Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification.
Ontology highlight
ABSTRACT:
SUBMITTER: Bing L
PROVIDER: S-EPMC5463197 | biostudies-other | 2017
REPOSITORIES: biostudies-other
Similar Datasets
Project description:The segmentation of prostate in CT images is of essential importance to external beam radiotherapy, which is one of the major treatments for prostate cancer nowadays. During the radiotherapy, the prostate is radiated by high-energy x rays from different directions. In order to maximize the dose to the cancer and minimize the dose to the surrounding healthy tissues (e.g., bladder and rectum), the prostate in the new treatment image needs to be accurately localized. Therefore, the effectiveness and efficiency of external beam radiotherapy highly depend on the accurate localization of the prostate. However, due to the low contrast of the prostate with its surrounding tissues (e.g., bladder), the unpredicted prostate motion, and the large appearance variations across different treatment days, it is challenging to segment the prostate in CT images. In this paper, the authors present a novel classification based segmentation method to address these problems.To segment the prostate, the proposed method first uses sparse representation based classification (SRC) to enhance the prostate in CT images by pixel-wise classification, in order to overcome the limitation of poor contrast of the prostate images. Then, based on the classification results, previous segmented prostates of the same patient are used as patient-specific atlases to align onto the current treatment image and the majority voting strategy is finally adopted to segment the prostate. In order to address the limitations of the traditional SRC in pixel-wise classification, especially for the purpose of segmentation, the authors extend SRC from the following four aspects: (1) A discriminant subdictionary learning method is proposed to learn a discriminant and compact representation of training samples for each class so that the discriminant power of SRC can be increased and also SRC can be applied to the large-scale pixel-wise classification. (2) The L1 regularized sparse coding is replaced by the elastic net in order to obtain a smooth and clear prostate boundary in the classification result. (3) Residue-based linear regression is incorporated to improve the classification performance and to extend SRC from hard classification to soft classification. (4) Iterative SRC is proposed by using context information to iteratively refine the classification results.The proposed method has been comprehensively evaluated on a dataset consisting of 330 CT images from 24 patients. The effectiveness of the extended SRC has been validated by comparing it with the traditional SRC based on the proposed four extensions. The experimental results show that our extended SRC can obtain not only more accurate classification results but also smoother and clearer prostate boundary than the traditional SRC. Besides, the comparison with other five state-of-the-art prostate segmentation methods indicates that our method can achieve better performance than other methods under comparison.The authors have proposed a novel prostate segmentation method based on the sparse representation based classification, which can achieve considerably accurate segmentation results in CT prostate segmentation.
| S-EPMC3477196 | biostudies-other
Project description:Breast cancer diagnosis is one of the many areas that has taken advantage of artificial intelligence to achieve better performance, despite the fact that the availability of a large medical image dataset remains a challenge. Transfer learning (TL) is a phenomenon that enables deep learning algorithms to overcome the issue of shortage of training data in constructing an efficient model by transferring knowledge from a given source task to a target task. However, in most cases, ImageNet (natural images) pre-trained models that do not include medical images, are utilized for transfer learning to medical images. Considering the utilization of microscopic cancer cell line images that can be acquired in large amount, we argue that learning from both natural and medical datasets improves performance in ultrasound breast cancer image classification. The proposed multistage transfer learning (MSTL) algorithm was implemented using three pre-trained models: EfficientNetB2, InceptionV3, and ResNet50 with three optimizers: Adam, Adagrad, and stochastic gradient de-scent (SGD). Dataset sizes of 20,400 cancer cell images, 200 ultrasound images from Mendeley and 400 ultrasound images from the MT-Small-Dataset were used. ResNet50-Adagrad-based MSTL achieved a test accuracy of 99 ± 0.612% on the Mendeley dataset and 98.7 ± 1.1% on the MT-Small-Dataset, averaging over 5-fold cross validation. A p-value of 0.01191 was achieved when comparing MSTL against ImageNet based TL for the Mendeley dataset. The result is a significant improvement in the performance of artificial intelligence methods for ultrasound breast cancer classification compared to state-of-the-art methods and could remarkably improve the early diagnosis of breast cancer in young women.
| S-EPMC8775102 | biostudies-literature
Project description:Sparse representation classification (SRC) is one of the most promising classification methods for supervised learning. This method can effectively exploit discriminating information by introducing a [Symbol: see text]1 regularization terms to the data. With the desirable property of sparisty, SRC is robust to both noise and outliers. In this study, we propose a weighted meta-sample based non-parametric sparse representation classification method for the accurate identification of tumor subtype. The proposed method includes three steps. First, we extract the weighted meta-samples for each sub class from raw data, and the rationality of the weighting strategy is proven mathematically. Second, sparse representation coefficients can be obtained by [Symnbol: see text]1 regularization of underdetermined linear equations. Thus, data dependent sparsity can be adaptively tuned. A simple characteristic function is eventually utilized to achieve classification. Asymptotic time complexity analysis is applied to our method. Compared with some state-of-the-art classifiers, the proposed method has lower time complexity and more flexibility. Experiments on eight samples of publicly available gene expression profile data show the effectiveness of the proposed method.
| S-EPMC4130588 | biostudies-literature
Project description:An image target recognition approach based on mixed features and adaptive weighted joint sparse representation is proposed in this paper. This method is robust to the illumination variation, deformation, and rotation of the target image. It is a data-lightweight classification framework, which can recognize targets well with few training samples. First, Gabor wavelet transform and convolutional neural network (CNN) are used to extract the Gabor wavelet features and deep features of training samples and test samples, respectively. Then, the contribution weights of the Gabor wavelet feature vector and the deep feature vector are calculated. After adaptive weighted reconstruction, we can form the mixed features and obtain the training sample feature set and test sample feature set. Aiming at the high-dimensional problem of mixed features, we use principal component analysis (PCA) to reduce the dimensions. Lastly, the public features and private features of images are extracted from the training sample feature set so as to construct the joint feature dictionary. Based on joint feature dictionary, the sparse representation based classifier (SRC) is used to recognize the targets. The experiments on different datasets show that this approach is superior to some other advanced methods.
| S-EPMC7436358 | biostudies-literature
Project description:The classification of tumors is crucial for the proper treatment of cancer. Sparse representation-based classifier (SRC) exhibits good classification performance and has been successfully used to classify tumors using gene expression profile data. In this study, we propose a three-step maxdenominator reweighted sparse representation classification (MRSRC) method to classify tumors. First, we extract a set of metagenes from the training samples. These metagenes can capture the structures inherent to the data and are more effective for classification than the original gene expression data. Second, we use a reweighted regularization method to obtain the sparse representation coefficients. Reweighted regularization can enhance sparsity and obtain better sparse representation coefficients. Third, we classify the data by utilizing a maxdenominator residual error function. Maxdenominator strategy can reduce the residual error and improve the accuracy of the final classification. Extensive experiments using publicly available gene expression profile data sets show that the performance of MRSRC is comparable with or better than many existing representative methods.
| S-EPMC5385541 | biostudies-literature
Project description:We hide grayscale secret images into a grayscale cover image, which is considered to be a challenging steganography problem. Our goal is to develop a steganography scheme with enhanced embedding capacity while preserving the visual quality of the stego-image as well as the extracted secret image, and ensuring that the stego-image is resistant to steganographic attacks. The novel embedding rule of our scheme helps to hide secret image sparse coefficients into the oversampled cover image sparse coefficients in a staggered manner. The stego-image is constructed by using the Alternating Direction Method of Multipliers (ADMM) to solve the Least Absolute Shrinkage and Selection Operator (LASSO) formulation of the underlying minimization problem. Finally, the secret images are extracted from the constructed stego-image using the reverse of our embedding rule. Using these components together, to achieve the above mentioned competing goals, forms our most novel contribution. We term our scheme SABMIS (Sparse Approximation Blind Multi-Image Steganography). We perform extensive experiments on several standard images. By choosing the size of the length and the width of the secret images to be half of the length and the width of cover image, respectively, we obtain embedding capacities of 2 bpp (bits per pixel), 4 bpp, 6 bpp, and 8 bpp while embedding one, two, three, and four secret images, respectively. Our focus is on hiding multiple secret images. For the case of hiding two and three secret images, our embedding capacities are higher than all the embedding capacities obtained in the literature until now (3 times and 6 times than the existing best, respectively). For the case of hiding four secret images, although our capacity is slightly lower than one work (about 2/3rd), we do better on the other two goals (quality of stego-image & extracted secret image as well as resistance to steganographic attacks). For our experiments, there is very little deterioration in the quality of the stego-images as compared to their corresponding cover images. Like all other competing works, this is supported visually as well as over 30 dB of Peak Signal-to-Noise Ratio (PSNR) values. The good quality of the stego-images is further validated by multiple numerical measures. None of the existing works perform this exhaustive validation. When using SABMIS, the quality of the extracted secret images is almost same as that of the corresponding original secret images. This aspect is also not demonstrated in all competing literature. SABMIS further improves the security of the inherently steganographic attack resistant transform based schemes. Thus, it is one of the most secure schemes among the existing ones. Additionally, we demonstrate that SABMIS executes in few minutes, and show its application on the real-life problems of securely transmitting medical images over the internet.
| S-EPMC9748825 | biostudies-literature
Project description:The task of predicting protein-protein interactions (PPIs) has been essential in the context of understanding biological processes. This paper proposes a novel computational model namely FCTP-WSRC to predict PPIs effectively. Initially, combinations of the F-vector, composition (C) and transition (T) are used to map each protein sequence onto numeric feature vectors. Afterwards, an effective feature extraction method PCA (principal component analysis) is employed to reconstruct the most discriminative feature subspaces, which is subsequently used as input in weighted sparse representation based classification (WSRC) for prediction. The FCTP-WSRC model achieves accuracies of 96.67%, 99.82%, and 98.09% for H. pylori, Human and Yeast datasets respectively. Furthermore, the FCTP-WSRC model performs well when predicting three significant PPIs networks: the single-core network (CD9), the multiple-core network (Ras-Raf-Mek-Erk-Elk-Srf pathway), and the cross-connection network (Wnt-related Network). Consequently, the promising results show that the proposed method can be a powerful tool for PPIs prediction with excellent performance and less time.
| S-EPMC7010952 | biostudies-literature
Project description:Sensory systems create neural representations of environmental stimuli and these representations can be associated with other stimuli through learning. Are spike patterns the neural representations that get directly associated with reinforcement during conditioning? In the moth Manduca sexta, we found that odor presentations that support associative conditioning elicited only one or two spikes on the odor's onset (and sometimes offset) in each of a small fraction of Kenyon cells. Using associative conditioning procedures that effectively induced learning and varying the timing of reinforcement relative to spiking in Kenyon cells, we found that odor-elicited spiking in these cells ended well before the reinforcement was delivered. Furthermore, increasing the temporal overlap between spiking in Kenyon cells and reinforcement presentation actually reduced the efficacy of learning. Thus, spikes in Kenyon cells do not constitute the odor representation that coincides with reinforcement, and Hebbian spike timing-dependent plasticity in Kenyon cells alone cannot underlie this learning.
| S-EPMC3124899 | biostudies-literature
Project description:Quantitative Transmission Ultrasound (QT) is a powerful and emerging imaging paradigm which has the potential to perform true three-dimensional image reconstruction of biological tissue. Breast imaging is an important application of QT and allows non-invasive, non-ionizing imaging of whole breasts in vivo. Here, we report the first demonstration of breast tissue image classification in QT imaging. We systematically assess the ability of the QT images' features to differentiate between normal breast tissue types. The three QT features were used in Support Vector Machines (SVM) classifiers, and classification of breast tissue as either skin, fat, glands, ducts or connective tissue was demonstrated with an overall accuracy of greater than 90%. Finally, the classifier was validated on whole breast image volumes to provide a color-coded breast tissue volume. This study serves as a first step towards a computer-aided detection/diagnosis platform for QT.
| S-EPMC5146962 | biostudies-literature
Project description:Brain functional network analysis has shown great potential in understanding brain functions and also in identifying biomarkers for brain diseases, such as Alzheimer's disease (AD) and its early stage, mild cognitive impairment (MCI). In these applications, accurate construction of biologically meaningful brain network is critical. Sparse learning has been widely used for brain network construction; however, its l1 -norm penalty simply penalizes each edge of a brain network equally, without considering the original connectivity strength which is one of the most important inherent linkwise characters. Besides, based on the similarity of the linkwise connectivity, brain network shows prominent group structure (i.e., a set of edges sharing similar attributes). In this article, we propose a novel brain functional network modeling framework with a "connectivity strength-weighted sparse group constraint." In particular, the network modeling can be optimized by considering both raw connectivity strength and its group structure, without losing the merit of sparsity. Our proposed method is applied to MCI classification, a challenging task for early AD diagnosis. Experimental results based on the resting-state functional MRI, from 50 MCI patients and 49 healthy controls, show that our proposed method is more effective (i.e., achieving a significantly higher classification accuracy, 84.8%) than other competing methods (e.g., sparse representation, accuracy = 65.6%). Post hoc inspection of the informative features further shows more biologically meaningful brain functional connectivities obtained by our proposed method. Hum Brain Mapp 38:2370-2383, 2017. © 2017 Wiley Periodicals, Inc.
| S-EPMC5488335 | biostudies-literature