Method For Diagnosis Research Articles

Pre-clinical study of IR808 dye for cervical cancer in vitro and in vivo imaging.

There is an urgent need for improved methods for early screening and rapid diagnosis of cervical cancer since current conventional screening methods are plagued by operator subjectivity and unnecessary biopsies. IR808 is a tumour-targeting near-infrared (NIR) fluorescent dye that permits NIR imaging without the requirement of chemical conjugation. Our study investigates an IR808-based strategy for real-time monitoring of the cervix in vivo and rapid assessment of cervical specimens in vitro. We investigated the uptake of IR808 in vitro using normal cervical epithelial cells and three cervical cancer cell lines. The biodistribution of IR808 was examined in vivo via intravenous injection into tumour-bearing mice. Additionally, in vitro tissues were stained with IR808 to simulate the identification of cervical tumors in the clinical setting. Biocompatibility of the dye in both cellular and animal models was also examined. IR808 exhibited significant tumour-to-background ratios in fluorescence molecular imaging of in vivo tumors in nude mice. The application of NIR fluorescent dye IR808 in specific imaging screening, safe and non-invasive real-time monitoring, and rapid identification of cervical tumors from tissue specimens is expected to improve current screening methods for cervical cancer.

Research on fault diagnosis for three-phase rectifier device in direct current transmission system based on continuous wavelet transform and vision transformer

Abstract As a core component of photovoltaic power generation systems, the three-phase rectifier device plays a crucial role, and its failure can potentially reduce energy conversion efficiency and output quality. Presently, the performance of fault time-domain signal diagnosis methods based on three-phase rectifier circuits is challenging to enhance. This paper proposes a novel fault detection method for three-phase rectifier devices based on Vision Transformer, referred to as CWT-ViT, to address this issue. This method transforms time-domain fault signals into images through Continuous Wavelet Transform (CWT), subsequently inputting these images into a Vision Transformer model. Relying on its powerful self-attention mechanism and fully connected layers, it realizes the extraction and learning of rectifier device image features. A Simulink simulation model of a three-phase bridge controllable rectifier circuit is established for fault injection to collect fault signals. Fault diagnosis experiments demonstrate that the proposed diagnostic method achieves a prediction accuracy of 98.6%, maintaining a relatively high precision level. In comparison to four excellent classification models currently available: AlexNet, RepVGG, ResNet, and GoogLeNet, the proposed method demonstrates superior diagnostic performance. Additionally, this paper conducts ablation experiments to meticulously analyze the impact of each module in the fault diagnosis process. This research achieves more precise and efficient fault diagnosis in photovoltaic power generation systems, thereby reducing downtime and maintenance costs for actual equipment and enhancing the stability of photovoltaic power generation systems. This research provides an innovative, intelligent solution for the intelligent operations and maintenance of photovoltaic power generation.

Fault diagnosis for multiple redundancy aileron actuator based on parallel-SDP and polar sparse representation

Abstract As a critical component of aircraft flight control systems, the aileron actuator's fault directly affects the performance of flight control performance system and the overall flight safety of aircraft. Therefore, effective fault diagnosis of the aileron actuator becomes particularly important. However, with the development of redundancy design, the structure of aileron actuators more and more complex, and the fault modes are more and more diverse, which increases the difficulty of fault diagnosis significantly. To address this challenge, this study proposes a fault diagnosis method based on Parallel-SDP and Polar Sparse Representation.
First, the current residual signals of force motors are obtained using bi-step observer. Then, the residual signals are transformed into Parallel-SDP images, where each of the four petals of Parallel-SDP image generated from the corresponding channel. The Parallel-SDP image presents global fault information and capture subtle changes of residual signals, which increases the sensitivity of fault diagnosis. Subsequently, rapid single-channel fault localization is achieved by barycenter analysis of Parallel-SDP images. Finally, based on the result of fault localization, the proposed polar sparse representation algorithm is utilized for fault diagnosis of mechanical and control faults separately. Based on the dataset obtained from physical-parameter-simulation, the proposed method was validated, and the accuracy of fault diagnosis of was 99.29%, which is better than conventional fault diagnosis, meanwhile, the computational resources consumption of the proposed method is much less than deeplearning-based method, which is suitable for embedded computing system in aircraft.

In-depth research on fault diagnosis of turbine rotor utilizing NGSABO-optimized VMD and CNN-BiLSTM

Abstract To solve the problem of difficulty in extracting and identifying fault types during turbine rotor operation, a fault diagnosis method based on improved subtraction mean optimizer (NGSABO) algorithm to optimize variational mode decomposition (VMD) and CNN-BiLSTM neural network is proposed. Firstly, three improvements are made to the subtraction average optimizer algorithm. Secondly, the optimal VMD parameter combination of NGSABO adaptive selection mode decomposition number K and penalty factor is used to decompose the rotor fault signal, and the minimum sample entropy is used as the fitness function for feature extraction. Combining convolutional neural network and bidirectional long short-term memory network to identify and classify features. Compared with other methods, this method has outstanding performance in the diagnosis of single and coupled rotor faults. The accuracy of fault diagnosis reaches 98.5714%, which has good practical application value.

A graph-based method for automatic graded diagnosis of depression using EEG signals

Depression is a common psychological disorder typically categorized into four grades according to the symptom severity. Accurately diagnosing different grades of depression is significant for taking appropriate treatment strategies to prevent the condition from worsening. Electroencephalography (EEG) has the potential to mirror the prevailing mental state of patients, providing a possible way to diagnose depression. However, it is still a challenge to extract EEG features that reflect varying degrees of depression for automatic grading diagnosis. It has been pointed out that depression involves the intensification of abnormal interactions among distinct brain regions as it advances, which suggests that brain spatial information may play a key role in tracking different grades of depression. Based on this, combined with deep learning models, this paper proposes a new graph-based method for automatic grading diagnosis of depression. A novel graph-based brain network (BN) construction method is first proposed to convert EEG into graph structure containing brain spatial information, where the individual-level (IBN) and group-level brain networks (GBN) are constructed respectively. Next, a new deep learning model P-I-GAT is built based on graph attention networks (GAT) for identifying EEG signals from depression patients with different severity. In specific, the “P” represents the prior information integration capability, synthesizing attribute information from the IBN and structural information from the GBN. The resulting synthesized brain network contains prior information from these two different scales, referred to as the prior brain network (PBN). “I” denotes the multi-rhythm interaction capability, which adaptively assigns learning weights to each rhythmic PBN to fully exploit the information embedded within the PBNs. Ultimately, the proposed method is validated on the open dataset MODMA, achieving an accuracy of 88.57% and a specificity of 91.97%.

A novel approach to aeroengine performance diagnosis based on physical model coupling data-driven using low-rank multimodal fusion method

Aeroengine health assessment plays a pivotal role in ensuring flight safety and reliability. Traditionally, this process involves diagnosing the performance of the aeroengine gas path. However, owing to the intricacies of operating conditions, non-linear performance, and the interplay of gas path performance fault characteristics, determining the aeroengine health condition directly from engine monitoring information poses a significant challenge, particularly in cases of insufficient sensor data. To address these challenges, a novel digital twin method for aeroengine performance diagnosis has been proposed. This method integrates data-driven and performance models, employing a low-rank multimodal fusion approach. By digitizing the physical system or process through mathematical models and simulation technology, this approach presents distinct advantages compared to previous methods relying solely on models or data. At the aeroengine component level, an adaptive model was implemented, and the data-driven model was constructed using flight data. Gas path fault classification employed support vector machines. The engine digital twin was established through low-order multimodal fusion. Results indicate that the proposed method attains excellent diagnostic accuracy under both steady and transient conditions. It can be harnessed to enhance engine performance monitoring and evaluation, thereby improving the reliability, availability, and efficiency of the engine.

Joint Image Processing with Learning-Driven Data Representation and Model Behavior for Non-Intrusive Anemia Diagnosis in Pediatric Patients

Anemia diagnosis is crucial for pediatric patients due to its impact on growth and development. Traditional methods, like blood tests, are effective but pose challenges, such as discomfort, infection risk, and frequent monitoring difficulties, underscoring the need for non-intrusive diagnostic methods. In light of this, this study proposes a novel method that combines image processing with learning-driven data representation and model behavior for non-intrusive anemia diagnosis in pediatric patients. The contributions of this study are threefold. First, it uses an image-processing pipeline to extract 181 features from 13 categories, with a feature-selection process identifying the most crucial data for learning. Second, a deep multilayered network based on long short-term memory (LSTM) is utilized to train a model for classifying images into anemic and non-anemic cases, where hyperparameters are optimized using Bayesian approaches. Third, the trained LSTM model is integrated as a layer into a learning model developed based on recurrent expansion rules, forming a part of a new deep network called a recurrent expansion network (RexNet). RexNet is designed to learn data representations akin to traditional deep-learning methods while also understanding the interaction between dependent and independent variables. The proposed approach is applied to three public datasets, namely conjunctival eye images, palmar images, and fingernail images of children aged up to 6 years. RexNet achieves an overall evaluation of 99.83 ± 0.02% across all classification metrics, demonstrating significant improvements in diagnostic results and generalization compared to LSTM networks and existing methods. This highlights RexNet’s potential as a promising alternative to traditional blood-based methods for non-intrusive anemia diagnosis.

Multi-label semantic segmentation of magnetic resonance images of the prostate gland

Prostate segmentation is a substantial factor in the diagnostic pathway of suspicious prostate lesions. Medical doctors are assisted by computer-aided detection and diagnosis systems systems and methods derived from artificial intelligence deep learning-based systems have to be trained on existing data. Especially freely available labeled prostate magnetic resonance imaging data is rare. With regard to this problem, we show a method to combine two existing small datasets to form a bigger one. We present a data processing pipeline consisting of a cascaded network architecture that is able to perform multi-label semantic segmentation, hence, capable of classifying each pixel in a T2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{T}_{2}$$\\end{document}-weighted image not only to one class but to a subset of the prostate zones and classes of interest. This delivers richer information such as overlapping zones that are key to medical radiological examination. Additionally, we describe how to integrate expert knowledge in our deep learning system. To increase data variety for training and evaluation we use image augmentation on our two datasets—a freely available dataset and our new open-source dataset. To combine the datasets we denoise the contourings in our dataset by using an effective yet simple algorithm based on standard computer vision methods only. The performance of the presented methodology is compared and evaluated using the dice score metric and 5-fold cross-validation on all datasets. Although we trained on tiny datasets our method achieves excellent segmentation quality and is even able to detect prostate cancer. Our method to combine the two datasets reduces segmentation errors and increases data variety. The proposed architecture significantly improves performance by including expert knowledge via feature-map concatenation. On the initiative for collaborative computer vision benchmarking dataset we achieve on average dice scores of approximately 91% for the whole prostate gland, 67% for the peripheral zone and 75% for the prostate central gland. We find that image augmentation except contrast limited adaptive histogram equalisation did not have much influence on the segmentation quality. Derived and enhanced from existing methods we present an approach that is able to deliver multi-label semantic segmentation results for prostate magnetic resonance imaging. This approach is simple and could be applied to other applications of deep learning as well. It improves the segmentation results by a large margin. Once tweaked to the data, our denoising and combination algorithm delivers robust and accurate results even on data with segmentation errors.

B-176 Rapid Diagnosis of 21-Hydroxylase Deficiency Using LC-MS/MS for Urinary Unconjugated Steroid Analysis

Abstract Background Urinary steroid profiling through gas chromatography-mass spectrometry (GC-MS) serves as a potent diagnostic tool for detecting abnormal steroid production linked to congenital enzyme deficiencies and steroid-related diseases. This technique involves deconjugating and extracting both conjugated and unconjugated steroids, followed by derivatization and analysis via GC-MS. It provides comprehensive insights into steroid metabolism, aiding in the identification of genetic disorders and conditions with atypical steroid levels. However, the procedure is intricate and time-consuming, particularly the deconjugation of steroids for analysis. The present study aimed to assess the usability of LC-MS/MS assays measuring unconjugated Δ4- and Δ5-steroids in urine for diagnosing steroid abnormalities. Methods The Biotage ISOLUTE SLE+ (Biotage, Sweden) was used for sample preparation, with dichloromethane for elution. LC-MS/MS analysis was performed on an LCMS8060NX (Shimadzu, Kyoto, Japan), using a Shim-Pack Velox Biphenyl column 2.1mm*150mm* 1.8μm (Shimadzu GLC, Tokyo, Japan). The mobile phase consisted of a 0.2mmol/L ammonium fluoride aqueous solution and a 0.2mmol/L ammonium fluoride methanol solution. We targeted 38 steroids, including four steroid medications, and used 19 stable isotope-labeled steroids for quantification. For the measurements, 30 neonatal urine samples were used (IRB Approval Number 20221210), which were suspected of 21-hydroxylase deficiency (21OHD) based on clinical symptoms or screening for 17α-hydroxyprogesterone (17OHP) using Dried Blood Spot. Of these, 18 had been confirmed as 21OHD cases by exceeding the GC-MS diagnostic criterion for Pregnanetriolone (>0.06ng/g Creatinine). Results Blood 21-deoxycortisol (21DOF) is a reliable marker for diagnosing 21OHD, which is generated from 17OHP through an alternative biochemical route. In consideration of that, we measured the urinary concentration of unconjugated 21-deoxycortisone (21DOE, precurcer of Pregnanetriolone), into which 21DOF is putatively converted in the kidney. In cases where 21OHD was excluded by GC-MS diagnosis, 21DOE was undetectable, falling below the sensitivity levels. On the other hand, 21DOE was detected in all samples confirmed 21OHD cases, consistent with the conversion of 21DOF to 21DOE in the kidney. Conclusions The present study suggested the usability of LC-MS/MS assays measuring urinary unconjugated 21DOE for diagnosing 21OHD. This approach provides a faster, less complex method for diagnosis, eliminating the need for the deconjugation process. To establish the value of urinary unconjugated steroids as diagnostic markers for steroid abnormalities, efforts to accumulate further findings are underway using clinical samples.

Automated early ovarian cancer detection system based on bioinformatics

Ovarian cancer is a common gynecological tumor, with a high mortality rate and difficult clinical treatment. Early detection of ovarian cancer has significant diagnostic value. In response to the problem of poor diagnostic performance of traditional early diagnosis methods, this article designed an automated early ovarian cancer detection system to improve the detection of early ovarian cancer. The conventional early diagnosis methods include serum CA125 (carbohydrate antigen 125) detection and positron emission tomography/computed tomography (PET/CT) imaging. This article combined serum CA125 detection and PET/CT imaging to detect the CA125 level and maximum standardized uptake value (SUV) in patient’s serum. When the CA125 level exceeded 35U/ml and the maximum SUV value exceeded 2.5, the test was considered positive. This article selected 200 patients from Jingzhou Hospital for the experiment and compared the three detection methods. The average specificity of single serum CA125 detection, single PET/CT imaging, and automated detection in patients under 50 were 61.24%, 79.57%, and 97.79%, respectively. The automated early ovarian cancer detection system designed in this article can significantly improve the specificity of early ovarian cancer detection and has excellent application value for early ovarian cancer detection.

Fault Diagnosis of Maritime Equipment Using an Intelligent Fuzzy Framework

The task of automatically and intelligently diagnosing faults in marine equipment is of great significance due to the numerous duties that shipboard professionals must handle. Incorporating automated and intelligent systems on ships allows for more efficient equipment monitoring and better decision-making. This approach has attracted considerable interest in both academia and industry because of its potential for economic savings and improved safety. Several fault diagnosis methods are documented in the literature, often involving mathematical and control theory models. However, due to the inherent complexity of some processes, not all characteristics are precisely known, making mathematical modeling highly challenging. As a result, fault diagnosis often depends on data or heuristic information. Fuzzy logic theory is particularly well suited for processing this type of information. Therefore, this paper employs fuzzy models to diagnose faults in a marine pneumatic servo-actuated valve. The fuzzy models used in fault diagnosis are obtained from the data. These fuzzy models are identified for the normal operation of the marine pneumatic servo-actuated valve, and for each fault, predicting the system’s outputs from the inputs and outputs of the process. The proposed fault diagnosis framework analyzes the discrepancy signals between the outputs of the fuzzy models and the actual process outputs. These discrepancies, known as residuals, help in detecting and isolating equipment faults. The fault isolation process uses an intelligent decision-making approach to determine the specific fault in the system. This method is applied to diagnose abrupt faults in a marine pneumatic servo-actuated valve. The approach presented was used to detect and diagnose three very important faults in the operation of a marine pneumatic servo-actuated valve. The three faults were correctly detected and isolated, and no errors were detected in this detection and isolation process.

Peracute Enterotoxemia in Saanen and Alpine Goat Herd

Background: Enterotoxemia" or "overeating disease" is considered a common and often fatal disease affecting the economy of small ruminant breeding systems. This study presents findings on the occurrence of a peracute form of enterotoxemia in a herd of Saanen and Alpine, including an examination of the clinical signs, post-mortem findings, and methods for diagnosis. examination of the clinical signs, post-mortem findings, and methods for diagnosis. Methods: In a herd of goats a distressing situation occurred where the goats displayed signs (Sudden death and high fever) of peracute enterotoxemia (125 kids). It is noteworthy that these goats had previously been vaccinated against enterotoxemia. The onset of the condition seemed to be linked to three instances of interruption and reconnection of concentrate feed. To obtain a definitive diagnosis, the findings from postmortem examinations and ELISA were utilized. Results: In total, 60 Alpine and 65 Saanen succumbed to this peracute form. These losses occurred over three days but were successfully stopped by re-vaccination after two days. Clinical signs, postmortem observations, bacterial analysis, and ELISA results all provided confirmation of enterotoxemia. Notable findings included high fever (90%), duodenum hyperemia (89%), pulmonary edema (82%), convulsions (43%), and hemorrhage in the pericardium and endocardium (58%). Conclusion: Frequent and consecutive changes in goats' diet or discontinuation of concentrate supply by breeders can disrupt the vaccine-induced immune barrier, increasing the likelihood of enterotoxemia, and leading to casualties and economic losses. Consistent and stable nutrition practices are essential for maintaining vaccination efficacy and preventing enterotoxemia in goats, particularly kids.

A Novel Fault Feature Selection and Diagnosis Method for Rotating Machinery with SI-IR2CMSE and SSGMM-SR

Abstract In the field of fault diagnosis, machine learning is highly valued for its broad applicability and efficiency. Feature extraction and feature selection are key steps in the application of machine learning, and the performance of fault diagnosis methods relies heavily on the effective execution of these two steps. For this reason, this paper aims to enhance the performance of fault diagnosis methods by improving these two aspects. Firstly, to address the non-linearity and non-stationarity of rotating machinery vibration signals under variable operation conditions, this paper proposes an improved rapid refined composite multiscale sample entropy (IR2CMSE) feature extraction method. In addition, this paper decomposes the vibration signals with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and extracts the sensitive intrinsic modal functions’ (IMFs') IR2CMSE values (SI-IR2CMSE) as the initial feature vector, which more accurately reveals the intrinsic time-scale characteristics of the vibration signals. Secondly, to address the problem of over-reliance on sample labels in most feature selection methods, this paper proposes a semi-supervised Gaussian mixing model with sparse regularization (SSGMM-SR) feature selection model. The model does not require complete fault labels and can automatically identify important features. Finally, validation with two rotating machinery fault datasets shows that the method proposed in this study exhibits high diagnostic accuracy and stability across multiple classifiers.

A Semantic Alignment Guided Transfer-Learning Method for Electro-Mechanical Actuator Fault Diagnosis Under Variable Working Conditions

A Semantic Alignment Guided Transfer-Learning Method for Electro-Mechanical Actuator Fault Diagnosis Under Variable Working Conditions

The relationship between static and dynamic postural deformities with pain and quality of life in non-athletic women

BackgroundThe assessment of the postural condition with functional tests are used with the least facilities in the shortest time, for a wide the range of movements for different parts of the body. Both static and dynamic posture measurements are predictive of injury. These two assessments provide different information regarding posture control. Also, with the advancement of this technology, the speed of posture assessment and deformity diagnosis can be increased and done with the minimum facilities. This can signal a new method for the quick diagnosis of abnormalities and ultimately prevent or correct psychological effects and musculoskeletal pain in the future. Because as seen according to the citations, abnormalities cause musculoskeletal pains, movement restrictions and ultimately affect the quality of life.MethodsThe current research is of the applied and semi-experimental type, and in terms of the results it is of the relational and correlational type. In this research, 148 non-Athletic women from Fardis City participated, in which the results obtained from the static evaluation was analyzed by the Posture Screen application after taking photos from four directions using a smartphone, and also the dynamic evaluation was identified and analyzed by the researcher using the overhead squat test of compensatory movements, with the data that from Cornell pain and quality of life SF-36 questionnaires was. Data description and correlation between variables were done with the η coefficient method.ResultsAccording to the findings there is a positive and significant correlation between the prevalence of uneven pelvic deformity and the amount of pain in non-athletic women (P = 0.036, η (148) = 0.17). In other words, pain increased significantly when the pelvis was changed from a normal position to a lateral deviation position. Also, there is a negative and significant relationship between the prevalence of deformity of knee movement, back arch, straight back, heel lift and the quality of life in non-athletic women (P = 0.020, η (148) = 0.19).ConclusionsAccording to the results, deformities have an effect on pain and the frequency of pain, on the other hand, in the present study, dynamic evaluations showed deformities more accurately than static evaluations.

The effectiveness of various approaches in the treatment of peripheral neuropathies in people with type 2 diabetes mellitus

Introduction. Optimal therapeutic tactics for diabetic peripheral neuropathy (DPN) can reduce the risk of complications and improve the quality of life of patients with diabetes mellitus (DM).Aim: To evaluate the effectiveness of various approaches to the treatment of DPN.Materials and Methods. 67 patients were examined (36 men and 31 women, mean age 59.4 ± 9.7 years), duration of diabetes was at least 7 years. Patients underwent general clinical examinations, neurological examination and diagnosis of DPN with assessment of pain, tactile and vibration sensitivity. All patients underwent ultrasound of the peroneal nerve (PN): the structure and cross-sectional area (CSA) were assessed (≤ 11 mm2 was taken as the norm). Patients with symptoms of PN compression received mini-invasive treatment by perineural administration of 20 mg methylprednisolone under ultrasound control.Results. Clinical manifestations of DPN were identified in 33 (49.3%) cases. Changes in ultrasound PN occurred in 62 (92.5%) patients. 29 patients with echographic changes in PN and asymptomatic DPN received α-lipolic acid and benfotiamine: the CSA of the PN before treatment was 13,2 ± 2,4 mm2, after 6 months –10,4 ± 1,6 mm2; the proportion of people with CSA PN ≥ 12 mm2 before treatment was 82,7%, after 6 months –27,6% (all p < 0.05). 19 patients with symptoms of DPN, but without signs of compression of the MBN, received additional drugs and techniques. The average pain intensity before treatment was 4,93 ± 1,07, after 6 months –2,47 ± 0,61; CSA PN before treatment –17,3 ± 3,8 mm2, after 6 months –13,2 ± 2,2 (all р < 0,017). 14 patients with PN compression underwent mini-invasive treatment under ultrasound control. In the first 24–48 hours after manipulation, in all cases there was a moderate increase in local manifestations of compression. Then the pain intensity decreased (5.74 ± 1.19 points – before manipulation, 3.18 ± 0.97 – after 6 months, р < 0,0125), CSA decreased (22.4 ± 4.3 mm2 – to 15.3 ± 3.6 mm2 – after 6 months, р < 0,0125) and echographic characteristics improved.Conclusions. Ultrasound of the nerves can be a valuable method for the early diagnosis of DPN and a tool for choosing treatment tactics. The use of pathogenetic pharmacotherapy alone or in combination with other drugs was associated with satisfactory tolerability, favorable clinical and ultrasound dynamics. The use of mini-invasive treatment with perineural administration of drugs for compartment syndrome was characterized by a positive effect on compression symptoms and ultrasound characteristics of the nerve.

Neural architecture search for multi-sensor information fusion-based intelligent fault diagnosis

The multi-sensor information fusion-based intelligent fault diagnosis (MIF-IFD) method using deep learning aims to provide more accurate and reliable ways of identifying equipment health status than single-sensor methods. However, designing feature extraction modules in deep networks and determining information fusion execution layers still requires expertise and extensive experimentation, imposing high development costs. This limitation impedes the development and application of MIF-IFD. This paper proposes an architecture to mitigate the development challenges of MIF-IFD. Firstly, the basic module of the network consists of searchable feature extraction cells and a mask self-attention mechanism to achieve the extraction and fusion of multi-sensor information. Secondly, the optimal feature extraction cells and fusion starting layers are searched by constructing a continuous search space to compose the optimal fusion diagnostic structure, respectively. Finally, validation and analysis are conducted using two experimental datasets. The results demonstrate that the proposed method not only ensures diagnostic accuracy but also significantly improves development efficiency.

Rapid 3D imaging at cellular resolution for digital cytopathology with a multi-camera array scanner (MCAS)

Optical microscopy has long been the standard method for diagnosis in cytopathology. Whole slide scanners can image and digitize large sample areas automatically, but are slow, expensive and therefore not widely available. Clinical diagnosis of cytology specimens is especially challenging since these samples are both spread over large areas and thick, which requires 3D capture. Here, we introduce a new parallelized microscope for scanning thick specimens across extremely wide fields-of-view (54 × 72 mm2) at 1.2 and 0.6 μm resolutions, accompanied by machine learning software to rapidly assess these 16 gigapixel scans. This Multi-Camera Array Scanner (MCAS) comprises 48 micro-cameras closely arranged to simultaneously image different areas. By capturing 624 megapixels per snapshot, the MCAS is significantly faster than most conventional whole-slide scanners. We used this system to digitize entire cytology samples (scanning three entire slides in 3D in just several minutes) and demonstrate two machine learning techniques to assist pathologists: first, an adenocarcinoma detection model in lung specimens (0.73 recall); second, a slide-level classification model of lung smears (0.969 AUC).

WCNN-RSN: a novel fault diagnosis method for rolling bearing using multimodal feature fusion

Abstract Fault diagnosis of rolling bearings is significant for the safe operation of engineering equipment. Many intelligent diagnostic methods have been successfully developed. However, it is often susceptible to noisy environments. Therefore, the paper proposes a rolling bearing fault diagnosis method based on multimodal information fusion in time and time–frequency domains by combining an improved 1D-convolutional neural network (CNN) with ResNet50 wavelet improved CNN-ResNet (WCNN-RSN). The algorithm employs the Multi-Head Attention (MHA) mechanism to complementarily fuse fault features in different scales, achieving fault diagnosis by fully extracting fault features. The experimental results show that the diagnostic effect of WCNN-RSN is better than that of the comparison methods under noise interference, which proves that the proposed method possesses good anti-noise and generalization ability.

Research on Typical Fault Diagnosis of Gear based on GHM Multiwavelet Transform and MCKD Algorithm

Background: Gear is the key part of the transmission part of mechanical equipment, which has a high failure rate under complex working conditions or long-term operation, directly affecting the reliability of mechanical equipment. To realize online monitoring of gears and predict gear faults, whether the diagnosis of typical gear faults is accurate and timely is a key link, so it is necessary to study the diagnosis of typical gear faults. Objective: This paper aims to propose a method that can effectively diagnose typical faults of gears and is easy to program, which is beneficial to realize online monitoring of rotating machinery equipment faults. Method: A typical gear fault diagnosis method based on GHM multiwavelet transform and maximum correlation kurtosis deconvolution algorithm (MCKD) is proposed in this paper. The measured vibration signal is decomposed into components with multiple scale spaces and frequency bands through the GHM multiwavelet transform. Then, the MCKD algorithm is run to suppress the noise of GHM multiwavelet transform coefficients, and the periodic components containing fault information are retained and reconstructed. The typical faults such as gear pitting and broken teeth are tested. Results: GHM multiwavelet transform combined with MCKD algorithm can accurately locate the frequency band containing fault information from the vibration signal with multiple modulations, double sideband, and multi-frequency interference and effectively extract the fault frequency and its frequency multiplication. The root means a square error of the extracted fault frequency is 0.08. This method has a good noise suppression effect and high accuracy in extracting fault frequency. Conclusion: The method proposed in this paper is helpful in realizing automatic programming of gear fault diagnosis and is of great significance in realizing real-time monitoring and online diagnosis of rotating machinery equipment faults. More related patents will appear in the future.