Residual Network Model Research Articles

Integration of dosimetric parameters, clinical factors, and radiomics to predict symptomatic radiation pneumonitis in lung cancer patients undergoing combined immunotherapy and radiotherapy

PurposeThis study aimed to combine clinical/dosimetric factors and handcrafted/deep learning radiomic features to establish a predictive model for symptomatic (grade ≥ 2) radiation pneumonitis (RP) in lung cancer patients who received immunotherapy followed by radiotherapy. Materials and MethodsThis study retrospectively collected data of 73 lung cancer patients with prior receipt of ICIs who underwent thoracic radiotherapy (TRT). Of these 73 patients, 41 (56.2 %) developed symptomatic grade ≥ 2 RP. RP was defined per multidisciplinary clinician consensus using CTCAE v5.0. Regions of interest (ROIs) (from radiotherapy planning CT images) utilized herein were gross tumor volume (GTV), planning tumor volume (PTV), and PTV-GTV. Clinical/dosimetric (mean lung dose and V5-V30) parameters were collected, and 107 handcrafted radiomic (HCR) features were extracted from each ROI. Deep learning-based radiomic (DLR) features were also extracted based on pre-trained 3D residual network models. HCR models, Fusion HCR model, Fusion HCR + ResNet models, and Fusion HCR + ResNet + Clinical models were built and compared using the receiver operating characteristic (ROC) curve with measurement of the area under the curve (AUC). Five-fold cross-validation was performed to avoid model overfitting. ResultsHCR models across various ROIs and the Fusion HCR model showed good predictive ability with AUCs from 0.740 to 0.808 and 0.740–0.802 in the training and testing cohorts, respectively. The addition of DLR features improved the effectiveness of HCR models (AUCs from 0.826 to 0.898 and 0.821–0.898 in both respective cohorts). The best performing prediction model (HCR + ResNet + Clinical) combined HCR & DLR features with 7 clinical/dosimetric characteristics and achieved an average AUC of 0.936 and 0.946 in both respective cohorts. ConclusionsIn patients undergoing combined immunotherapy/RT for lung cancer, integrating clinical/dosimetric factors and handcrafted/deep learning radiomic features can offer a high predictive capacity for RP, and merits further prospective validation.

EXTRACTION OF PAINT LOSS IN ANCIENT MURALS BASED ON 3D RESIDUAL NEURAL NETWORK

Abstract. The ancient murals of Qutan Temple in Qinghai Province have a very serious loss of paint. Moreover, the main components of the base color paint layer in the paint loss area and the white patterns in the murals are both calcified, which are similar in color and spectral features. Thus, it is difficult to distinguish them by only using spectral features. A method of paint loss area extraction based on 3D residual network with multi-scale feature fusion is proposed. Firstly, the hyperspectral images with paint loss regions were collected by hyperspectral images. They are pre-processed to establish the training data set. Secondly, 3D residual network models are constructed using 3×3×3, 3×3×5 and 5×5×3 convolution kernels to realize the extraction and fusion of spatial and spectral features at different scales of hyperspectral images. The produced mural hyperspectral dataset is used for network training to obtain the prediction model. Finally, the hyperspectral images are input into the trained model to achieve the extraction of paint loss. After comparing different methods, the experimental result shows that the proposed method can improve the extraction accuracy of mural paint loss and serve as a reference for other deteriorations extraction.

A new domain adaption residual separable convolutional neural network model for cross-domain remaining useful life prediction

In order to realize the remaining useful life (RUL) prediction of mechanical equipment under different operating conditions, a domain adaption residual separable convolutional neural network (DRSCN) model is proposed in this paper. In the DRSCN model, instead of the traditional convolutional layer, a residual separable convolutional module is developed to improve the feature extraction ability of the model. Moreover, a multi-kernel maximum mean discrepancy metric function and an adversarial learning mechanism are embedded in the DRSCN model to enhance its ability to resist domain shifts, thus improving the cross-domain RUL prediction accuracy of the model. The effectiveness of the DRSCN model is verified on an aircraft engine dataset. The experimental results show that the proposed model can realize high-accuracy RUL prediction.

Which cortical regions affect the prediction of cerebrospinal fluid amyloid beta from PET images by novel residual neural network (ArcheD)

AbstractBackgroundAmyloid‐β (Aβ) aggregation, as a biological hallmark of Alzheimer’s disease (AD), is a key component of biological classification of AD in the AT(N) framework. This research aimed to develop a new deep learning model for predicting Aβ cerebrospinal fluid (CSF) measures from amyloid PET scans and explore which cortical regions are most important contributors in the model’s prediction.MethodWe developed a Residual Network model (ArcheD) to predict Aβ CSF from amyloid PET images, and trained it on 1,870 PET scans from the Alzheimer’s Disease Neuroimaging Initiative. We registered PET scans to MNI152 template and used the Neuromorphometrics atlas to derive cortical gray matter (GM) regions. We extracted brain regions’ contributions to model decision‐making by guided backpropagation, and visualized these contributions as relevance heatmaps. We used bootstrapping, Welch’s t‐test and FDR correction in testing significance of brain regions’ relevance to predictions in the whole cohort, and separately in clinical diagnostic classes of AD, mild cognitive impairment (MCI), and cognitively normal (CN) cases.ResultArcheD showed high accuracy in predicting Aβ CSF (r = 0.81; p<0.00001). According to the relevance analysis for all samples (n = 1,390) temporal (mean 0.106; 95%CI [0.105, 0.108]) and parietal (0.105; 95%CI [0.104, 0.107]) lobes were the most important GM regions for the model decision‐making. Occipital (0.098; 95%CI [0.098, 0.100]) and frontal lobes (0.091; 95%CI [0.089, 0.92]) showed noticeably fewer relevance values. Based on between‐classes comparison, these regions contribute significantly more to CSF prediction in AD and MCI individuals compared to CN (p<0.05). Analysis of 49 smaller regions showed an almost 7‐fold difference between the most and least contributing regions.ConclusionWe developed a deep residual neural network model that predicted Aβ CSF from amyloid PET scans with high accuracy, and found that temporal and parietal lobes have the highest influence on Aβ CSF predictions. In the next step, we will validate the model in independent data and aim to develop the model further for clinical use.

Which cortical regions affect the prediction of cerebrospinal fluid amyloid beta from PET images by novel residual neural network (ArcheD)

AbstractBackgroundAmyloid‐ß (Aß) aggregation, as a biological hallmark of Alzheimer’s disease (AD), is a key component of biological classification of AD in the AT(N) framework. This research aimed to develop a new deep learning model for predicting Aß cerebrospinal fluid (CSF) measures from amyloid PET scans and explore which cortical regions are most important contributors in the model’s prediction.MethodWe developed a Residual Network model (ArcheD) to predict Aß CSF from amyloid PET images, and trained it on 1,870 PET scans from the Alzheimer’s Disease Neuroimaging Initiative. We registered PET scans to MNI152 template and used the Neuromorphometrics atlas to derive cortical gray matter (GM) regions. We extracted brain regions’ contributions to model decision‐making by guided backpropagation, and visualized these contributions as relevance heatmaps. We used bootstrapping, Welch’s t‐test and FDR correction in testing significance of brain regions’ relevance to predictions in the whole cohort, and separately in clinical diagnostic classes of AD, mild cognitive impairment (MCI), and cognitively normal (CN) cases.ResultArcheD showed high accuracy in predicting Aß CSF (r = 0.81; p<0.00001). According to the relevance analysis for all samples (n = 1,390) temporal (mean 0.106; 95%CI [0.105, 0.108]) and parietal (0.105; 95%CI [0.104, 0.107]) lobes were the most important GM regions for the model decision‐making. Occipital (0.098; 95%CI [0.098, 0.100]) and frontal lobes (0.091; 95%CI [0.089, 0.92]) showed noticeably fewer relevance values. Based on between‐classes comparison, these regions contribute significantly more to CSF prediction in AD and MCI individuals compared to CN (p<0.05). Analysis of 49 smaller regions showed an almost 7‐fold difference between the most and least contributing regions.ConclusionWe developed a deep residual neural network model that predicted Aß CSF from amyloid PET scans with high accuracy, and found that temporal and parietal lobes have the highest influence on Aß CSF predictions. In the next step, we will validate the model in independent data and aim to develop the model further for clinical use.

Alzheimer’s Disease Dementia Classification Through Residual Network and QEEG Image representations

AbstractBackgroundOur everyday actions and decisions involve a complex coordination of various cognitive functions. Severe deterioration of such functions, commonly referred to as dementia, adversely affects quality of our lives. However, through early screening of the disease at its pre‐clinical stage and appropriate treatment, they can be reverted. Current diagnostic criteria for dementia utilize questionnaire‐based cognitive function assessments, such as the mini‐mental state examination. However, it is statistically less robust, where further tests such as positron emission tomography are required for accurate diagnosis. This is laborious, expensive and expose patients to harmful radiation. Therefore, we propose a quantitative electroencephalography (QEEG) based approach that distinguishes Alzheimer’s disease dementia (ADD) from a non‐ADD group that include mild cognitive impairment and subjective cognitive decline data.Method19 channel EEG data employed in the present study were clinically acquired from Chung‐Ang university hospital, in eyes‐closed resting state. Artefacts were eliminated through independent component analysis and bad epoch rejection. Through spectral analysis, the powers of a frequency spectrum (1‐45Hz) were computed with 0.25Hz resolution. Henceforth, the Z‐score of each value were calculated through iMediSync’s age‐ and sex‐differentiated normative database and were mapped into a rectangular arrangement in accordance with channel locations on the scalp. The rearranged Z‐score matrices were visualized, clearly exhibiting both spectral and spatial information. Gamma spectrum (30‐45Hz) was excluded due to its vulnerability to contaminations induced by external noises and muscle movements. The final dataset (N = 732; 137 ADD, 595 non‐ADD) was established, where the 75% of non‐ADD were first excluded as test data due to data imbalance. The remaining data were split into 2 to 8 ratio for testing (N = 503; 27 ADD; 476 non‐ADD) and training (N = 229; 110 ADD; 119 non‐ADD).ResultThe final 18‐layer Residual network model showed test accuracy at 88.5% with ADD sensitivity at 88.9% and specificity at 88.4%. Explainable artificial intelligence algorithm was utilized for the inference and verification of classification criteria.ConclusionThe outstanding classification results of the established model upholds QEEG utility in the distinguishment of dementia from its pre‐clinical stages. Continuous refinement will bolster its potential in the diagnosis several other neurological diseases.

Real-time assessment of surface cracks in concrete structures using integrated deep neural networks with autonomous unmanned aerial vehicle

Ensuring the structural integrity of civil infrastructures is critical, given the potential hazards presented by cracks. Traditional manual inspections, though common, often face challenges related to accuracy, accessibility, safety, and cost-effectiveness. To address these issues, this study presents a new approach that integrates unmanned aerial vehicles (UAVs) with advanced computer vision techniques. A key feature of our approach is a system where a self-operating UAV is paired with a carefully crafted deep-learning design. This design takes advantage of both the Fast Region-based Convolutional Neural Network (FRCNN) and Residual Network (ResNet) models, allowing for real-time and accurate crack detection from ongoing video feeds. For uninterrupted real-time processing, our UAV is equipped with a data transmission module, sending live video to a computational platform enhanced with our advanced crack-spotting tool. After thorough training using a diverse dataset of 1000 images, our FRCNN-ResNet model was compared to other top models, achieving a precision rate of 93.3% and a quick 59.7ms inference time. Overall, this study offers a notable improvement in how we monitor civil structures, focusing on better safety and cost savings.

Optimal deep transfer learning driven computer‐aided breast cancer classification using ultrasound images

AbstractBreast cancer (BC) is regarded as the second leading type of cancer among women globally. Ultrasound images are typically used for the identification and classification of abnormalities that exist in the breast. To enhance diagnosis performance, the computer assisted diagnosis (CAD) model finds it effective for identifying and classifying BC. Generally, the CAD technique contains distinct procedures like feature extraction, preprocessing, segmentation, and classification. The recent developments of deep learning (DL) algorithms in the form of CAD system helps to minimize the cost and enhance the ability of radiologists to interpret medical images. Therefore, this study develops an optimal deep transfer learning driven computer aided BC classification (ODTLD‐CABCC) technique on ultrasound images. The presented ODTLD‐CABCC algorithm undergoes pre‐processing in two levels such as median filtering based noise removal and graph cut segmentation. Furthermore, the residual network (ResNet101) model can be used as a feature extractor. Finally, the sailfish optimizer (SFO) with a labelled weighted extreme learning machine (LWELM) algorithm is used for the classification process. The SFO technique is employed to choose optimal parameters involved in the LWELM algorithm. A comprehensive set of simulations are conducted on the benchmark data and the experimental outcomes are examined under numerous aspects. The comparative examination represents the supremacy of the ODTLD‐CABCC technique over the other approaches.

A fine-tuning deep residual convolutional neural network for emotion recognition based on frequency-channel matrices representation of one-dimensional electroencephalography

Emotion recognition (ER) plays a crucial role in enabling machines to perceive human emotional and psychological states, thus enhancing human-machine interaction. Recently, there has been a growing interest in ER based on electroencephalogram (EEG) signals. However, due to the noisy, nonlinear, and nonstationary properties of electroencephalography signals, developing an automatic and high-accuracy ER system is still a challenging task. In this study, a pretrained deep residual convolutional neural network model, including 17 convolutional layers and one fully connected layer with transfer learning technique in combination frequency-channel matrices (FCM) of two-dimensional data based on Welch power spectral density estimate from the one-dimensional EEG data has been proposed for improving the ER by automatically learning the underlying intrinsic features of multi-channel EEG data. The experiment result shows a mean accuracy of 93.61 ± 0.84%, a mean precision of 94.70 ± 0.60%, a mean sensitivity of 95.13 ± 1.02%, a mean specificity of 91.04 ± 1.02%, and a mean F1-score of 94.91 ± 0.68%, respectively using 5-fold cross-validation on the DEAP dataset. Meanwhile, to better explore and understand how the proposed model works, we noted that the ranking of clustering effect of FCM for the same category by employing the t-distributed stochastic neighbor embedding strategy is: softmax layer activation is the best, the middle convolutional layer activation is the second, and the early max pooling layer activation is the worst. These findings confirm the promising potential of combining deep learning approaches with transfer learning techniques and FCM for effective ER tasks.

CWGAN-GP with residual network model for lithium-ion battery thermal image data expansion with quantitative metrics

Lithium batteries find extensive applications in energy storage. Temperature is a crucial indicator for assessing the state of lithium-ion batteries, and numerous experiments require thermal images of lithium-ion batteries for research purposes. However, acquiring thermal imaging samples of lithium-ion battery faults is challenging due to factors such as high experimental costs and associated risks. To address this, our study proposes the utilization of a Conditional Wasserstein Generative Adversarial Network with Gradient Penalty and Residual Network (CWGAN-GP with Residual Network) to augment the dataset of thermal images depicting lithium-ion battery faults. We employ various evaluation metrics to quantitatively analyze and compare the generated thermal images of lithium-ion batteries. Subsequently, the expanded dataset, comprising four types of thermal images depicting lithium-ion battery faults, is input into a Mask Region-based Convolutional Neural Network for training. The results demonstrate that the proposed model surpasses both traditional Generative Adversarial Network and Wasserstein Generative Adversarial Network in terms of the quality of generated thermal images of lithium-ion batteries. Moreover, the augmentation of the dataset leads to an improvement in the fault diagnosis accuracy of the Mask Region-based Convolutional Neural Network.

Fault diagnosis for spent fuel shearing machines based on Bayesian optimization and CBAM-ResNet

Spent fuel shearing machines in nuclear power plants are important equipment for the head end of spent fuel reprocessing in power reactors. Condition monitoring and fault diagnosis play important roles in ensuring the safe operation of spent fuel shearing machines, avoiding serious accidents, and reducing their maintenance time and cost. Existing research on fault diagnosis of spent fuel shearing machines has some shortcomings: (a) the current research on fault diagnosis of shearing machines is small and diagnostic accuracy is not high. The research methodology of shearing machines needs to be updated; (b) the high difficulty in obtaining fault data and the often limited and highly informative fault data for shearing machines lead to low diagnostic performance. To solve these problems, this study constructs a residual network (ResNet) model based on Bayesian optimization (BO) and convolutional block attention module (CBAM). First, dual-channel difference method is introduced into the preprocessing of noise signals, and two data enhancements were applied to the Mel spectrograms used as inputs to the model. Second, the attention mechanism CBAM is introduced to improve the ResNet to enhance the deep feature extraction ability of the network, and the BO algorithm is used to train the hyperparameters, such as the optimizer, and retrain the network model after obtaining the optimal hyperparameters. Finally, the feasibility and effectiveness of the proposed model are verified through experiments on the noise signals of spent fuel shearing machines. The experimental results show that the diagnostic accuracy of the constructed model is 93.67%, which is a significant improvement over the other methods.

Data fusion of FT-NIR and ATR-FTIR spectra for accurate authentication of geographical indications for Gastrodia elata Blume

Gastrodia elata Blume (G. elata Bl.), with its excellent nutritional and medicinal value from Zhaotong, has been protected by geographical indication (GI). Accurate certification of its origin is a prerequisite to safeguard consumer interests and maintain the market. Four different regions and three varieties of G. elata Bl. from Zhaotong were used in this study (n = 262). Tri-step infrared spectroscopy was used for ATR-FTIR spectral analysis to filter out fingerprint regions for data fusion with FT-NIR spectra, after which conventional discriminant models (PLS-DA and GS-SVM) were built. The second derivative (SD), multiple scattering correction (MSC), and Savitzky-Golay (SG) preprocessing were also performed on the spectra, and it was found that the preprocessing improved the performance of the PLS-DA model. The optimal model results in GS-SVM, based on mid-level data fusion of principal components (PCs) and latent variables (LVs), with sensitivity, specificity, accuracy, and Matthews correlation coefficient (MCC) of 1 for the test set. Furthermore, the residual convolutional neural network (ResNet) models were built, based on FT-NIR full spectra, band 3600−2700 cm−1 (MFA) and band 1750−500 cm−1 (MFB). Their accuracy in both train and test sets exceeds 97%, and the loss function curve is close to 0, which indicates that these three bands can be used as a fingerprint area to verify the GI of Zhaotong G. elata Bl. This study provides a fast, non-invasive method for the authentication of food or medicinal plant GI.

Eye Disease Diagnosis and Classification using Deep Convolution Neural Network

Human eye plays a vital role in everyone’s life. If retinal diseases occur it could cause complete or partial vision loss. Objective: To overcome that situation, the fundus images can be utilized by the ophthalmologists to automatically diagnose the retinal diseases. At the same time, the development of latest Artificial Intelligence (AI) techniques, especially Deep Learning (DL) models finds useful for object detection in several application areas, including medical imaging. Methods: In this view, this paper presents an automated DL based multi-retinal disease diagnosis and classification model. The presented technique comprises three processes, such as pre-processing, feature extraction, and classification. For feature extraction purposes, AlexNet and Residual Network (ResNet) models are employed. Besides, Convolutional Neural Network (CNN) and Deep Neural Network (DNN) models are applied to classify the retinal fundus images into different retinal diseases. The incorporation of DL models for feature extraction and classification resulted to enhanced diagnostic performance. Findings: A series of experiments were conducted on benchmark dataset and the experimental results are examined under different aspects. The experimental values exhibited that the ResNet-CNN model has achieved better performance with the accuracy of 98.84%, precision of 98.84%, recall of 98.17%, and F1-score of 98.48%. Novelty: With the help of such methods and techniques those latest findings indicate that some human eye diseases which can be alleviated by pharmacological interventions in an easy manner.

Low-dose CT image quality evaluation method based on radiomics and deep residual network with attention mechanism

Low-dose computed tomography (CT) produces less radiation but may degrade image quality. Research on automatic evaluation and classification of low-dose CT image quality is necessary, which is helpful to clinicians. A low-dose CT image quality evaluation method is proposed based on radiomics and deep learning. After pre-training on the ImageNet dataset, the trained deep learning model is then transferred to the target dataset of low-dose CT image. Region of interest is obtained through a deep residual network with attention mechanism. Pyradiomics is used to extract radiomics features of ROI, and T-test and LASSO algorithm are used for feature screening. Finally, support vector machine, random forest and logistic regression models are adopted to classify and predict the quality of low-dose CT image based on the selected radiomics features. Experimental results show that the trained deep residual network model with attention module can achieve 92% recognition accuracy of region of interest, and the evaluation accuracy of the three machine learning models achieve 86.6% (support vector machine), 84.5% (random forest) and 61.7% (logistic regression), respectively. Transfer learning can effectively reduce the required number of samples for the training of deep learning model and avoid overfitting. After the introduction of attention module in deep residual network model, accuracy rises faster, and the final accuracy is slightly higher than that of deep residual network model without attention module, but the improvement is slightly lower than expected. Radiomics features of region of interest reflect the quality differences of low-dose CT images which can be employed for the quality evaluation of low-dose CT image.

Applying multi-layer perceptron and ResNet for handwritten digits recognition

The task of handwritten digit recognition is to recognizing the handwritten digits from pictures. Applying machine learning based models to automatically perform handwritten digit recognition task can significantly improve efficiency. This paper applies two machine learning based models, including multi-layer perceptron and residual neural network, for such a task. Firstly, this paper introduces the basic concept of the simple multi-layer perceptron model and then presents the structure of the residual neural network model. Subsequently, such two models are trained on the MNIST corpus, one of the classical dataset for the handwritten digit recognition task. The data pre-processing, like the splitting of training and test set, is described. Also, the processes of testing and training of the two models are presented. According to the experiments on the test set of MNIST, it is observed that the residual neural network can achieve better performance where the accuracy score is 99.240%, while the accuracy score of the multi-layer perceptron model is 97.260%.

An Early Detection and Classification of Alzheimer's Disease Framework Based on ResNet-50.

The objective of this study is to develop a more effective early detection system for Alzheimer's disease (AD) using a Deep Residual Network (ResNet) model by addressing the issue of convolutional layers in conventional Convolutional Neural Networks (CNN) and applying image preprocessing techniques. The proposed method involves using Contrast Limited Adaptive Histogram Equalizer (CLAHE) and Boosted Anisotropic Diffusion Filters (BADF) for equalization and noise removal and K-means clustering for segmentation. A ResNet-50 model with shortcut links between three residual layers is proposed to extract features more efficiently. ResNet-50 is preferred over other ResNet types due to its intermediate depth, striking a balance between computational efficiency and improved performance, making it a widely adopted and effective architecture for various computer vision tasks. While other ResNet variations may offer higher depths, they are more prone to overfitting and computational complexity, which can hinder their practical application. The proposed method is evaluated on a dataset of MRI scans of AD patients. The proposed method achieved high accuracy and minimum losses of 95% and 0.12, respectively. While some models showed better accuracy, they were prone to overfitting. In contrast, the suggested framework, based on the ResNet-50 model, demonstrated superior performance in terms of various performance metrics, providing a robust and reliable approach to Alzheimer's disease categorization. The proposed ResNet-50 model with shortcut links between three residual layers, combined with image preprocessing techniques, provides an effective early detection system for AD. The study demonstrates the potential of deep learning and image processing techniques in developing accurate and efficient diagnostic tools for AD. The proposed method improves the existing approaches to AD classification and provides a promising framework for future research in this area.

MJAR: A novel joint generalization-based diagnosis method for industrial robots with compound faults

Compound faults inevitably occur in multi-joint industrial robots resulting in excessive vibration. Intelligent diagnosis for the occurrence and position of fault joints can efficiently reduce the maintenance cost. Compared with laboratory disassembly parts, joint diagnosis of in-situ industrial robots is more challenging due to coupling of multiple subsystems and the industrial noise interference. This paper proposes a novel joint generalization-based fault diagnosis method for industrial robots via the multi-joint attention residual network (MJAR) model. Each joint signals are independently input to parallel residual convolution with unidirectional matrix kernel (ResCUM) in multi-joint decoupling attention (MJDA) module, which is exclusively designed combining residual and attention mechanism to provide decoupling capability of compound faults. And the multi-spatial reconstruction (MSR) module based on sparse sampling is design to provide multi-scale feature extraction adapted to real industrial signals. MJAR can diagnose unseen compound fault combinations without using any transfer strategy as the robot joint generalization-based fault diagnosis (RJGFD) framework. Integrated experiment results show that the MJAR is superior to some advanced congener DL methods.

Open-Circuit Fault Analysis and Recognition in Three-Level Inverters Based on Recurrence Plot and Convolution Neural Network

Power electronics is vital to modern infrastructure, but it is susceptible to open-circuit faults that can cause serious damage. Three-level inverters are commonly used in such equipment, but their high sensitivity and probability of failure make them particularly challenging to diagnose. In this groundbreaking study, we present a new method for accurately detecting and locating open-circuit faults in three-level, neutral-clamped inverters. Using advanced simulation tools and nonlinear dynamic methods, we develop a new diagnostic model that outperforms existing fault classification algorithms. By converting the current signal into an unthreshold recurrence plot (URP) and mapping its nonlinear features to a two-dimensional plane, it is possible to extract key spatial information and train a residual neural network model for fault diagnosis. The method represents a major advance in power electronics and has the potential to save equipment from costly damage. By accurately detecting and locating open-circuit faults in three-level inverters, the reliability and safety of power electronics can be guaranteed for years to come.

Prediction of Progression After Cervix Cancer Radiotherapy Using a Machine-Learning Model on Pre-Treatment MRI

MRI may be useful to identify women with cervical cancer at high risk of disease progression to test strategies of treatment intensification. The purpose of this study was to determine the value of a machine-learning model built on pre-treatment MRI for prediction of risk of progression after radiation therapy. MagneticResonance Imaging (MRI) data for women with cervical cancer was collected from The Cancer Genome Atlas Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma Collection (TCGA-CESC) on the Cancer Imaging Archive (TCIA), which reported clinical, treatment, and imaging data from a single institution. 27 patients who had received radiation for cervical cancer were selected for input into a custom 3-D Residual Neural Network (ResNet) model with added custom layers specific to DICOM data in tensorflow python package. One T2 MRI per patient was used to predict recurrence free survival after radiation treatment, where patients were predicted to be "high risk" or "low risk" for disease recurrence as the output of the model. All slices of the T2 MRI were used. The model was validated using five-fold cross validation; 80% of the data was used to train each fold and 20% was used for testing. Final model statistical significance was confirmed through shuffle test at the p < 0.01 level. The clinical outcomes of patients and the model's "low-risk" and "high-risk" prediction were compared. There were 27 patients in the study with mean age of 51 years (range 29-79). 20 patients had squamous cell carcinoma and 7 patients had adenocarcinoma. The stage breakdown consisted of 9 women IB, 2 IIA, 9 IIB, 2 IIIA, 2 IIIB, and 3 stage IV. 10 women were treated with radiation alone and 17 with chemo-radiation. 5 women received surgery in addition to radiation or chemoradiation. 21 patients received brachytherapy. Median follow-up of patients was 29 months (range 3-64). The model predicted 7 patients as "high risk" for recurrence; all 7 developed a recurrence during follow up. None of the 20 patients predicted to be "low risk" developed disease recurrence. Among all patients in the study, the two-year progression free survival (PFS) was 82.0%. Patients identified as "low risk" and "high risk" by model had two-year PFS of 100% and 43%, respectively. Among patients with recurrence, 3 developed local recurrence and 4 developed distant metastases. The ResNet model achieved cross-validated accuracy of 92% for prediction of progression-free survival (p<0.01). A 3-D ResNet machine-learning model using pretreatment MRI image data can accurately predict clinical outcomes for cervical cancer following radiation therapy. Future work to confirm generalizability should focus on validation with a larger clinical dataset.

An autoencoder deep residual network model for multi focus image fusion

An autoencoder deep residual network model for multi focus image fusion