.Several studies denote the superiority of machine learning(ML)techniques over standard techniques.Therefore,this study develops novel brain tumor detection and classification model using met heuristic optimization with machine learning(BTDC-MOML)model.To accomplish the detection of brain tumor effectively,a Computer-Aided Design(CAD)model using Machine Learning(ML)technique is proposed in this research manuscript.Initially,the input image pre-processing is performed using Gaborfiltering(GF)based noise removal,contrast enhancement,and skull stripping.Next,mayfly optimization with the Kapur’s thresholding based segmentation process takes place.For feature extraction proposes,local diagonal extreme patterns(LDEP)are exploited.At last,the Extreme Gradient Boosting(XGBoost)model can be used for the BT classification process.The accuracy analysis is performed in terms of Learning accuracy,and the validation accuracy is performed to determine the efficiency of the proposed research work.The experimental validation of the proposed model demonstrates its promising performance over other existing methods.

Novel Computer-Aided Diagnosis System for the Early Detection of Alzheimer’s Disease

Aging is a natural process that leads to debility,disease,and dependency.Alzheimer’s disease(AD)causes degeneration of the brain cells leading to cognitive decline and memory loss,as well as dependence on others to fulfill basic daily needs.AD is the major cause of dementia.Computer-aided diagnosis(CADx)tools aid medical practitioners in accurately identifying diseases such as AD in patients.This study aimed to develop a CADx tool for the early detection of AD using the Intelligent Water Drop(IWD)algorithm and the Random Forest(RF)classifier.The IWD algorithm an efficient feature selection method,was used to identify the most deterministic features of AD in the dataset.RF is an ensemble method that leverages multiple weak learners to classify a patient’s disease as either demented(DN)or cognitively normal(CN).The proposed tool also classifies patients as mild cognitive impairment(MCI)or CN.The dataset on which the performance of the proposed CADx was evaluated was sourced from the Alzheimer’s Disease Neuroimaging Initiative(ADNI).The RF ensemble method achieves 100%accuracy in identifying DN patients from CN patients.The classification accuracy for classifying patients as MCI or CN is 92%.This study emphasizes the significance of pre-processing prior to classification to improve the classification results of the proposed CADx tool.

Pre-Trained Deep Neural Network-Based Computer-Aided Breast Tumor Diagnosis Using ROI Structures

Deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast tumors.However,a Brightness mode(B-mode)ultrasound image derives training feature samples that make closer isolation toward the infection part.Hence,it is expensive due to a metaheuristic search of features occupying the global region of interest(ROI)structures of input images.Thus,it may lead to the high computational complexity of the pre-trained DNN-based CABTD method.This paper proposes a novel ensemble pretrained DNN-based CABTD method using global-and local-ROI-structures of B-mode ultrasound images.It conveys the additional consideration of a local-ROI-structures for further enhan-cing the pretrained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual quality.The features are extracted at various depths(18,50,and 101)from the global and local ROI structures and feed to support vector machine for better classification.From the experimental results,it has been observed that the combined local and global ROI structure of small depth residual network ResNet18(0.8 in%)has produced significant improve-ment in pixel ratio as compared to ResNet50(0.5 in%)and ResNet101(0.3 in%),respectively.Subsequently,the pretrained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors(Benign and Malignant)and improve the diagnostic accuracy(86%)compared to Dense Net,Alex Net,VGG Net,and Google Net.Moreover,it reduces the computational complexity due to the small depth residual network ResNet18,respectively.

Framework for a Computer-Aided Treatment Prediction (CATP) System for Breast Cancer

This study offers a framework for a breast cancer computer-aided treat-ment prediction(CATP)system.The rising death rate among women due to breast cancer is a worldwide health concern that can only be addressed by early diagno-sis and frequent screening.Mammography has been the most utilized breast ima-ging technique to date.Radiologists have begun to use computer-aided detection and diagnosis(CAD)systems to improve the accuracy of breast cancer diagnosis by minimizing human errors.Despite the progress of artificial intelligence(AI)in the medical field,this study indicates that systems that can anticipate a treatment plan once a patient has been diagnosed with cancer are few and not widely used.Having such a system will assist clinicians in determining the optimal treatment plan and avoid exposing a patient to unnecessary hazardous treatment that wastes a significant amount of money.To develop the prediction model,data from 336,525 patients from the SEER dataset were split into training(80%),and testing(20%)sets.Decision Trees,Random Forest,XGBoost,and CatBoost are utilized with feature importance to build the treatment prediction model.The best overall Area Under the Curve(AUC)achieved was 0.91 using Random Forest on the SEER dataset.

Ultrafast photoemission electron microscopy:A multidimensional probe of nonequilibrium physics

Exploring the realms of physics that extend beyond thermal equilibrium has emerged as a crucial branch of condensed matter physics research.It aims to unravel the intricate processes involving the excitations,interactions,and annihilations of quasi-and many-body particles,and ultimately to achieve the manipulation and engineering of exotic non-equilibrium quantum phases on the ultrasmall and ultrafast spatiotemporal scales.Given the inherent complexities arising from many-body dynamics,it therefore seeks a technique that has efficient and diverse detection degrees of freedom to study the underlying physics.By combining high-power femtosecond lasers with real-or momentum-space photoemission electron microscopy(PEEM),imaging excited state phenomena from multiple perspectives,including time,real space,energy,momentum,and spin,can be conveniently achieved,making it a unique technique in studying physics out of equilibrium.In this context,we overview the working principle and technical advances of the PEEM apparatus and the related laser systems,and survey key excited-state phenomena probed through this surface-sensitive methodology,including the ultrafast dynamics of electrons,excitons,plasmons,spins,etc.,in materials ranging from bulk and nano-structured metals and semiconductors to low-dimensional quantum materials.Through this review,one can further envision that time-resolved PEEM will open new avenues for investigating a variety of classical and quantum phenomena in a multidimensional parameter space,offering unprecedented and comprehensive insights into important questions in the field of condensed matter physics.

Investigation of reflection anisotropy induced by micropipe defects on the surface of a 4H-SiC single crystal using scanning anisotropy microscopy

Optical reflection anisotropy microscopy mappings of micropipe defects on the surface of a 4H-SiC single crystal are studied by the scanning anisotropy microscopy(SAM)system.The reflection anisotropy(RA)image with a'butterfly pattern'is obtained around the micropipes by SAM.The RA image of the edge dislocations is theoretically simulated based on dislocation theory and the photoelastic principle.By comparing with the Raman spectrum,it is verified that the micropipes consist of edge dislocations.The different patterns of the RA images are due to the different orientations of the Burgers vectors.Besides,the strain distribution of the micropipes is also deduced.One can identify the dislocation type,the direction of the Burgers vector and the optical anisotropy from the RA image by using SAM.Therefore,SAM is an ideal tool to measure the optical anisotropy induced by the strain field around a defect.

A review of understanding electrocatalytic reactions in energy conversion and energy storage systems via scanning electrochemical microscopy

To address climate change and promote environmental sustainability,electrochemical energy conversion and storage systems emerge as promising alternative to fossil fuels,catering to the escalating demand for energy.Achieving optimal energy efficiency and cost competitiveness in these systems requires the strategic design of electrocatalysts,coupled with a thorough comprehension of the underlying mechanisms and degradation behavior occurring during the electrocatalysis processes.Scanning electrochemical microscopy(SECM),an analytical technique for studying surface electrochemically,stands out as a powerful tool offering electrochemical insights.It possesses remarkable spatiotemporal resolution,enabling the visualization of the localized electrochemical activity and surface topography.This review compiles crucial research findings and recent breakthroughs in electrocatalytic processes utilizing the SECM methodology,specifically focusing on applications in electrolysis,fuel cells,and metal–oxygen batteries within the realm of energy conversion and storage systems.Commencing with an overview of each energy system,the review introduces the fundamental principles of SECM,and aiming to provide new perspectives and broadening the scope of applied research by describing the major research categories within SECM.

Estimation-free spatial-domain image reconstruction of structured illumination microscopy

Structured illumination microscopy(SIM)achieves super-resolution(SR)by modulating the high-frequency information of the sample into the passband of the optical system and subsequent image reconstruction.The traditional Wiener-filtering-based reconstruction algorithm operates in the Fourier domain,it requires prior knowledge of the sinusoidal illumination patterns which makes the time-consuming procedure of parameter estimation to raw datasets necessary,besides,the parameter estimation is sensitive to noise or aberration-induced pattern distortion which leads to reconstruction artifacts.Here,we propose a spatial-domain image reconstruction method that does not require parameter estimation but calculates patterns from raw datasets,and a reconstructed image can be obtained just by calculating the spatial covariance of differential calculated patterns and differential filtered datasets(the notch filtering operation is performed to the raw datasets for attenuating and compensating the optical transfer function(OTF)).Experiments on reconstructing raw datasets including nonbiological,biological,and simulated samples demonstrate that our method has SR capability,high reconstruction speed,and high robustness to aberration and noise.

Capturing the non-equilibrium state in light–matter–free-electron interactions through ultrafast transmission electron microscopy

Ultrafast transmission electron microscope(UTEM) with the multimodality of time-resolved diffraction, imaging,and spectroscopy provides a unique platform to reveal the fundamental features associated with the interaction between free electrons and matter. In this review, we summarize the principles, instrumentation, and recent developments of the UTEM and its applications in capturing dynamic processes and non-equilibrium transient states. The combination of the transmission electron microscope with a femtosecond laser via the pump–probe method guarantees the high spatiotemporal resolution, allowing the investigation of the transient process in real, reciprocal and energy spaces. Ultrafast structural dynamics can be studied by diffraction and imaging methods, revealing the coherent acoustic phonon generation and photoinduced phase transition process. In the energy dimension, time-resolved electron energy-loss spectroscopy enables the examination of the intrinsic electronic dynamics of materials, while the photon-induced near-field electron microscopy extends the application of the UTEM to the imaging of optical near fields with high real-space resolution. It is noted that light–free-electron interactions have the ability to shape electron wave packets in both longitudinal and transverse directions, showing the potential application in the generation of attosecond electron pulses and vortex electron beams.

Correlation of work function and stacking fault energy through Kelvin probe force microscopy and nanohardness in diluteα-magnesium

Electronic interactions of the Group 2A elements with magnesium have been studied through the dilute solid solutions in binary Mg-Ca,Mg-Sr and Mg-Ba systems.This investigation incorporated the difference in the‘Work Function'(ΔWF)measured via Kelvin Probe Force Microscopy(KPFM),as a property directly affected by interatomic bond types,i.e.the electronic structure,nanoindentation measurements,and Stacking Fault Energy values reported in the literature.It was shown that the nano-hardness of the solid-solutionα-Mg phase changed in the order of Mg-Ca>Mg-Sr>Mg-Ba.Thus,it was shown,by also considering the nano-hardness levels,that SFE of a solid-solution is closely correlated with its‘Work Function'level.Nano-hardness measurements on the eutectics andΔWF difference between eutectic phases enabled an assessment of the relative bond strength and the pertinent electronic structures of the eutectics in the three alloys.Correlation withΔWF and at least qualitative verification of those computed SFE values with some experimental measurement techniques were considered important as those computational methods are based on zero Kelvin degree,relatively simple atomic models and a number of assumptions.As asserted by this investigation,if the results of measurement techniques can be qualitatively correlated with those of the computational methods,it can be possible to evaluate the electronic structures in alloys,starting from binary systems,going to ternary and then multi-elemental systems.Our investigation has shown that such a qualitative correlation is possible.After all,the SFE values are not treated as absolute values but rather become essential in comparative investigations when assessing the influences of alloying elements at a fundamental level,that is,free electron density distributions.Our study indicated that the principles of‘electronic metallurgy'in developing multi-elemental alloy systems can be followed via practical experimental methods,i.e.ΔWF measurements using KPFM and nanoindentation.

Microscopic growth mechanism and edge states of monolayer 1T'-MoTe_(2)

Transition metal ditellurides(TMTDs)have versatile physical properties,including non-trivial topology,Weyl semimetal states and unique spin texture.Controlled growth of high-quality and large-scale monolayer TMTDs with preferred crystal phases is crucial for their applications.Here,we demonstrate the epitaxial growth of 1T'-MoTe_(2) on Au(111)and graphitized silicon carbide(Gr/SiC)by molecular beam epitaxy(MBE).We investigate the morphology of the grown1T'-MoTe_(2) at the atomic level by scanning tunnelling microscopy(STM)and reveal the corresponding microscopic growth mechanism.It is found that the unique ordered Te structures preferentially deposited on Au(111)regulate the growth of monolayer single crystal 1T'-MoTe_(2),while the Mo clusters were preferentially deposited on the Gr/SiC substrate,which impedes the ordered growth of monolayer MoTe_(2).We confirm that the size of single crystal 1T'-MoTe_(2) grown on Au(111)is nearly two orders of magnitude larger than that on Gr/SiC.By scanning tunnelling spectroscopy(STS),we observe that the STS spectrum of the monolayer 1T'-MoTe_(2) nano-island at the edge is different from that at the interior,which exhibits enhanced conductivity.

Computer-Aided Translation Technology and Translation Teaching

With the development of computer technology, Computer-Aided Translation(CAT) is widely used in the translation process, thus increasing the efficiency of the entire translation work. The purpose of this article is to analyze the importance of introducing CAT technology into translation teaching and explore some ways of integrating CAT technology with translation teaching, so as to improve the quality of the translators and the translation work.

Computer-aided Translation Technology and Its Applications

This article begins with a brief analysis of the significance of translation technology in different spheres of modern life,followed by a distinction between machine translation(MT)and computer-aided translation(CAT).It then describes some translation resources and tools and examines the negative and positive aspects of computer-aided translations.Finally it comes to a conclusion that it would be greatly efficient and productive for the translators to acquire the new skills in the translation workplace.

Application of computer-aided engineering optimum design method in aluminum profile extrusion mould

The finite element analysis and the optimum design of aluminum profile extrusion mould were investigated using the ANSYS software and its parameterized modeling method. The optimum dimensions of the mould were obtained. It is found that the stress distribution is very uneven, and the stress convergence is rather severe in the bridge of the aluminum profile extrusion mould. The optimum height of the mould is 70.527 mm, and the optimum radius of dividing holes are 70.182 mm and 80.663 mm. Increasing the height of the mould in the range of 61.282 mm to 70.422 mm can prolong its longevity, but when the height is over 70.422 mm, its longevity reduces.

Enhanced characterization of solid solitary pulmonary nodules with Bayesian analysis-based computer-aided diagnosis

The aim of this study was to prospectively assess the accuracy gain of Bayesian analysis-based computeraided diagnosis(CAD) vs human judgment alone in characterizing solitary pulmonary nodules(SPNs) at computed tomography(CT). The study included 100 randomly selected SPNs with a definitive diagnosis. Nodule features at first and follow-up CT scans as well as clinical data were evaluated individually on a 1 to 5 points risk chart by 7 radiologists, firstly blinded then aware of Bayesian Inference Malignancy Calculator(BIMC) model predictions. Raters' predictions were evaluated by means of receiver operating characteristic(ROC) curve analysis and decision analysis. Overall ROC area under the curve was 0.758 before and 0.803 after the disclosure of CAD predictions(P = 0.003). A net gain in diagnostic accuracy was found in 6 out of 7 readers. Mean risk class of benign nodules dropped from 2.48 to 2.29, while mean risk class of malignancies rose from 3.66 to 3.92. Awareness of CAD predictions also determined a significant drop on mean indeterminate SPNs(15 vs 23.86 SPNs) and raised the mean number of correct and confident diagnoses(mean 39.57 vs 25.71 SPNs). This study provides evidence supporting the integration of the Bayesian analysis-based BIMC model in SPN characterization.

Computer-aided texture analysis combined with experts' knowledge: Improving endoscopic celiac disease diagnosis

AIM: To further improve the endoscopic detection of intestinal mucosa alterations due to celiac disease(CD).METHODS: We assessed a hybrid approach based on the integration of expert knowledge into the computerbased classification pipeline. A total of 2835 endoscopic images from the duodenum were recorded in 290 children using the modified immersion technique(MIT). These children underwent routine upper endoscopy for suspected CD or non-celiac upper abdominal symptoms between August 2008 and December 2014. Blinded to the clinical data and biopsy results, three medical experts visually classified each image as normal mucosa(Marsh-0) or villous atrophy(Marsh-3). The experts' decisions were further integrated into state-of-the-arttexture recognition systems. Using the biopsy results as the reference standard, the classification accuracies of this hybrid approach were compared to the experts' diagnoses in 27 different settings.RESULTS: Compared to the experts' diagnoses, in 24 of 27 classification settings(consisting of three imaging modalities, three endoscopists and three classification approaches), the best overall classification accuracies were obtained with the new hybrid approach. In 17 of 24 classification settings, the improvements achieved with the hybrid approach were statistically significant(P < 0.05). Using the hybrid approach classification accuracies between 94% and 100% were obtained. Whereas the improvements are only moderate in the case of the most experienced expert, the results of the less experienced expert could be improved significantly in 17 out of 18 classification settings. Furthermore, the lowest classification accuracy, based on the combination of one database and one specific expert, could be improved from 80% to 95%(P < 0.001).CONCLUSION: The overall classification performance of medical experts, especially less experienced experts, can be boosted significantly by integrating expert knowledge into computer-aided diagnosis systems.

Breast Tumor Computer-Aided Detection System Based on Magnetic Resonance Imaging Using Convolutional Neural Network

Background:The main cause of breast cancer is the deterioration of malignant tumor cells in breast tissue.Early diagnosis of tumors has become the most effective way to prevent breast cancer.Method:For distinguishing between tumor and non-tumor in MRI,a new type of computer-aided detection CAD system for breast tumors is designed in this paper.The CAD system was constructed using three networks,namely,the VGG16,Inception V3,and ResNet50.Then,the influence of the convolutional neural network second migration on the experimental results was further explored in the VGG16 system.Result:CAD system built based on VGG16,Inception V3,and ResNet50 has higher performance than mainstream CAD systems.Among them,the system built based on VGG16 and ResNet50 has outstanding performance.We further explore the impact of the secondary migration on the experimental results in the VGG16 system,and these results show that the migration can improve system performance of the proposed framework.Conclusion:The accuracy of CNN represented by VGG16 is as high as 91.25%,which is more accurate than traditional machine learningmodels.The F1 score of the three basic networks that join the secondary migration is close to 1.0,and the performance of the VGG16-based breast tumor CAD system is higher than Inception V3,and ResNet50.

3D printed nerve guidance channels: computer-aided control of geometry, physical cues, biological supplements and gradients

Nerve guidance channels for peripheral nerve injury:Over the past decade,nerve guidance channels(NGCs)have emerged as a promising technology for regenerating gap injuries in peripheral nerves.Nerve gap injuries resulting from neurodegeneration and trauma,such as car accidents and battlefield wounds,affect hundreds of thousands of people annually.Motivated by suboptimal results obtained with the current gold standard of autologous grafting(i.e.,autografts),various commercially available NGCs composed of synthetic and biomaterials are now