One of the most important processes in the diagnosis of breast cancer, which is the leading mortality rate in women, is the detection of the mitosis stage at the cellular level. In literature, many studies have been proposed on the computer-aided diagnosis (CAD) system for detecting mitotic cells in breast cancer histopathological images. In this study, comparative evaluation of conventional and deep learning based feature extraction methods for automatic detection of mitosis in histopathological images are focused. While various handcrafted features are extracted with textural/spatial, statistical and shape-based methods in conventional approach, the convolutional neural network structure proposed on the deep learning approach aims to create an architecture that extracts the features of small cellular structures such as mitotic cells. Mitosis detection/counting is an important process that helps us assess how aggressive or malignant the cancer’s spread is. In the proposed study, approximately 180,000 non-mitotic and 748 mitotic cells are extracted for the evaluations. It is obvious that the classification stage cannot be performed properly due to the imbalanced numbers of mitotic and non-mitotic cells extracted from histopathological images. Hence, the random under-sampling boosting (RUSBoost) method is exploited to overcome this problem. The proposed framework is tested on mitosis detection in breast cancer histopathological images dataset provided from the International Conference on Pattern Recognition (ICPR) 2014 contest. In the results obtained with the deep learning approach, 79.42% recall, 96.78% precision and 86.97% F-measure values are achieved more successfully than handcrafted methods. A client/server-based framework has also been developed as a secondary decision support system for use by pathologists in hospitals. Thus, it is aimed that pathologists will be able to detect mitotic cells in various histopathological images more easily through necessary interfaces.
相似文献Immunoglobulin A (IgA)-nephropathy (IgAN) is one of the major reasons for renal failure. It provides vital clues to estimate the stage and the proliferation rate of end-stage kidney disease. IgA stage can be estimated with the help of MEST-C score. The manual estimation of MEST-C score from whole slide kidney images is a very tedious and difficult task. This study uses some Convolutional neural networks (CNNs) related models to detect mesangial hypercellularity (M score) in MEST-C. CNN learns the features directly from image data without the requirement of analytical data. CNN is trained efficiently when image data size is large enough for a particular class. In the case of smaller data size, transfer learning can be used efficiently in which CNN is pre-trained on some general images and then on subject images. Since the data set size is small, time spent in collecting large data set is saved. The training time of transfer learning is also reduced because the model is already pre-trained. This research work aims at the detection of mesangial hypercellularity from biopsy images with small data size by utilizing the transfer learning. The dataset used in this research work consists of 138 individual glomerulus (× 20 magnification digital biopsy) images of IgA patients received from All India Institute of Medical Science, Delhi. Here, machine learning (k-nearest neighbour (KNN) and support vector machine (SVM)) classifiers are compared to transfer learning CNN methods. The deep extracted image features are used by machine learning classifiers. The different evaluation parameters have been used for comparing the predictions of basic classifiers to the deep learning model. The research work concludes that the transfer learning deep CNN method can improve the detection of mesangial hypercellularity as compare to KNN, SVM methods when using the small data set. This model could help the pathologists to understand the stages of kidney failure.
相似文献To prevent the same known vulnerabilities from affecting different firmware, searching known vulnerabilities in binary firmware across different architectures is crucial. Because the accuracy of existing cross-architecture vulnerability search methods is not high, we propose a staged approach based on support vector machine (SVM) and attributed control flow graph (ACFG) at the function level to improve the accuracy using prior knowledge. Furthermore, for efficiency, we utilize the k-nearest neighbor (kNN) algorithm to prune and SVM to refine in the function prefilter stage. Although the accuracy of the proposed method using kNN-SVM approach is slightly lower than the accuracy of the method using only SVM, its efficiency is significantly enhanced. We have implemented our approach CVSkSA to search several vulnerabilities in real-world firmware images. The experimental results show that the accuracy of the proposed method using kNN-SVM approach is close to the accuracy of the method using only SVM in most cases, while the former is approximately four times faster than the latter.
相似文献Recent research on image super-resolution (SR) has greatly progressed with the development of convolutional neural networks (CNNs). However, the fixed geometric structures of standard convolution filters largely limit the learning capacity of CNNs for image SR. To effectively address this problem, we propose a deformable and residual convolutional network (DefRCN) for image SR. Specifically, a deformable residual convolution block (DRCB) is developed to augment spatial sampling locations and enhance the transformation modelling capability of CNNs. In addition, we optimize the residual convolution block to reduce the model redundancy and alleviate the vanishing-gradient in backpropagation. In addition, the proposed upsample block allows the network to directly process low-resolution images, which reduces the computational resource cost. Extensive experiments on benchmark datasets verify that the proposed method achieves a high quantitative and qualitative performance.
相似文献The purpose of this study was to explore the value of extraction of tumor features in contrast-enhanced ultrasonography (CEUS) images based on the deep belief networks (DBN) for the diagnosis of cervical cancer patients and realize the intelligent evaluation on effects of diagnosis and chemotherapy of the cervical cancer. An automatic extraction algorithm with the time-intensity curve (TIC) was proposed based on Sparse nonnegative matrix factorization (SNMF) in this study, and was applied to the framework of automatic analysis of cervical cancer tumors based on the deep belief networks, to assist doctors in the analysis of cervical cancer tumors. The framework was applied to the real clinical diagnostic data, and the feasibility of the method was verified by comparing the accuracy, sensitivity, and specificity. Later, the parameters of patients’ time to peak (TP), peak intensity (PI), mean transit time (MTT), and area under the curve (AUC) were obtained by drawing TICs, and the changes of p53 protein and ki-67 protein obtained by pathological section staining were analyzed to evaluate the therapeutic effect in the patients. It was found that the proposed model of tumor feature extraction based on the DBN had the higher accuracy (86.36%), sensitivity (83.33%), and specificity (87.50%). The related parameters of TIC curve obtained based on SNMF showed that there was a significant difference in p53 content between tissues with different degrees of disease (p?<?0.05), the PI of poorly differentiated tissues was significantly higher than that of those with high to medium differentiation (p?<?0.05). In addition, PI and AUC of patients after chemotherapy were significantly lower than that before chemotherapy (p?<?0.05), while MTT was significantly higher than that before chemotherapy (p?<?0.05). Therefore, the proposed TIC feature extraction of CEUS images based on SNMF and the automatic tumor classification based on deep learning can be used in the diagnosis and efficacy evaluation of cervical cancer patients.
相似文献Convolution neural networks (CNNs) based on the discrete convolutional operation have achieved great success in image processing, voice and audio processing, natural language processing and other fields. However, it is still an open problem how to develop new models instead of CNNs. Using the idea of the sequence block matrix product, we propose a novel operation and its corresponding neural network, namely two-dimensional discrete matrix-product operation (TDDMPO) and matrix-product neural network (MPNN). We present the definition of the TDDMPO, a series of its properties and matrix-product theorem in detail, and then construct its corresponding MPNN. Experimental results on Fashion-MNIST, SVHN, FLOWER17 and FLOWER102 datasets show that MPNNs obtain 1.65–13.04% relative performance improvement in comparison with the corresponding CNNs, and the amount of calculation of matrix-product layers of MPNNs obtains 41× to 57× reduction in comparison with the corresponding convolutional layers of CNNs. Hence, it is a potential model that may open some new directions for deep neural networks, particularly alternatives to CNNs.
相似文献Palmprint recognition and palm vein recognition are two emerging biometrics technologies. In the past two decades, many traditional methods have been proposed for palmprint recognition and palm vein recognition, and have achieved impressive results. However, the research on deep learning-based palmprint recognition and palm vein recognition is still very preliminary. In this paper, in order to investigate the problem of deep learning based 2D and 3D palmprint recognition and palm vein recognition in-depth, we conduct performance evaluation of seventeen representative and classic convolutional neural networks (CNNs) on one 3D palmprint database, five 2D palmprint databases and two palm vein databases. A lot of experiments have been carried out in the conditions of different network structures, different learning rates, and different numbers of network layers. We have also conducted experiments on both separate data mode and mixed data mode. Experimental results show that these classic CNNs can achieve promising recognition results, and the recognition performance of recently proposed CNNs is better. Particularly, among classic CNNs, one of the recently proposed classic CNNs, i.e., EfficientNet achieves the best recognition accuracy. However, the recognition performance of classic CNNs is still slightly worse than that of some traditional recognition methods.
相似文献The present study reports classification and analysis of composite land features using fusion images obtained by fusing two original hyperspectral and multispectral datasets. The high spatial-spectral resolution, multi-instrument and multi-period satellite images were used for fusion. Three pixel level fusion based techniques, Color Normalized Spectral Sharpening (CNSS), Principal Component Spectral Sharpening Transform (PCSST) and Gram-Schmidt Transform (GST), were implemented on the datasets. Performance evaluations of three fusion algorithms were done using classification results. The Support Vector Machine (SVM) and Gaussian Maximum Likelihood Classification (MLC) were used for classification using five types of images, viz. hyperspectral, multispectral and three fused images. Number of classes considered was eight. Sufficient number of ground field data for each class has also been acquired which was needed for supervise based classification. The accuracy was improved from 74.44 to 97.65% when the fused images were considered with SVM classifier. Similarly, the results were improved from 69.25 to 94.61% with original and fused data using MLC classifier. The fusion image technique was found to be superior to the single original image and the SVM is better than the MLC method.
相似文献This paper proposes a novel deep learning-based approach for financial chart patterns classification. Convolutional neural networks (CNNs) have made notable achievements in image recognition and computer vision applications. These networks are usually based on two-dimensional convolutional neural networks (2D CNNs). In this paper, we describe the design and implementation of one-dimensional convolutional neural networks (1D CNNs) for the classification of chart patterns from financial time series. The proposed 1D CNN model is compared against support vector machine, extreme learning machine, long short-term memory, rule-based and dynamic time warping. Experimental results on synthetic datasets reveal that the accuracy of 1D CNN is highest among all the methods evaluated. Results on real datasets also reveal that chart patterns identified by 1D CNN are also the most recognized instances when they are compared to those classified by other methods.
相似文献With new architectures providing astonishing performance on many vision tasks, the interest in Convolutional Neural Networks (CNNs) has grown exponentially in the recent past. Such architectures, however, are not problem-free. For instance, one of the many issues is that they require a huge amount of labeled data and are not able to encode pose and deformation information. Capsule Networks (CapsNets) have been recently proposed as a solution to the issues related to CNNs. CapsNet achieved interesting results in images recognition by addressing pose and deformation encoding challenges. Despite their success, CapsNets are still an under-investigated architecture with respect to the more classical CNNs. Following the ideas of CapsNet, we propose to introduce Residual Capsule Network (ResNetCaps) and Dense Capsule Network (DenseNetCaps) to tackle the image recognition problem. With these two architectures, we expand the encoding phase of CapsNet by adding residual convolutional and densely connected convolutional blocks. In addition to this, we investigate the application of feature interaction methods between capsules to promote their cooperation while dealing with complex data. Experiments on four benchmark datasets demonstrate that the proposed approach performs better than existing solutions.
相似文献This study introduces a new strategy that combines unsupervised learning (clustering) and transfer learning. Clustering methods are employed to generate synthetic labels for the source dataset (ICAR-2018). The generated dataset is then used for transfer learning to other histopathological datasets (KimiaPath960, CRC, Biomaging??2015, Breakhis, and Lymphoma). The comparative study based on two clustering algorithms (K-means and multi-objective clustering stream) demonstrates the efficiency of MOC-Stream. The generated synthetic histopathological dataset by this clustering algorithm outperformed the original labeled dataset and the imageNet models in transfer learning.
相似文献The process of separation of brain tumor from normal brain tissues is Brain tumor segmentation. Segmentation of tumor from the MR images is a very challenging task as brain tumors are of different shapes and sizes. There are multiple phases to achieve the segmentation and the phases are pre-processing, segmentation, feature extraction, feature reduction, and classification of the tumor into benign and malignant. In this paper, Otsu thresholding is used in segmentation phase, Discrete Wavelet Transform (DWT) in feature extraction phase, Principal Component Analysis (PCA) in feature reduction phase and Support Vector Machine (SVM), Least Squared-Support Vector Machine (LS-SVM), Proximal Support Vector Machine (PSVM) and Twin Support Vector Machine (TWSVM) in the classification phase. We have compared the performances of all these classifiers, where TWSVM outperformed all other classifiers with 100% accuracy.
相似文献In the register detection of printing field, a new approach based on Zernike-CNNs is proposed. The edge feature of image is extracted by Zernike moments (ZMs), and a recursive algorithm of ZMs called Kintner method is derived. An improved convolutional neural networks (CNNs) are investigated to improve the accuracy of classification. Based on the classic convolutional neural network (CNN), the improved CNNs adopt parallel CNN to enhance local features, and adopt auxiliary classification part to modify classification layer weights. A printed image is trained with 7?×?400 samples and tested with 7?×?100 samples, and then the method in this paper is compared with other methods. In image processing, Zernike is compared with Sobel method, Laplacian of Gaussian (LoG) method, Smallest Univalue Segment Assimilating Nucleus (SUSAN) method, Finite Impusle Response (FIR) method, Multi-scale Morphological Gradient (MMG) method. In image classification, improved CNNs are compared with classical CNN. The experimental results show that Zernike-CNNs have the best performance, the mean square error (MSE) of the training samples reaches 0.0143, and the detection accuracy of training samples and test samples reached 91.43% and 94.85% respectively. The experiments reveal that Zernike-CNNs are a feasible approach for register detection.
相似文献