Robust Detection Research Articles

Robust ROI Detection in Whole Slide Images Guided by Pathologists' Viewing Patterns.

Deep learning techniques offer improvements in computer-aided diagnosis systems. However, acquiring image domain annotations is challenging due to the knowledge and commitment required of expert pathologists. Pathologists often identify regions in whole slide images with diagnostic relevance rather than examining the entire slide, with a positive correlation between the time spent on these critical image regions and diagnostic accuracy. In this paper, a heatmap is generated to represent pathologists' viewing patterns during diagnosis and used to guide a deep learning architecture during training. The proposed system outperforms traditional approaches based on color and texture image characteristics, integrating pathologists' domain expertise to enhance region of interest detection without needing individual case annotations. Evaluating our best model, a U-Net model with a pre-trained ResNet-18 encoder, on a skin biopsy whole slide image dataset for melanoma diagnosis, shows its potential in detecting regions of interest, surpassing conventional methods with an increase of 20%, 11%, 22%, and 12% in precision, recall, F1-score, and Intersection over Union, respectively. In a clinical evaluation, three dermatopathologists agreed on the model's effectiveness in replicating pathologists' diagnostic viewing behavior and accurately identifying critical regions. Finally, our study demonstrates that incorporating heatmaps as supplementary signals can enhance the performance of computer-aided diagnosis systems. Without the availability of eye tracking data, identifying precise focus areas is challenging, but our approach shows promise in assisting pathologists in improving diagnostic accuracy and efficiency, streamlining annotation processes, and aiding the training of new pathologists.

Detection of residual pluripotent stem cells in cell therapy products utilizing droplet digital PCR: an international multisite evaluation study.

The presence of residual undifferentiated pluripotent stem cells (PSCs) in PSC-derived cell therapy products (CTPs) is a major safety issue for their clinical application, due to the potential risk of PSC-derived tumor formation. An international multidisciplinary multisite study to evaluate a droplet digital PCR (ddPCR) approach to detect residual undifferentiated PSCs in PSC-derived CTPs was conducted as part of the Health and Environmental Sciences Institute Cell Therapy-TRAcking, Circulation & Safety Technical Committee. To evaluate the use of ddPCR in quantifying residual iPSCs in a cell sample, different quantities of induced pluripotent stem cells (iPSCs) were spiked into a background of iPSC-derived cardiomyocytes (CMs) to mimic different concentrations of residual iPSCs. A one step reverse transcription ddPCR (RT-ddPCR) was performed to measure mRNA levels of several iPSC-specific markers and to evaluate the assay performance (precision, sensitivity, and specificity) between and within laboratories. The RT-ddPCR assay variability was initially assessed by measuring the same RNA samples across all participating facilities. Subsequently, each facility independently conducted the entire process, incorporating the spiking step, to discern the parameters influencing potential variability. Our results show that a RT-ddPCR assay targeting ESRG, LINC00678, and LIN28A genes offers a highly sensitive and robust detection of impurities of iPSC-derived CMs and that the main contribution to variability between laboratories is the iPSC-spiking procedure, and not the RT-ddPCR. The RT-ddPCR assay would be generally applicable for tumorigenicity evaluation of PSC-derived CTPs with appropriate marker genes suitable for each CTP.

IMC-ResNet: Atrial fibrillation detection method based on interlayer multiscale coupling

Atrial fibrillation(AF) is one of the most common cardiac arrhythmias, and reliable detection of it is of significant importance. This study proposes a multilayer convolutional neural network for AF detection, which introduces the Multiscale Information Interaction module composed of a Detail Enhancer and a Context Information Extractor to achieve the extraction and coupling of multiscale information between layers. The Detail Enhancer is composed of multiscale transposed convolutions to encode waveform details in the electrocardiogram (ECG). The Context Information Extractor is composed of multiscale dilated convolutions to encode the morphological information of the ECG. Furthermore, the Multiscale Information Interaction module is used in conjunction with residual blocks to model the surface feature correlation and intrinsic abstract structure of AF signals. This approach extracts implicit information of AF from ECG signals, achieving high-precision and robust detection of AF. Five-fold cross-validation on the AFDB dataset resulted in an accuracy of 99.56% and an F1-score of 99.65%. Inter-patient testing on the clinical SPHDB database yielded an accuracy of 96.17% and an F1-score of 96.14%. In addition, this study conducted experiments to evaluate the model’s robustness against noise, yielding favorable results across four types of noise tests. The results indicate that the proposed method has great potential for application in clinical auxiliary diagnosis based on wearable devices.

Application of Digital Twin Technology in Synthetic Aperture Radar Ground Moving Target Intelligent Detection System

In recent years, the detection performance of SAR-GMTI (synthetic aperture radar-ground moving target indication) algorithm based on deep learning has always been limited by insufficient measured data due to the heavy operation complexity and high cost of real SAR systems. To solve this problem, this paper proposes an overall DT-based implementation framework for SAR ground moving target intelligent detection tasks. In particular, by virtue of a SAR imaging algorithm, a high-fidelity twin replica of SAR moving targets is established in digital space through parameter traversal based on the prior target characteristics of the obtained measured datasets. Then, the constructed SAR twin datasets is fed into the neural network model to train an intelligent detector by fully learning features of the moving targets and preset the SAR scene in the twin space, which can realize the robust detection of ground moving targets in related practical scenarios with no need for multiple and complex field experiments. Moreover, the effectiveness of the proposed framework is verified on the MiniSAR measured system, and a comparison with traditional CFAR detection method is given simultaneously.

Portable and ultrasensitive detection of traces of water in alcoholic solvents by a polypyrrole-modified screen-printed electrode

In industrial production, the water content in alcoholic solvents is crucial for determining the quality and yield of the final products, and excessive water can potentially lead to accidents. However, in-situ, rapid, and accurate detection of trace amounts of water in alcoholic solvents has been a persistent challenge. Herein, we report a screen-printed electrode (SPE) modified with electroactive polypyrrole (PPy@SPE), which enables rapid and ultrasensitive quantification of water content in four alcoholic solvents. The amine groups on PPy provide hydrogen bonding sites, which, in conjunction with the rough surface of the SPE, enhance the adsorption of alcohol molecules and decrease the electrochemical response of the PPy@SPE due to the hindrance of charge transfer. Under optimal conditions, the PPy@SPE can detect water levels as low as 0.02 %, 0.01 %, 0.01 %, and 0.01 %, in methanol, ethanol, n-propanol, and isopropanol, respectively, and can be reused for six cycles or more. Furthermore, the capability for in-situ detection of water in alcoholic solvents was demonstrated by integrating the PPy@SPE with a miniaturized potentiostat. With the advantages of being ultrasensitive, robust, low-cost, and facile detection, this sensor is potentially a valuable tool for on-site water content monitoring in chemical industries.

Robust change point detection for high‐dimensional linear models with tolerance for outliers and heavy tails

Robust change point detection for high‐dimensional linear models with tolerance for outliers and heavy tails

Robust marker detection and identification using deep learning in underwater images for close range photogrammetry

The progressing industrialization of oceans mandates reliable, accurate and automatable subsea survey methods. Close-range photogrammetry is a promising discipline, which is frequently applied by archaeologists, fish-farmers, and the offshore energy industry. This paper presents a robust approach for the reliable detection and identification of photogrammetric markers in subsea images. The proposed method is robust to severe image degradation, which is frequently observed in underwater images due to turbidity, light absorption, and optical aberrations. This is the first step towards a highly automated work-flow for single-camera underwater photogrammetry. The newly developed approach comprises several machine learning models, which are trained by 10,122 real-world subsea images, showing a total of 338,301 photogrammetric markers. The performance is evaluated using an object detection metrics, and through a comparison with the commercially available software Metashape by Agisoft. Metashape delivers satisfactory results when the image quality is good. In images with strong noise, haze or little light, only the novel approach retrieves sufficient information for a high degree of automation of the subsequent bundle adjustment. While the need for offshore personnel and the time-to-results decreases, the robustness of the survey increases.

Robust Signal Detection in Complex Noise and Interference Environment Based on MoG Modeling

Robust Signal Detection in Complex Noise and Interference Environment Based on MoG Modeling

Ensemble learning techniques against structured query language injection attacks

Structured query language (SQL) injection threats pose severe risks to web applications, necessitating robust detection measures. This study introduced DSQLIA, employing ensemble learning algorithms-Bagging, Stacking, and AdaBoost classifiers-for SQL injection detection. Results unveiled the bagging classifier's 84% accuracy with perfect precision (100%) but moderate recall (68%). The stacking classifier achieved 85% accuracy, exceptional precision (99%), and balanced memory (72%), yielding an 83% F1-Score. Remarkably, the AdaBoost classifier outperformed, achieving 99% accuracy, high precision (98%), and outstanding recall (99%), leading to a remarkable 99% F1-Score. These findings highlight AdaBoost's superior ability to identify malicious queries with minimal false positives accurately. Overall, this research underscores the potential of ensemble learning in fortifying web application security against SQL injection attacks, emphasizing the AdaBoost classifier's exceptional performance in achieving precise and comprehensive detection.

A robust defect detection method with a generalization enhancer and cross-modality aggregator for cylinder bores

High-quality cylinder bores in automobile engines enable drivers to respond quickly to emergencies. Automated detection methods are gradually being adopted across various industries. However, uncontrollable factors and improper preservation methods lead to various types of defects on cylinder bores, thereby causing existing high-performance detectors to exhibit not only undesirable generalizability for unseen defect types but also a certain degree of missed detection for defects of seen types, thereby allowing defective cylinder bores to flow into the market. To address these issues, we propose a foundation-model-based robust defect detection method with high generalizability for cylinder bores (RHG-Detector). Specifically, to address unseen defect categories, we propose a generalization enhancer comprising a box filter, a region extractor and a defect discriminator (DeDi) based on a foundation model to extend defect detection from a closed set to an open set. To reduce missed detections, we adopt a cross-modality aggregator to aggregate the detection results from different modalities. Additionally, we collected and annotated challenging defect classification and detection datasets for cylinder bores, named HIT-EngDC (Harbin Institute of Technology Engine defect classification dataset) and HIT-EngDD2 (Engine defect detection dataset-version 2), which cover nearly all types of cylinder bore defects. Extensive experiments on HIT-EngDC and HIT-EngDD2 demonstrate the state-of-the-art performance of RHG-Detector, with a classification accuracy of 92.0 and a mAP@50 (mean average precision under intersection over union = 0.5) score of 45.2, where the latter is increased by ∼6 and ∼3 compared to the corresponding FasterRCNN (faster region-based convolutional neural networks) and YOLOv7 (you only look once) scores, respectively.

Two deep learning methods in comparison to characterize droplet sizes in emulsification flow processes

AbstractFor reliable supervision in multiphase processes, the droplet size represents a critical quality attribute and needs to be monitored. A promising approach is the use of smart image flow sensors since optical measurement is the most commonly used technique for droplet size distribution determination. For this, two different AI-based object detection methods, Mask RCNN and YOLOv4, are compared regarding their accuracy and their applicability to an emulsification flow process. Iterative optimization steps, including data diversification and adaption of training parameters, enable the models to achieve robust detection performance across varying image qualities and compositions. YOLOv4 shows better detection performances and more accurate results which leads to a wider application window than Mask RCNN in determining droplet sizes in emulsification processes. The final droplet detection model YOLOv4 with Hough Circle (HC) for feature extraction determines reliable droplet sizes across diverse datasets of liquid-liquid flow systems (disperse phase content 1–15 vol.-%, droplet size range 5–150 μm). Evaluating the adjustment of Confidence Scores (CS) ensures statistical representation of even smaller droplets. The droplet detection performance of the final YOLOv4 model is compared with a manual image processing method to validate the model in general as well as its accuracy and reliability. Since YOLOv4 in combination with Hough Circle (HC) shows an accurate and robust detection and size determination, it is applicable for online monitoring and characterization of various liquid-liquid flow processes. Graphical abstract

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

CRRFNet: An adaptive traffic object detection method based on camera and radar radio frequency fusion

A large number of studies have proved that camera and radar fusion is a useful and economical solution for traffic object detection. However, how to improve the reliability and robustness of fusion methods is still a huge challenge. In this paper, an adaptive traffic object detection method based on a camera and radar radio frequency Network (CRRFNet) is proposed, to solve the problem of robust and reliable traffic object detection in noisy or abnormal scenes. Firstly, two different deep convolution modules are designed for extracting features from the camera and radar; Secondly, the camera and radar features are catenated, and a deconvolution module is built for upsampling; Thirdly, the heatmap module is used to compress redundant channels. Finally, the objects in the Field of View (FoV) are predicted by location-based Non-Maximum Suppression (L-NMS). In addition, a data scrambling technique is proposed to alleviate the problem of overfitting to a single sensor by the fusion method. The existing Washington University Camera Radar (CRUW) dataset is improved and a new dataset named Camera-Radar Nanjing University of Science and Technology Version 1.0 (CRNJUST-v1.0) is collected to verify the proposed method. Experiments show that CRRFNet can detect objects by using the information of radar and camera at the same time, which is far more accurate than a single sensor method. Combined with the proposed data scrambling technology, CRRFNet shows excellent robustness that can effectively detect objects in the case of interference or single sensor failure.

A robust and real-time lane detection method in low-light scenarios to advanced driver assistance systems

Lane detection, which relies on front-view RGB cameras, is a crucial aspect of Advanced Driver Assistance Systems (ADAS), but its effectiveness is notably reduced in low-light conditions. This issue is exacerbated by the lack of specialized datasets and generalizable methods for such scenarios. To address this gap, we introduce NightLane, a comprehensive dataset tailored for low-light, multi-traffic lane detection. We adhere to stringent data annotation guidelines, ensuring reliable detection accuracy. Additionally, we propose the Fused Low-Light Enhancement Framework (FLLENet), which leverages modern detection networks and incorporates a low-light enhancement module and attention mechanisms. The enhancement module, based on zero-reference learning, improves image quality and channel richness, while the attention mechanisms effectively extract and utilize these features. Our extensive testing on NightLane and CULane datasets demonstrates superior performance in low-light lane detection, showcasing FLLENet’s robust generalizability and efficacy. Specifically, our approach achieves an F1 measure of 76.90 on CULane and 78.91 on NightLane, demonstrating its effectiveness against state-of-the-art methods. We also evaluate the real-time applicability of our framework on a low-power embedded lane detection system using NVIDIA Jetson AGX/Orin, achieving high accuracy and real-time performance. Our work offers a new approach and reference in the field of low-light lane detection, potentially aiding in the ongoing enhancement of ADAS (ADAS). Dateset are available at https://github.com/pengjingt/FLLENet.

Establishing the capacity to monitor proteins relevant to the study of drug exposure and response using liver-derived extracellular vesicles.

Drug exposure and response is determined by pharmacokinetic (PK) and pharmacodynamic (PD) profiles. Interindividual differences in abundance of drug metabolizing enzymes (DMEs) and drug target proteins underpin PK and PD variability and impact treatment efficacy and tolerability. Extracellular vesicles (EVs) carry protein cargo inherited from originating cells and may be useful for defining differences in key proteins related to hepatic drug metabolism and the treatment of metabolic-associated fatty liver disease (MAFLD). We sought to quantify these proteins in liver-derived EVs and establish the profile relative to paired tissue. EVs were recovered from human liver tissue samples (LT-EV, n = 11). Targeted liquid chromatography with tandem mass spectrometry (LC-MS/MS) assays were employed for absolute quantification of proteins in EV isolates and matched liver tissue. DMEs and MAFLD drug targets were readily detected and quantified in LT-EVs. Twelve of 15 DMEs exhibited moderate to strong correlation (Spearman ⍴ = 0.618-0.973) between tissue and EVs. Correlation in protein abundance was influenced by the extent of extra-hepatic expression of the target. This study provides evidence that key proteins related to PK and PD profiles can be measured in liver-derived EVs and abundance of liver-enriched DMEs are robustly correlated between paired tissue and EVs. The robust detection of protein markers related to drug PD profile in MAFLD opens the possibility to track within-subject changes in MAFLD and lays the foundation for future development of a liver-derived EV liquid biopsy to assess markers of drug exposure and response in vivo.

Intelligent seam tracking in foils joining based on spatial–temporal deep learning from molten pool serial images

Vision-based weld seam tracking has become one of the key technologies to realize intelligent robotic welding, and weld deviation detection is an essential step. However, accurate and robust detection of weld deviations during the microwelding of ultrathin metal foils remains a significant challenge. This challenge can be attributed to the fusion zone at the mesoscopic scale and the complex time-varying interference (pulsed arcs and reflected light from the workpiece surface). In this paper, an intelligent seam tracking approach for foils joining based on spatial–temporal deep learning from molten pool serial images is proposed. More specifically, a microscopic passive vision sensor is designed to capture molten pool and seam trajectory images under pulsed arc lights. A 3D convolutional neural network (3DCNN) and long short-term memory (LSTM)-based welding torch offset prediction network (WTOP-net) is established to implement highly accurate deviation prediction by capturing long-term dependence of spatial–temporal features. Then, expert knowledge is further incorporated into the spatio-temporal features to improve the robustness of the model. In addition, the slime mould algorithm (SMA) is used to prevent local optima and improve accuracy, efficiency of WTOP-net. The experimental results indicate that the maximum error detected by our method fluctuates within ± 0.08 mm and the average error is within ± 0.011 mm when joining two 0.12 mm thickness stainless steel diaphragms. The proposed approach provides a basis for automated robotic seam tracking and intelligent precision manufacturing of ultrathin sheets welded components in aerospace and other fields.

Robust fault detection for switched systems with unstable modes: A bumpless transfer piecewise filtering approach

AbstractThis investigation addresses the bumpless transfer fault detection (FD) problem within switched systems that possess unstable modes. A switched piecewise FD filter is developed as a residual generator by segmenting each dwell time interval. The transition between different filters precipitates pronounced, abrupt jumps in the residual signal. Consequently, a novel definition of the residual bumpless transfer performance is introduced to constrain the magnitude of residual fluctuations during switching instances. Additionally, an alternating switching strategy—characterized by slow and fast mode‐dependent average dwell time and supported by the multiple discontinuous Lyapunov function method—is devised to assure the asymptotic stability and the weighted performance of the augmented system. Concurrently, sufficient conditions for the solvability of the bumpless transfer FD problem are articulated in the form of linear matrix inequalities. Lastly, a switched buck‐boost circuit and a numerical example are presented to substantiate the merits of the proposed bumpless transfer piecewise filtering method.

Empowering the on-site detection of nucleic acids by integrating CRISPR and digital signal processing

Addressing the global disparity in cancer care necessitates the development of rapid and affordable nucleic acid (NA) testing technologies. This need is particularly critical for cervical cancer, where molecular detection of human papillomavirus (HPV) has emerged as an accurate screening method. However, implementing this transition in low- and middle-income countries has been challenging due to the high costs and centralized facilities required for current NA tests. Here, we present CreDiT (CRISPR Enhanced Digital Testing) for on-site NA detection. The CreDiT platform integrates i) a one-pot CRISPR strategy that simultaneously amplifies both target NAs and analytical signals and ii) a robust fluorescent detection based on digital communication (encoding/decoding) technology. These features enable a rapid assay (<35 minutes) in a single streamlined workflow. We demonstrate the sensitive detection of cell-derived HPV DNA targets down to single copies and accurate identification of HPV types in clinical cervical brushing specimens (n = 121).

Biofilm Production and Its Implications in Pediatrics.

Biofilms, aggregates of bacteria enclosed in a self-produced matrix, have been implicated in various pediatric respiratory infections, including acute otitis media (AOM), otitis media with effusion (OME), adenoiditis, protracted bacterial bronchitis, and pulmonary exacerbations in cystic fibrosis. These infections are prevalent in children and often associated with biofilm-producing pathogens, leading to recurrent and chronic conditions. Biofilms reduce antibiotic efficacy, contributing to treatment failure and disease persistence. This narrative review discusses biofilm production by respiratory pathogens such as Streptococcus pneumoniae, non-typeable Haemophilus influenzae, Pseudomonas aeruginosa, and Staphylococcus aureus. It examines their mechanisms of biofilm formation, antibiotic resistance, and the challenges they present in clinical treatment. Various antibiofilm strategies have shown promise in vitro and in animal studies, including the use of N-acetylcysteine, enzymes like dispersin B, and agents disrupting quorum sensing and biofilm matrix components. However, their clinical application, particularly in children, remains limited. Traditional treatments for biofilm-associated diseases have not significantly evolved, even with biofilm detection. The transition from experimental findings to clinical practice is complex and requires robust clinical trials and standardized biofilm detection protocols. Addressing biofilms in pediatric respiratory infections is crucial for improving treatment outcomes and managing recurrent and chronic diseases effectively.

Robust detection of infectious disease, autoimmunity, and cancer from the paratope networks of adaptive immune receptors.

Liquid biopsies based on peripheral blood offer a minimally invasive alternative to solid tissue biopsies for the detection of diseases, primarily cancers. However, such tests currently consider only the serum component of blood, overlooking a potentially rich source of biomarkers: adaptive immune receptors (AIRs) expressed on circulating B and T cells. Machine learning-based classifiers trained on AIRs have been reported to accurately identify not only cancers but also autoimmune and infectious diseases as well. However, when using the conventional "clonotype cluster" representation of AIRs, individuals within a disease or healthy cohort exhibit vastly different features, limiting the generalizability of these classifiers. This study aimed to address the challenge of classifying specific diseases from circulating B or T cells by developing a novel representation of AIRs based on similarity networks constructed from their antigen-binding regions (paratopes). Features based on this novel representation, paratope cluster occupancies (PCOs), significantly improved disease classification performance for infectious disease, autoimmune disease, and cancer. Under identical methodological conditions, classifiers trained on PCOs achieved a mean AUC of 0.893 when applied to new individuals, outperforming clonotype cluster-based classifiers (AUC 0.714) and the best-performing published classifier (AUC 0.777). Surprisingly, for cancer patients, we observed that "healthy-biased" AIRs were predicted to target known cancer-associated antigens at dramatically higher rates than healthy AIRs as a whole (Z scores >75), suggesting an overlooked reservoir of cancer-targeting immune cells that could be identified by PCOs.