Multimodal medical image fusion aims to integrate complementary information from different modalities of medical images. Deep learning methods, especially recent vision Transformers, have effectively improved image fusion performance. However, there are limitations for Transformers in image fusion, such as lacks of local feature extraction and cross-modal feature interaction, resulting in insufficient multimodal feature extraction and integration. In addition, the computational cost of Transformers is higher. To address these challenges, in this work, we develop an adaptive cross-modal fusion strategy for unsupervised multimodal medical image fusion. Specifically, we propose a novel lightweight cross Transformer based on cross multi-axis attention mechanism. It includes cross-window attention and cross-grid attention to mine and integrate both local and global interactions of multimodal features. The cross Transformer is further guided by a spatial adaptation fusion module, which allows the model to focus on the most relevant information. Moreover, we design a special feature extraction module that combines multiple gradient residual dense convolutional and Transformer layers to obtain local features from coarse to fine and capture global features. The proposed strategy significantly boosts the fusion performance while minimizing computational costs. Extensive experiments, including clinical brain tumor image fusion, have shown that our model can achieve clearer texture details and better visual quality than other state-of-the-art fusion methods.

This paper presents a multistage SSA method to denoise a signal efficiently and adaptively. The multistage SSA is to apply basic SSA recursively toward the noisy signal. Therefore, the noise dominated components will be extracted out from the noisy signal stage by stage. However, the denoised signal is still noisy if the number of stages is small. On the other hand, after all the noise dominated components have been extracted out by enough number of stages, some signal dominated components begin to be moved into the noise group as the multistage SSA based denoising proceeds. An adaptive criterion based on correlation measure is proposed to terminate the multistage SSA based denoising algorithm in order to prevent moving the signal dominated components into the noise group. The multistage SSA based denoising algorithm is efficient since the window length is selected as a small positive integer in every stage. Also, the adaptive stop criterion makes the proposed method avoid inappropriate parameter selection effectively. Computer numerical simulation results show that the proposed method has better denoising performance towards different test signals under different noise levels as well as needs less processing time when compared to the conventional SSA denoising method.

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to represent novel classes. The correlation-based methods lack the ability to consider interaction of the two subspace matching scores due to the inherent nature of the real-valued 2D convolutions. In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra. Specifically, our QCLNet is formulated as a hyper-complex valued network and represents correlation tensors in the quaternion domain, which uses quaternion-valued convolution to explore the external relations of query subspace when considering the hidden relationship of the support sub-dimension in the quaternion space. Extensive experiments on the PASCAL-5 ⁱ and COCO-20 ⁱ datasets demonstrate that our method outperforms the existing state-of-the-art methods effectively.

This paper proposes a strategy for suppressing noise via empirical mode decomposition (EMD) based hierarchical multiresolution analysis. First, an intrinsic mode function (IMF) index that can differentiate the noise dominant IMFs and the information dominant IMFs in the first level of decomposition is determined by the conventional EMD based denoising method. Next, the EMD is applied to those discarded IMFs in the first level of decomposition to obtain the IMFs in the second level of decomposition. Then, the detrended fluctuation analysis (DFA) is employed to define the IMF index separating the noise dominant IMFs and the information dominant IMFs in the second level of decomposition. Information dominant IMFs in both the first and the second level of decompositions are summed together to obtain denoised signal. The study is limited to signals that were corrupted by additive white Gaussian noise (AWGN). Extensive computer numerical simulations are conducted on both synthetic signals and practical signals. The results show that our proposed method is promising in some cases especially at high input SNR levels. For example, in the case of the CH4 signal with 12dB input SNR, the processed SNR based on our proposed strategy with the consecutive mean squared error (CMSE) is 23.27dB, while that based on the conventional CMSE method is only 23.14dB. Also, our proposed method can extract information from more than one level of decomposition to reconstruct the denoised signal compared to only one level of decomposition in the conventional EMD based denoising method.

Although sparse multinomial logistic regression (SMLR) has provided a useful tool for sparse classification, it suffers from inefficacy in dealing with high dimensional features and manually set initial regressor values. This has significantly constrained its applications for hyperspectral image (HSI) classification. In order to tackle these two drawbacks, an extreme sparse multinomial logistic regression (ESMLR) is proposed for effective classification of HSI. First, the HSI dataset is projected to a new feature space with randomly generated weight and bias. Second, an optimization model is established by the Lagrange multiplier method and the dual principle to automatically determine a good initial regressor for SMLR via minimizing the training error and the regressor value. Furthermore, the extended multi-attribute profiles (EMAPs) are utilized for extracting both the spectral and spatial features. A combinational linear multiple features learning (MFL) method is proposed to further enhance the features extracted by ESMLR and EMAPs. Finally, the logistic regression via the variable splitting and the augmented Lagrangian (LORSAL) is adopted in the proposed framework for reducing the computational time. Experiments are conducted on two well-known HSI datasets, namely the Indian Pines dataset and the Pavia University dataset, which have shown the fast and robust performance of the proposed ESMLR framework.

This paper proposes a framework combining the complementary ensemble empirical mode decomposition with both the independent component analysis and the non-negative matrix factorization for estimating both the heart rate and the respiratory rate from the photoplethysmography (PPG) signal. After performing the complementary ensemble empirical mode decomposition on the PPG signal, a finite number of intrinsic mode functions are obtained. Then, these intrinsic mode functions are divided into two groups to perform the further analysis via both the independent component analysis and the non-negative matrix factorization. The surrogate cardiac signal related to the heart activity and another surrogate respiratory signal related to the respiratory activity are reconstructed to estimate the heart rate and the respiratory rate, respectively. Finally, different records of signals acquired from the Medical Information Mart for Intensive Care database downloaded from the Physionet Automated Teller Machine (ATM) data bank are employed for demonstrating the outperformance of our proposed method. The results show that our proposed method outperforms both the digital filtering approach and the conventional empirical mode decomposition based methods in terms of reconstructing both the surrogate cardiac signal and the respiratory signal from the PPG signal as well as both achieving the higher accuracy and the higher reliability for estimating both the heart rate and the respiratory rate.