Independent Features Research Articles

Machine learning enabled 2D photonic crystal biosensor for early cancer detection

In this paper, a novel 2D Photonic Crystal (PC)-based cancer biosensor is proposed for the detection of different types of cancer cells HeLa, PC12, MDA, MCF, and Jurkat. The sensor is designed using Silicon-on-insulator (SOI) substrate in a triangular lattice with holes in the slab. The proposed design is optimized to provide a high-quality factor of 15,000, high sensitivity and a low detection limit that are highly effective in cancer detection. Proposed biosensor uses a series of resonant cavities that slice the resonant wavelength to a high peak resonant wavelength with a spectral linewidth of 0.1 nm. The integration of 2D PC biosensors with machine learning techniques for early and accurate cancer detection is optimized for the data set. The performance analysis of Multiple Linear Regression (MLR) and Support Vector Machine (SVM) is studied by repeating training, testing, and optimization of target values (Resonant Wavelength) with dependent and independent features of a 2D PC biosensor system. The SVM modelprovides an R squared value of 0.99 for the biosensor, and the MLR model gave an R squared value of 0.88. TheSVM model provides excellent accuracy in predicting the target values with all the trained input features of a 2D PC biosensing system.

Developmental Constitutionalism and the Fourth Branch: Ghana’s Independent Constitutional Bodies and the Redress of Poverty and Inequality

Ghana’s Constitution has long emphasised the importance of equality, democracy, human rights and development. These principles are entrenched in a separation of powers framework that includes independent constitutional bodies that operate semi-autonomously from the tripartite executive, legislative and judicial branches. As part of a symposium on so-called ‘fourth branch’ institutions that provide redress for poverty and inequality, this article explores two institutions: the Commission on Human Rights and Administrative Justice and the National Development Planning Commission. The first is a 30-year-old national human rights institution, which monitors and investigates alleged violations of human rights, corruption and the misappropriation of public moneys, and provides redress, partly through its increasing focus on economic and social rights and the claims of the most vulnerable, including women, children and persons with disabilities. The second, currently executive body, is the subject of current calls for constitutional reform in Ghana. These reforms would entrench national development planning to enhance features of autonomy, technical capacity and partisan independence. As such, these proposals offer a distinctive and yet also paradigm-defying model of fourth branch arrangements in developmental constitutionalism, raising questions about the usurpation of policymaking and the deficits of democracy that are commonly raised against courts, international financial institutions or other international economic arrangements.

An industrial process fault diagnosis method based on independent slow feature analysis and stacked sparse autoencoder network

Deep learning, with its powerful multilayer nonlinear representation of deep neural networks, enables models trained based on deep learning to describe the true distribution of data more accurately and thus have better generalization capabilities. However, the training data are usually assumed to obey independent identical distribution. Industrial process data nowadays usually have complex characteristics such as non-Gaussian, nonlinear, dynamic, strong correlation, and high-dimensional, which make it difficult to meet the assumptions of deep learning. Using industrial process data directly would result in low model accuracy and bias in the model output. This paper proposes a fault diagnosis method based on independent slow feature analysis (ISFA) and stacked sparse autoencoder (SSAE) network. The statistical properties possessed by ISFA are used to perform preliminary feature extraction of industrial process data, and then the extracted preliminary features are input to the SSAE network for fine-grained feature extraction. The proposed two-step feature extraction method not only makes the data input to the SSAE network as close as possible to obey independent identical distribution and provides convincing fault diagnosis results, but also makes full use of the powerful feature extraction capability of the SSAE network, which makes the proposed method also significantly improve the detection accuracy of incipient faults. The feasibility and superiority of the proposed method is verified through the TE process.

An intelligent sparse feature extraction approach for music data component recognition and analysis of hybrid instruments

In this paper, a sparse feature extraction method is presented based on sparse decomposition and multiple musical instrument component dictionaries to address the challenges of existing methods in component-recognition and analysis of mixed musical instrument music data. These methods, which are often dependent on data labels, and rely primarily on frequency domain or physical features, can be improved significantly using this technique. Through the in-depth analysis of the sparse coefficient vectors, this method is capable of generating independent sparse music features that are highly interpretable and have been shown to intuitively express the composition of musical instruments, and capture the variations of emotion in the music. Consequently, this approach has great potential for application in the field of mixed musical instrument composition analysis and other time-varying signal analysis.

Enhancing Mental Fatigue Detection through Physiological Signals and Machine Learning Using Contextual Insights and Efficient Modelling

This research presents a machine learning modeling process for detecting mental fatigue using three physiological signals: electrodermal activity, electrocardiogram, and respiration. It follows the conventional machine learning modeling pipeline, while emphasizing the significant contribution of the feature selection process, resulting in, not only a high-performance model, but also a relevant one. The employed feature selection process considers both statistical and contextual aspects of feature relevance. Statistical relevance was assessed through variance and correlation analyses between independent features and the dependent variable (fatigue state). A contextual analysis was based on insights derived from the experimental design and feature characteristics. Additionally, feature sequencing and set conversion techniques were employed to incorporate the temporal aspects of physiological signals into the training of machine learning models based on random forest, decision tree, support vector machine, k-nearest neighbors, and gradient boosting. An evaluation was conducted using a dataset acquired from a wearable electronic system (in third-party research) with physiological data from three subjects undergoing a series of tests and fatigue stages. A total of 18 tests were performed by the 3 subjects in 3 mental fatigue states. Fatigue assessment was based on subjective measures and reaction time tests, and fatigue induction was performed through mental arithmetic operations. The results showed the highest performance when using random forest, achieving an average accuracy and F1-score of 96% in classifying three levels of mental fatigue.

A cell image segmentation method based on edge feature residual fusion.

In recent years, cancer has seriously damaged human health, and the morphological structure of cells serves as an important basis for cancer diagnosis and grading. Automatic cell segmentation based on deep learning has become an important means of computer-aided pathological diagnosis. Aiming at the existing problems of rough segmentation boundaries and inaccurate segmentation in cell image segmentation, this paper designs a cell image segmentation network model (ERF-TransUNet) based on edge feature residual fusion from the perspective of mutual complementarity and constraint between edge features and object features. The model uses a hybrid architecture of CNN and Transformer to extract multi-scale features from cell images, and adds independent edge feature extraction modules and residual fusion modules to enhance the extraction of edge features and their constraints when fusing with cell object features, improving the accuracy of cell contour positioning. Through experiments on two gland cell datasets, CRAG and Glas, and comparing the segmentation effects with current popular deep learning models, the network model proposed in this paper has achieved good performance in both Dice coefficient and Hausdorff distance, which can effectively improve the segmentation effect of cell images.

Feature-Specific Salience Maps in Human Cortex.

Priority map theory is a leading framework for understanding how various aspects of stimulus displays and task demands guide visual attention. Per this theory, the visual system computes a priority map, which is a representation of visual space indexing the relative importance, or priority, of locations in the environment. Priority is computed based on both salience, defined based on image-computable properties; and relevance, defined by an individual's current goals, and is used to direct attention to the highest-priority locations for further processing. Computational theories suggest that priority maps identify salient locations based on individual feature dimensions (e.g., color, motion), which are integrated into an aggregate priority map. While widely accepted, a core assumption of this framework, the existence of independent feature dimension maps in visual cortex, remains untested. Here, we tested the hypothesis that retinotopic regions selective for specific feature dimensions (color or motion) in human cortex act as neural feature dimension maps, indexing salient locations based on their preferred feature. We used fMRI activation patterns to reconstruct spatial maps while male and female human participants viewed stimuli with salient regions defined by relative color or motion direction. Activation in reconstructed spatial maps was localized to the salient stimulus position in the display. Moreover, the strength of the stimulus representation was strongest in the ROI selective for the salience-defining feature. Together, these results suggest that feature-selective extrastriate visual regions highlight salient locations based on local feature contrast within their preferred feature dimensions, supporting their role as neural feature dimension maps.SIGNIFICANCE STATEMENT Identifying salient information is important for navigating the world. For example, it is critical to detect a quickly approaching car when crossing the street. Leading models of computer vision and visual search rely on compartmentalized salience computations based on individual features; however, there has been no direct empirical demonstration identifying neural regions as responsible for performing these dissociable operations. Here, we provide evidence of a critical double dissociation that neural activation patterns from color-selective regions prioritize the location of color-defined salience while minimally representing motion-defined salience, whereas motion-selective regions show the complementary result. These findings reveal that specialized cortical regions act as neural "feature dimension maps" that are used to index salient locations based on specific features to guide attention.

Machine Learning Approach for Diagnosis and Prognosis of Cardiac Arrhythmia Condition Using a Minimum Feature Set and Auto-Segmentation-Based Window Optimisation

Cardiovascular diseases have become extremely prevalent in the global population. Several accurate classification methods for arrhythmias have been proposed in the healthcare literature. However, extensive research is required to improve the prediction accuracy of various arrhythmia conditions. In this paper, discussion is focussed on two major objectives: optimisation of windows based on our proposed auto-segmentation method for the exact diagnosis of the heart condition within the segment and prediction of arrhythmia progression. For prediction, identification of features is vital. Identified efficient independent feature sets such as RR interval, peak-to-peak amplitude, and unique derived parameters such as coefficient of variation (CV) of RR interval and CV of peak-to-peak amplitude. The progression of arrhythmia includes the following steps such as data preprocessing, time and frequency domain feature extraction, and feature selection using principal component analysis. A hypertuned support vector machine is utilised for accurate diagnosis. Proposed two techniques to predict the progression of arrhythmias: the regression-based trend curve (RBTC) and the fuzzy enhanced Markov model (FEMM). We have effectively evaluated our prediction algorithms using offline Massachusetts Institute of Technology Physio Net database signals, using automatic segmentation with prediction accuracy of 98 %. In terms of accuracy, FEMM outperforms RBTC. Thus, an auto-segmentation algorithm was proposed to classify various arrhythmia signals using a minimal feature set and to predict future conditions using our proposed method, FEMM.

TSMPN-PSI: high-performance polarization scattering imaging based on three-stage multi-pipeline networks.

Polarization imaging, which provides multidimensional information beyond traditional intensity imaging, has prominent advantages for complex imaging tasks, particularly in scattering environments. By introducing deep learning (DL) into computational imaging and sensing, polarization scattering imaging (PSI) has obtained impressive progresses, however, it remains a challenging but long-standing puzzle due to the fact that scattering medium can result in significant degradation of the object information. Herein, we explore the relationship between multiple polarization feature learning strategy and the PSI performances, and propose a new multi-polarization driven multi-pipeline (MPDMP) framework to extract rich hierarchical representations from multiple independent polarization feature maps. Based on the MPDMP framework, we introduce a well-designed three-stage multi-pipeline networks (TSMPN) architecture to achieve the PSI, named TSMPN-PSI. The proposed TSMPN-PSI comprises three stages: pre-processing polarization image for de-speckling, multiple polarization feature learning, and target information reconstruction. Furthermore, we establish a real-world polarization scattering imaging system under active light illumination to acquire a dataset of real-life scenarios for training the model. Both qualitative and quantitative experimental results show that the proposed TSMPN-PSI achieves higher generalization performance than other methods on three testing data sets refer to imaging distances, target structures, and target materials and their background materials. We believe that our work presents a new framework for the PSI and paves the way to its pragmatic applications.

Development and validation of stable ferroptosis- and pyroptosis-related signatures in predicting prognosis and immune status in breast cancer.

To develop and validate the predictive effects of stable ferroptosis- and pyroptosis-related features on the prognosis and immune status of breast cancer (BC). We retrieved as well as downloaded ferroptosis- and pyroptosis-related genes from the FerrDb and GeneCards databases. The minimum absolute contraction and selection operator (LASSO) algorithm in The Cancer Genome Atlas (TCGA) was used to construct a prognostic classifier combining the above two types of prognostic genes with differential expression, and the Integrated Gene Expression (GEO) dataset was used for validation. Seventeen genes presented a close association with BC prognosis. Thirteen key prognostic genes with prognostic value were considered to construct a new expression signature for classifying patients with BC into high- and low-risk groups. Kaplan-Meier analysis revealed a worse prognosis in the high-risk group. The receiver operating characteristic (ROC) curve and multivariate Cox regression analysis identified its predictive and independent features. Immune profile analysis showed that immunosuppressive cells were upregulated in the high-risk group, and this risk model was related to immunosuppressive molecules. We successfully constructed combined features of ferroptosis and pyroptosis in BC that are closely related to prognosis, clinicopathological and immune features, chemotherapy efficacy and immunosuppressive molecules. However, further experimental studies are required to verify these findings.

Fast Automatic Registration of UAV Images via Bidirectional Matching.

Image registration plays a vital role in the mosaic process of multiple UAV (Unmanned Aerial Vehicle) images acquired from different spatial positions of the same scene. Aimed at the problem that many fast registration methods cannot provide both high speed and accuracy simultaneously for UAV visible light images, this work proposes a novel registration framework based on a popular baseline registration algorithm, ORB-the Oriented FAST (Features from Accelerated Segment Test) and Rotated BRIEF (Binary Robust Independent Elemental Features) algorithm. First, the ORB algorithm is utilized to extract image feature points fast. On this basis, two bidirectional matching strategies are presented to match obtained feature points. Then, the PROSRC (Progressive Sample Consensus) algorithm is applied to remove false matches. Finally, the experiments are carried out on UAV image pairs about different scenes including urban, road, building, farmland, and forest. Compared with the original version and other state-of-the-art registration methods, the bi-matching ORB algorithm exhibits higher accuracy and faster speed without any training or prior knowledge. Meanwhile, its complexity is quite low for on-board realization.

Regularized Maximum Correntropy Criterion Kalman Filter for Uncalibrated Visual Servoing in the Presence of Non-Gaussian Feature Tracking Noise.

Some advantages of using cameras as sensor devices on feedback systems are the flexibility of the data it represents, the possibility to extract real-time information, and the fact that it does not require contact to operate. However, in unstructured scenarios, Image-Based Visual Servoing (IBVS) robot tasks are challenging. Camera calibration and robot kinematics can approximate a jacobian that maps the image features space to the robot actuation space, but they can become error-prone or require online changes. Uncalibrated visual servoing (UVS) aims at executing visual servoing tasks without previous camera calibration or through camera model uncertainties. One way to accomplish that is through jacobian identification using environment information in an estimator, such as the Kalman filter. The Kalman filter is optimal with Gaussian noise, but unstructured environments may present target occlusion, reflection, and other characteristics that confuse feature extraction algorithms, generating outliers. This work proposes RMCKF, a correntropy-induced estimator based on the Kalman Filter and the Maximum Correntropy Criterion that can handle non-Gaussian feature extraction noise. Unlike other approaches, we designed RMCKF for particularities in UVS, to deal with independent features, the IBVS control action, and simulated annealing. We designed Monte Carlo experiments to test RMCKF with non-Gaussian Kalman Filter-based techniques. The results showed that the proposed technique could outperform its relatives, especially in impulsive noise scenarios and various starting configurations.

An investigation of Glaucoma Detection in RFI Using Bio-Inspired Multivariable FE with ML Models for Early Diagnosis

To propose a bio-inspired multi-variant feature extraction technique in retinal fundus images to improve glaucoma detection for easy diagnosis. To improve the classification accuracy of glaucoma disease, a machine learning approach is employed based on the features extracted in RFI. Methods: The Fish School Search MOFS (FSS-MOFS) bio-inspired technique is employed to extract the multivariable features from digital RFI and spot the glaucoma variations to maximize the discrimination power and minimize the dimensionality. The Binary Robust Independent Elementary Feature (BRIEF-LD) technique is employed to identify the latent spots in RFI. The PAPILA dataset is utilized for this research study, which includes the clinical records of 244 patients and 488 images of the right and left eye of all the patients under 2 categories (male and female) with results in healthy, glaucoma, and suspect categories. In order to perform deep pixel identification and RFI segmentation, the Densenet-121 architecture is used along with a deep-lab model to incarcerate the built-in fine points of RFI with the help of dilated convolutions. The MATLAB tool is used to assess the suggested bio-inspired technique, and comparative analysis is done against the prevailing glaucoma detection and feature extraction methods such as I-SVM, RFSO, SE-GSO, VGG-Net, and DBN classifiers. Findings: The suggested FSS-MOFS multi-variant feature extraction technique outperforms the prevailing ML methods such as I-SVM, RFSO, SE-GSO, VGG-Net, and DBN classifiers. The result of the comparative study shows 94% accuracy, 96% sensitivity, 97% specificity, 96% F-measure, 96.8% Precision, 97% recall, 95% detection speed, 92.06% TPR, 92.15% TNR, and 8% FPR & FNR. Novelty: The promising result of the FSS-MOFS method boosts the accuracy level of glaucoma detection and classification compared to other classification techniques. The suggested model helps the ophthalmologists identify and diagnose glaucoma in a robust way. FSS-MOFS overcomes the shortcomings of prevailing feature extraction methods.

Resource allocation strategy for blockchain-enabled NOMA-based MEC networks

Blockchain technology is getting more and more attention due to its decentralization, independence and security features. However, in wireless networks it faces a computational challenge: the proof-of-work problem. Mobile edge computing (MEC) leads to a vaild scheme by providing cloud computing capabilities to mobile devices. Non-orthogonal multiple access (NOMA) exploits the diversity properties in the power domain to further increase system throughput and spectral efficiency. In this paper, we suggest a new NOMA-based MEC wireless blockchain network to minimize system energy consumption through task offloading decision optimization, user clustering, computing resource and transmit power allocation. In order to effectively figure out this non-convex problem, we first propose a offloading decision and user clustering algorithm, and then propose a computing resource allocation algorithm based on user Quality of Service (QoS) requirements. Finally, the transmission power can be easily determined. The numerical simulation results verify that the proposed joint optimization algorithm can effectively decrease the system energy consumption.

Hybrid Navigation of an Autonomous Mobile Robot to Depress an Elevator Button

The development of an autonomous mobile robot (AMR) with an eye-in-hand robot arm atop for depressing elevator button is proposed. The AMR can construct map and perform localization using the ORB-SLAM algorithm (the Oriented FAST (Features from Accelerated Segment Test) and Rotated BRIEF (Binary Robust Independent Elementary Features) feature detector-Simultaneous Localization and Mapping). It is also capable of real-time obstacle avoidance using information from 2D-LiDAR sensors. The AMR, robot manipulator, cameras, and sensors are all integrated under robot operating system (ROS). In experimental investigation to dispatch the AMR for depressing an elevator button, AMR navigation initiating from the laboratory is divided into three parts. First, the AMR initiated navigation using ORB-SLAM for most of the journey to a waypoint nearby the elevator. The resulting mean absolute error (MAE) is 8.5 cm on the x-axis, 10.8 cm on the y-axis, 9.2-degree rotation angle about the z-axis, and the linear displacement from the reference point is 15.1 cm. Next, the ORB-SLAM is replaced by an odometry based 2D-SLAM method for further navigating the AMR from waypoint to a point facing the elevator between 1.5 to 3 meter distance, where the ORB-SLAM is ineffective due to sparse feature points for localization and where the elevator can be clearly detected by an eye-in-hand machine vision onboard the AMR. Finally, the machine vision identifies space position of the elevator and again the odometry based 2D SLAM method is employed for navigating the AMR to front of the elevator between 0.3 to 0.5 meter distance. Only at this stage, the small-size elevator button can be detected and reached by the robot arm on the AMR. An averaged 60% successful rate of button depressing by the AMR starting at the laboratory is obtained in the experiments. Improvements of successful elevator button depressing rate are also pointed out.

A Robust State of Charge Estimator Based on the Fourier Neural Operator for xEV Batteries

This paper proposes a new state of charge estimation method inspired by the Fourier neural operator. The Fourier neural operator is capable of learning entire nonlinear dynamics of any partial differential equations. The complicated nonlinear dynamics of battery parameters is well captured by a flexible, efficient and expressive structure of the Fourier neural operators. Extensive numerical experiments and tests with a publicly available data as well as with our own data are conducted to demonstrate the noise-tolerance, time window independence, temperature generalization and transfer learning features of the proposed method. Our proposed method, as a robust SOC estimator, performs better than the other methods considered previously and the performances are in competitive manner with any state-of-the-art machine learning based methods.

Interpretable thoracic pathologic prediction via learning group-disentangled representation.

Deep learning has brought a significant progress in medical image analysis. However, their lack of interpretability might bring high risk for wrong diagnosis with limited clinical knowledge embedding. In other words, we believe it's crucial for humans to interpret how deep learning work for medical analysis, thus appropriately adding knowledge constraints to correct the bias of wrong results. With such purpose, we propose Representation Group-Disentangling Network (RGD-Net) to explain the process of feature extraction and decision making inside deep learning framework, where we completely disentangle feature space of input X-ray images into independent feature groups, and each group would contribute to diagnose of a specific disease. Specifically, we first state problem definition for interpretable prediction with auto-encoder structure. Then, group-disentangled representations are extracted from input X-ray images with the proposed Group-Disentangle Module, which constructs semantic latent space by enforcing semantic consistency of attributes. Afterwards, adversarial constricts on mapping from features to diseases are proposed to prevent model collapse during training. Finally, a novel design of local tuning medical application is proposed based on RGB-Net, which is capable to aid clinicians for reasonable diagnosis. By conducting quantity of experiments on public datasets, RGD-Net have been superior to comparative studies by leveraging potential factors contributing to different diseases. We believe our work could bring interpretability in digging inherent patterns of deep learning on medical image analysis.

Deformities Influencing Different Classes in Progressive Collapsing Foot

Category: Midfoot/Forefoot; Hindfoot Introduction/Purpose: The current classification system of progressive collapsing foot deformity (PCFD) is comprised of 5 possible classes. PCFD is understood to be a complex, three-dimensional deformity occurring in many regions along the foot and ankle. The question remains whether a deformity in one area impacts other areas. The objective of this study is to assess how each one of the classes is influenced by other classes by evaluating each associated angular measurement. We hypothesized that positive and linear correlations would occur for each class with at least one other class and that this influence would be high. Methods: We retrospectively assessed weight-bearing computed tomography (WBCT) measurements of 32 feet with PCFD diagnosis. The classes and their associated radiographic measurements were defined as follows: class A (hindfoot valgus) measured by the hindfoot moment arm (HMA), class B (midfoot abduction) measured by the talonavicular coverage angle (TNCA), class C (medial column instability) measured by Meary’s angle, class D (peritalar subluxation) measured by the medial facet uncoverage (MFU), and class E (ankle valgus) measured using the talar tilt angle (TTA). Multivariate analyses were completed comparing each class measurement to the other classes. A p-value < 0.05 was considered significant. Results: Class A showed a substantial positive correlation with class C (ρ=0.71; R2=0.576; p 0.001). Class B was substantially correlated with class D (ρ=0.74; R2=0.613; p 0.001). Class C showed a substantial positive correlation with class A (ρ=0.71; R2=0.576; p 0.001) and class D (ρ=0.75; R2=0.559; p 0.001). Class D showed a substantial positive correlation with class B and class C (ρ=0.74; R2=0.613; p 0.001), (ρ=0.75; R2=0.559; p 0.001) respectively. Class E did not show correlation with class B, C, or D (ρ=0.24; R2=0.074; p=0.059), (ρ=0.17; R2=0.071; p=0.179), and (ρ=0.22; R2=0.022; p=0.082) respectively. The average values of each class radiographic markers are listed in Figure 1. Conclusion: This study was able to find relations between components of PCFD deformity with exception of ankle valgus deformity (Class E). Measurements associated with each class were influenced by others, and in some instances, with pronounced strength such as between class A and C as well as between Class B and D. Surgical procedures to address certain class deformities could indirectly address other classes as well, which ultimately decreases surgical procedures numbers or complexity. The presented data may support the notion that PCFD is a three-dimensional complex deformity and suggests a possible relation among its ostensibly independent features.

Novel Functional Radiomics for Prediction of Cardiac PET Avidity in Lung Cancer Radiotherapy

Traditional methods of evaluating cardiotoxicity focus solely on radiation doses to the heart and do not incorporate functional imaging information. Functional imaging has great potential to improve the ability to provide early prediction for cardiotoxicity for lung cancer patients undergoing radiotherapy. FDG-based PET/CT imaging is routinely obtained as part of standard staging work up for lung cancer patients. Although FDG PET/CT scans are typically used to evaluate the tumor, imaging guidelines note that FDG PET/CT scans are an FDA-approved method to image for cardiac inflammation, and studies have noted that the PET cardiac signal can be predictive of clinical outcomes. The purpose of this work was to develop a radiomics model to predict clinical cardiac assessment of standard of care FDG PET/CT scans. The study included 100 consecutive lung cancer patients treated with radiotherapy who underwent standard pre-treatment FDG-PET/CT staging scans. A clinician reviewed the PET/CT scans per clinical cardiac assessment guidelines and classified the cardiac uptake as: 0 = uniform diffuse, 1 = absent, 2 = heterogeneous, with event rates of 20%, 44%, and 35%, respectively. The heart was delineated and 200 novel functional radiomics features were selected to classify cardiac FDG uptake patterns. We divided the data into an 80% training set and a 20% test set to train and evaluate the classification models. Feature reduction was carried out using the Wilcoxon test (with Bonferroni adjusted p<0.05), hierarchical clustering, and Recursive Feature Elimination. Two automatic machine learning (AutoML) frameworks were used to determine classification models: a Random Forest Classifier (Tree-based Pipeline Optimization Tool, TPOT) and Linear Discriminant Analysis (AutoSklearn). 10-fold cross validation was carried out for training and the accuracy of the ability of the models to predict for clinical cardiac assessment is reported. Fifty-one independent radiomics features were reduced to 3 clinically pertinent features (PET 2D Skewness, PET Grey Level Co-occurrence Matrix Correlation, and PET Median) using feature reduction techniques. The model selected by TPOT showed 89.8% predictive accuracy in the cross validation of the training set and 85% predictive accuracy on the test set. The model selected by AutoSklearn showed 89.7% predictive accuracy in the cross validation of the training set and 80% predictive accuracy on the test set. The novelty of this work is that it is the first study to develop and evaluate functional cardiac radiomic features from standard of care FDG PET/CT scans with the data showing good predictive accuracy with clinical imaging evaluation. If validated, the current work provides automated methods to provide functional cardiac information using standard of care imaging that can be used as an imaging biomarker for early clinical toxicity prediction for lung cancer patients.

An accurate novel circular hole inspection method for sheet metal parts using edge-guided robust multi-view stereo

Sheet metal parts are frequently used in the industrial field, and the circular holes on these parts are commonly employed as assembly references. Therefore, precise measurement of these circular holes is essential. Because of the scratches, rust, and complex reflection around the edges, the measurement of circular holes on sheet metal parts is a challenging task. In this research, an accurate circular hole inspection method for sheet metal parts is proposed to realize online inspection using a multi-camera system. After capturing images in a single shot, edge detection is adopted to obtain sub-pixel circular hole contours. A new adaptive matching cost based on the descriptor of binary robust independent elementary features and bilinear normalized cross-correlation is introduced to the PatchMatch-based multi-view stereo method to obtain dense and accurate point clouds. To improve the accuracy and integrity of circular hole measurement, a new edge-guided multi-scale geometric consistency matching strategy is proposed accompanied by depth detail restoration. Finally, the points around the circular hole in a spherical range are sampled using the trinocular constraint principle and fitted with the circular equation. The experimental results show that the proposed algorithm performs well, with an error of approximately 0.04 mm, and improves the measurement accuracy compared with the state-of-the-art algorithms.