Removing noise from scanned pages is a vital step before their submission to optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However, this assumption is rarely met in real settings. Besides, there is no single model that can remove various noise types from documents. Here, we propose a unified end-to-end unsupervised deep learning model, for the first time, that can effectively remove multiple types of noise, including salt & pepper noise, blurred and/or faded text, as well as watermarks from documents at various levels of intensity. We demonstrate that the proposed model significantly improves the quality of scanned images and the OCR of the pages on several test datasets.

GOAL: In computational biology, selecting a small subset of informative genes from microarray data continues to be a challenge due to the presence of thousands of genes. This paper aims at quantifying the dependence between gene expression data and the response variables and to identifying a subset of the most informative genes using a fast and scalable multivariate algorithm. METHODS: A novel algorithm for feature selection from gene expression data was developed. The algorithm was based on the Hilbert-Schmidt independence criterion (HSIC), and was partly motivated by singular value decomposition (SVD). RESULTS: The algorithm is computationally fast and scalable to large datasets. Moreover, it can be applied to problems with any type of response variables including, biclass, multiclass, and continuous response variables. The performance of the proposed algorithm in terms of accuracy, stability of the selected genes, speed, and scalability was evaluated using both synthetic and real-world datasets. The simulation results demonstrated that the proposed algorithm effectively and efficiently extracted stable genes with high predictive capability, in particular for datasets with multiclass response variables. CONCLUSION/SIGNIFICANCE: The proposed method does not require the whole microarray dataset to be stored in memory, and thus can easily be scaled to large datasets. This capability is an important attribute in big data analytics, where data can be large and massively distributed.

A noninvasive computer-aided-theragnosis (CAT) system was developed for the early therapeutic cancer response assessment in patients with locally advanced breast cancer (LABC) treated with neoadjuvant chemotherapy. The proposed CAT system was based on multi-parametric quantitative ultrasound (QUS) spectroscopic methods in conjunction with advanced machine learning techniques. Specifically, a kernel-based metric named maximum mean discrepancy (MMD), a technique for learning from imbalanced data based on random undersampling, and supervised learning were investigated with response-monitoring data from LABC patients. The CAT system was tested on 56 patients using statistical significance tests and leave-one-subject-out classification techniques. Textural features using state-of-the-art local binary patterns (LBP), and gray-scale intensity features were extracted from the spectral parametric maps in the proposed CAT system. The system indicated significant differences in changes between the responding and non-responding patient populations as well as high accuracy, sensitivity, and specificity in discriminating between the two patient groups early after the start of treatment, i.e., on weeks 1 and 4 of several months of treatment. The proposed CAT system achieved an accuracy of 85%, 87%, and 90% on weeks 1, 4 and 8, respectively. The sensitivity and specificity of developed CAT system for the same times was 85%, 95%, 90% and 85%, 85%, 91%, respectively. The proposed CAT system thus establishes a noninvasive framework for monitoring cancer treatment response in tumors using clinical ultrasound imaging in conjunction with machine learning techniques. Such a framework can potentially facilitate the detection of refractory responses in patients to treatment early on during a course of therapy to enable possibly switching to more efficacious treatments.

PURPOSE: Pathologists often look at whole slide images (WSIs) at low magnification to find potentially important regions and then zoom in to higher magnification to perform more sophisticated analysis of the tissue structures. Many automated methods of WSI analysis attempt to preprocess the down-sampled image in order to select salient regions which are then further analyzed by a more computationally intensive step at full magnification. Although it can greatly reduce processing times, this process may lead to small potentially important regions being overlooked at low magnification. We propose a texture analysis technique to ease the processing of H&E stained WSIs by triaging clinically important regions. METHOD: Image patches randomly selected from the whole tissue area were divided into smaller tiles and Gaussian-like texture filters were applied to them. Texture filter responses from each tile were combined together and statistical measures were derived from their histograms of responses. Bag of visual words pipeline was then employed to combine extracted features from tiles to form one histogram of words per every image patch. A support vector machine classifier was trained using the calculated histograms of words to be able to distinguish between clinically relevant and irrelevant patches. RESULT: Experimental analysis on 5151 image patches from 10 patient cases (65 tissue slides) indicated that our proposed texture technique out-performed two previously proposed colour and intensity based methods with an area under the ROC curve of 0.87. CONCLUSION: Texture features can be employed to triage clinically important areas within large WSIs.

Recently, a supervised dictionary learning (SDL) approach based on the Hilbert-Schmidt independence criterion (HSIC) has been proposed that learns the dictionary and the corresponding sparse coefficients in a space where the dependency between the data and the corresponding labels is maximized. In this paper, two multiview dictionary learning techniques are proposed based on this HSIC-based SDL. While one of these two techniques learns one dictionary and the corresponding coefficients in the space of fused features in all views, the other learns one dictionary in each view and subsequently fuses the sparse coefficients in the spaces of learned dictionaries. The effectiveness of the proposed multiview learning techniques in using the complementary information of single views is demonstrated in the application of speech emotion recognition (SER). The fully-continuous sub-challenge (FCSC) of the AVEC 2012 dataset is used in two different views: baseline and spectral energy distribution (SED) feature sets. Four dimensional affects, i.e., arousal, expectation, power, and valence are predicted using the proposed multiview methods as the continuous response variables. The results are compared with the single views, AVEC 2012 baseline system, and also other supervised and unsupervised multiview learning approaches in the literature. Using correlation coefficient as the performance measure in predicting the continuous dimensional affects, it is shown that the proposed approach achieves the highest performance among the rivals. The relative performance of the two proposed multiview techniques and their relationship are also discussed. Particularly, it is shown that by providing an additional constraint on the dictionary of one of these approaches, it becomes the same as the other.

Quantitative ultrasound (QUS) spectroscopic techniques in conjunction with maximum mean discrepancy (MMD) have been proposed to detect, and to classify noninvasively the levels of cell death in response to cancer therapy administration in tumor models. Evaluation of xenograft tumor responses to cancer treatments were carried out using conventional-frequency ultrasound at different times after chemotherapy exposure. Ultrasound data were analyzed using spectroscopic techniques and multi-parametric QUS spectral maps were generated. MMD was applied as a distance criterion, measuring alterations in each tumor in response to chemotherapy, and the extent of cell death was classified into less/more than 20% and 40% categories. Statistically significant differences were observed between "pre-" and "post-treatment" groups at different times after chemotherapy exposure, suggesting a high capability of proposed framework for detecting tumor response noninvasively. Promising results were also obtained for categorizing the extent of cell death response in each tumor using the proposed framework, with gold standard histological quantification of cell death as ground truth. The best classification results were obtained using MMD when applied on histograms of QUS parametric maps. In this case, classification accuracies of 84.7% and 88.2% were achieved for categorizing extent of tumor cell death into less/more than 20% and 40%, respectively.

In text categorization (TC), which is a supervised technique, a feature vector of terms or phrases is usually used to represent the documents. Due to the huge number of terms in even a moderate-size text corpus, high dimensional feature space is an intrinsic problem in TC. Random subspace method (RSM), a technique that divides the feature space to smaller ones each submitted to a (base) classifier (BC) in an ensemble, can be an effective approach to reduce the dimensionality of the feature space. Inspired by a similar research on functional magnetic resonance imaging (fMRI) of brain, here we address the estimation of ensemble parameters, i.e., the ensemble size (L) and the dimensionality of feature subsets (M) by defining three criteria: usability, coverage, and diversity of the ensemble. We will show that relatively medium M and small L yield an ensemble that improves the performance of a single support vector machine, which is considered as the state-of-the-art in TC.

Following an idea from B.M. ter Haar Romeny (see "Front-end vision and multiscale image analysis", Kluwer Academic Publishers, 2002), based on the Gaussian properties of eigenimages, the paper presents a new technique for texture classification using multiresolution eigenimages. The input image, composed of two textures from the Brodatz album, is subdivided into N sub-images of fixed size /spl delta//spl times//spl delta/, which are blurred with a Gaussian and normalized. The application of a Hotelling transform decomposes each sub-image into /spl delta//sup 2/ eigenimages. The R largest resulting coefficients can be used for classification of the texture present in the sub-images. Classification is done using the fuzzy C-means (FCM) algorithm and the performance is measured with an appropriate quality factor. We discuss the successful application of this technique, as well as the influence of the different parameters of the classification process on several pairs of textures. Moreover, the combing of Hotelling coefficients obtained with different values of /spl delta/ is shown to improve the performance, based on the idea of analyzing the texture at different levels of resolution.