Search

Fetal viability, gestational age, and complicated image processing have made evaluating placental maturity a tedious and time-consuming task. Despite various developments, automatic placental maturity still remains as a challenging issue. To address this issue, we propose a new method to automatically grade placental maturity from B-mode ultrasound (BUS) and color Doppler energy (CDE) images based on a hybrid learning architecture. We also apply an improved pyramidal shift invariant feature transform (IPSIFT) descriptor using a coarse-to-fine scale representation for visual feature extraction. These local features are then clustered by a generative Gaussian mixture model (GMM) to incorporate high order statistics. Next, the clustering representatives are encoded and aggregated via Fisher vector (FV). Instead of using traditional FV, an end-to-end deep training strategy is developed to fine-tune the GMM parameters to boost evaluation performance. A multi-view fusion technique is also developed for feature complementarity exploration. Extensive experimental results demonstrate that our method delivers promising performance in placental maturity evaluation and outperforms competing methods. [ABSTRACT FROM AUTHOR]

Since most image classification tasks involve discriminative information (i.e., saliency), this paper proposes a new bag-of-phrase (BoP) approach to incorporate this information. Specifically, saliency map and local features are first extracted from edge-based dense descriptors. These features are represented by histogram and mined with discriminative learning technique. Image score calculated from the saliency map is also investigated to optimize a support vector machine (SVM) classifier. Both feature map and kernel trick methods are explored to enhance the accuracy of the SVM classifier. In addition, novel inter- and intra-class histogram normalization methods are investigated to further boost the performance of the proposed method. Experiments using several publicly available benchmark datasets demonstrate that the proposed method achieves promising classification accuracy and superior performance over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

• We propose an FTN which is fully relied on Transformer. • We leverage sliding window tokenization to construct hierarchical features. • Spatial Pyramid Transformer to increase efficiency. • Transformer Decoder is proposed to aggregate hierarchical features. Automatic skin lesion analysis in terms of skin lesion segmentation and disease classification is of great importance. However, these two tasks are challenging as skin lesion images of multi-ethnic population are collected using various scanners in multiple international medical institutes. To address them, most recent works adopt convolutional neural networks (CNNs) for skin lesion analysis. However, due to the intrinsic locality of the convolution operator, CNNs lack the ability to capture contextual information and long-range dependency. To improve the baseline performance established by CNNs, we propose a Fully Transformer Network (FTN) to learn long-range contextual information for skin lesion analysis. FTN is a hierarchical Transformer computing features using Spatial Pyramid Transformer (SPT). SPT has linear computational complexity as it introduces a spatial pyramid pooling (SPP) module into multi-head attention (MHA)to largely reduce the computation and memory usage. We conduct extensive skin lesion analysis experiments to verify the effectiveness and efficiency of FTN using ISIC 2018 dataset. Our experimental results show that FTN consistently outperforms other state-of-the-art CNNs in terms of computational efficiency and the number of tunable parameters due to our efficient SPT and hierarchical network structure. The code and models will be public available at: https://github.com/Novestars/Fully-Transformer-Network. [ABSTRACT FROM AUTHOR]

Highlights: [•] A reversible watermarking method is proposed with wavelet transforms and SVD. [•] Signature and logo data are inserted by recursive dither modulation algorithm. [•] DE is explored to design the quantization steps optimally. [•] Good balance of imperceptibility, robustness and capacity is obtained by DE. [•] Experiments show good performance and outperform the related algorithms. [ABSTRACT FROM AUTHOR]

Abstract: The self-demodulation property of finite-amplitude ultrasonic waves can be applied with parametric loudspeaker to produce audible sound. A special characteristic of the reproduced sound waves using parametric loudspeaker is its high directivity. However, the demodulated signal from parametric loudspeaker suffers from high distortion. To reduce the distortion in the demodulated signal, preprocessing of the modulating signal is usually employed. To determine the effectiveness of the preprocessing technique, an important practical constraint on the bandwidth of the ultrasonic transducer of the parametric loudspeaker should be accounted. In this paper, we shall discuss a class of preprocessing techniques that is based on quadrature amplitude modulation. As compared to the conventional preprocessing methods used with bandlimited ultrasonic transducer, the demodulated signal from our proposed preprocessing techniques exhibits lower distortion. [Copyright &y& Elsevier]

• We propose a PC-based sparse low-rank representation to construct FC networks. • We propose a self-weighted adaptive structure learning method. • Our method uses multi-template multi-center ensemble classification scheme. • Our method learns the modularity prior and local manifold structure. • Our method has achieved better classification performance. As a kind of neurodevelopmental disease, autism spectrum disorder (ASD) can cause severe social, communication, interaction, and behavioral challenges. To date, many imaging-based machine learning techniques have been proposed to address ASD diagnosis issues. However, most of these techniques are restricted to a single template or dataset from one imaging center. In this paper, we propose a novel multi-template multi-center ensemble classification scheme for automatic ASD diagnosis. Specifically, based on different pre-defined templates, we construct multiple functional connectivity (FC) brain networks for each subject based on our proposed Pearson's correlation-based sparse low-rank representation. After extracting features from these FC networks, informative features to learn optimal similarity matrix are then selected by our self-weighted adaptive structure learning (SASL) model. For each template, the SASL method automatically assigns an optimal weight learned from the structural information without additional weights and parameters. Finally, an ensemble strategy based on the multi- template multi-center representations is applied to derive the final diagnosis results. Extensive experiments are conducted on the publicly available Autism Brain Imaging Data Exchange (ABIDE) database to demonstrate the efficacy of our proposed method. Experimental results verify that our proposed method boosts ASD diagnosis performance and outperforms state-of-the-art methods. Image, graphical abstract. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is the world's second most common progressive neurodegenerative disease. This disease is characterized by a combination of various non-motor symptoms (e.g., depression, olfactory, and sleep disturbance) and motor symptoms (e.g., bradykinesia, tremor, rigidity), therefore diagnosis and treatment of PD are usually complex. There are some machine learning techniques that automate PD diagnosis and predict clinical scores. These techniques are promising in assisting assessment of stage of pathology and predicting PD progression. However, existing PD research mainly focuses on single-function model (i.e., only classification or prediction) using one modality, which limits performance. In this work, we propose a novel feature selection framework based on multi-modal neuroimaging data for joint PD detection and clinical score prediction. Specifically, a unique objective function is designed to capture discriminative features which are used to train a support vector regression (SVR) model for predicting clinical score (e.g., sleep scores and olfactory scores), and a support vector classification (SVC) model for class label identification. We evaluate our method using a dataset of 208 subjects, which includes 56 normal controls (NC), 123 PD and 29 scans without evidence of dopamine deficit (SWEDD) via a 10-fold cross-validation strategy. Our experimental results demonstrate that multi-modal data effectively improves the performance in disease status identification and clinical scores prediction as compared to one single modality. Comparative analysis reveals that the proposed method outperforms state-of-art methods. [ABSTRACT FROM AUTHOR]

Placental maturity staging is a challenging task due to complex imaging procedure, fetal and gestational age variations. To address this issue, we extract features not only from B-mode gray-scale ultrasound (US) images, but also from color Doppler energy (CDE) images. Based on these features, we propose a method to automatically determine the placental maturity by harnessing multi-view and multi-layout discriminative learning fusion. Specifically, we devise a multi-view technique to generate features of complementary information. Scale invariant features are extracted from image locally, and a Gaussian mixture model (GMM) is then applied to summarize the high-level information features. The clustering representatives from GMM are encoded via a multi-layout Fisher vector (MFV) instead of traditional Fisher vector (FV) to aggregate features based on their spatial information. We apply a multi-layout feature encoding method to improve the staging performance using discriminative learning technique. Extensive experimental results demonstrate that our method achieves promising performance in placental maturity staging and outperforms existing methods. [ABSTRACT FROM AUTHOR]

• We design a joint and deep learning framework to predict the clinical scores of AD. • We use the group LASSO and correntropy for dimension reduction via feature selection. • We explore the multi-layer independently recurrent neural network regression. • We predict the clinical score by learning relationship between MRI and clinical score. Alzheimer's disease (AD) is a progressive neurodegenerative disease that often grows in middle-aged and elderly people with the gradual loss of cognitive ability. Presently, there is no cure for AD. Furthermore, the current clinical diagnosis of AD is too time-consuming. In this paper, we design a joint and deep learning framework to predict clinical scores of AD. Specifically, the feature selection method combining group LASSO and correntropy is used to reduce dimensions and screen the features of brain regions related to AD. We explore the multi-layer independently recurrent neural network regression to study the internal connection between different brain regions and the time correlation between longitudinal data. The proposed joint deep learning network studies the relationship between the magnetic resonance imaging and clinical score, and predicts the clinical score. The predicted clinical score values allow doctors to perform early diagnosis and timely treatment of patients' disease condition. [ABSTRACT FROM AUTHOR]

• A network estimation method can automatically calibrate data quality and integrate modula prior. • A multi-task feature learning method is developed using multi-modal data. • A joint non-convex regularizer is designed for subspace learning. • Our method has achieved good automatic diagnosis and classification performance. Detection of early stages of Alzheimer's disease (AD) (i.e., mild cognitive impairment (MCI)) is important to maximize the chances to delay or prevent progression to AD. Brain connectivity networks inferred from medical imaging data have been commonly used to distinguish MCI patients from normal controls (NC). However, existing methods still suffer from limited performance, and classification remains mainly based on single modality data. This paper proposes a new model to automatically diagnosing MCI (early MCI (EMCI) and late MCI (LMCI)) and its earlier stages (i.e., significant memory concern (SMC)) by combining low-rank self-calibrated functional brain networks and structural brain networks for joint multi-task learning. Specifically, we first develop a new functional brain network estimation method. We introduce data quality indicators for self-calibration, which can improve data quality while completing brain network estimation, and perform correlation analysis combined with low-rank structure. Second, functional and structural connected neuroimaging patterns are integrated into our multi-task learning model to select discriminative and informative features for fine MCI analysis. Different modalities are best suited to undertake distinct classification tasks, and similarities and differences among multiple tasks are best determined through joint learning to determine most discriminative features. The learning process is completed by non-convex regularizer, which effectively reduces the penalty bias of trace norm and approximates the original rank minimization problem. Finally, the most relevant disease features classified using a support vector machine (SVM) for MCI identification. Experimental results show that our method achieves promising performance with high classification accuracy and can effectively discriminate between different sub-stages of MCI. Image, graphical abstract [ABSTRACT FROM AUTHOR]