BACKGROUND: MicroRNA (miRNA) has been shown to play a key role in the occurrence and progression of diseases, making uncovering miRNA-disease associations vital for disease prevention and therapy. However, traditional laboratory methods for detecting these associations are slow, strenuous, expensive, and uncertain. Although numerous advanced algorithms have emerged, it is still a challenge to develop more effective methods to explore underlying miRNA-disease associations. RESULTS: In the study, we designed a novel approach on the basis of deep autoencoder and combined feature representation (DAE-CFR) to predict possible miRNA-disease associations. We began by creating integrated similarity matrices of miRNAs and diseases, performing a logistic function transformation, balancing positive and negative samples with k-means clustering, and constructing training samples. Then, deep autoencoder was used to extract low-dimensional feature from two kinds of feature representations for miRNAs and diseases, namely, original association information-based and similarity information-based. Next, we combined the resulting features for each miRNA-disease pair and used a logistic regression (LR) classifier to infer all unknown miRNA-disease interactions. Under five and tenfold cross-validation (CV) frameworks, DAE-CFR not only outperformed six popular algorithms and nine classifiers, but also demonstrated superior performance on an additional dataset. Furthermore, case studies on three diseases (myocardial infarction, hypertension and stroke) confirmed the validity of DAE-CFR in practice. CONCLUSIONS: DAE-CFR achieved outstanding performance in predicting miRNA-disease associations and can provide evidence to inform biological experiments and clinical therapy.

Self-supervised learning (SSL) is a challenging task in sleep stage classification (SSC) that is capable of mining valuable representations from unlabeled data. However, traditional SSL methods typically focus on single-view learning and do not fully exploit the interactions among information across multiple views. In this study, we focused on a multi-domain view of the same EEG signal and developed a self-supervised multi-view representation learning framework via time series and time-frequency contrasting (MV-TTFC). In the MV-TTFC framework, we built-in a cross-domain view contrastive learning prediction task to establish connections between the temporal view and time-frequency (TF) view, thereby enhancing the information exchange between multiple views. In addition, to improve the quality of the TF view inputs, we introduced an enhanced multisynchrosqueezing transform, which can create high energy concentration TF image views to compensate for the inaccurate representations in traditional TF processing techniques. Finally, integrating temporal, TF, and fusion space contrastive learning effectively captured the latent features in EEG signals. We evaluated MV-TTFC based on two real-world SSC datasets (SleepEDF-78 and SHHS) and compared it with baseline methods in downstream tasks. Our method exhibited state-of-the-art performance, achieving accuracies of 78.64% and 81.45% with SleepEDF-78 and SHHS, respectively, and macro F1-scores of 70.39% with SleepEDF-78 and 70.47% with SHHS.

Motion estimation is a fundamental step in dynamic medical image processing for the assessment of target organ anatomy and function. However, existing image-based motion estimation methods, which optimize the motion field by evaluating the local image similarity, are prone to produce implausible estimation, especially in the presence of large motion. In addition, the correct anatomical topology is difficult to be preserved as the image global context is not well incorporated into motion estimation. In this study, we provide a novel motion estimation framework of dense-sparse-dense (DSD), which comprises two stages. In the first stage, we process the raw dense image to extract sparse landmarks to represent the target organ's anatomical topology, and discard the redundant information that is unnecessary for motion estimation. For this purpose, we introduce an unsupervised 3-D landmark detection network to extract spatially sparse but representative landmarks for the target organ's motion estimation. In the second stage, we derive the sparse motion displacement from the extracted sparse landmarks of two images of different time points. Then, we present a motion reconstruction network to construct the motion field by projecting the sparse landmarks' displacement back into the dense image domain. Furthermore, we employ the estimated motion field from our two-stage DSD framework as initialization and boost the motion estimation quality in light-weight yet effective iterative optimization. We evaluate our method on two dynamic medical imaging tasks to model cardiac motion and lung respiratory motion, respectively. Our method has produced superior motion estimation accuracy compared to the existing comparative methods. Besides, the extensive experimental results demonstrate that our solution can extract well-representative anatomical landmarks without any requirement of manual annotation. Our code is publicly available online: https://github.com/yyguo-sjtu/DSD-3D-Unsupervised-Landmark-Detection-Based-Motion-Estimation.

Object detection in remote sensing (RS) images is a challenging task because of complex background and multi-scale objects. Recently, much research has been devoted to improving detection accuracy, but they ignore the speed and memory size. In this letter, we introduce a light anchor-free detection model for resource-limited satellite devices trained with the proposed heatmap-saliency distillation (HSD) strategy, enhancing the performance of small models by learning teachers’ heatmaps in output layers and middle layers. On the one hand, the students mimic the teacher’s localization prediction of negative targets indicating the object shapes. On the other hand, saliency coefficient maps are generated by the ground truth heatmaps with rectangular masks to help students obtain features of multi-scale objects and local contexts across the complex background. Significantly, the model with a Res-9-256 backbone achieves 94.60% mAP on the NWPU VHR-10 dataset with only 8.5 MB of memory. And the test time of this tiny network performs 16.2 ms per image. Additional experiments are conducted on the DOTA dataset. Comprehensive evaluations demonstrate the effectiveness of our light anchor-free object detector trained with the HSD method.

Convolutional neural networks (CNNs) have been extensively used in remote sensing (RS) detection models. Although the memory size of detection models is massive, quantization can offer access to using these models in satellite embedded devices. However, for privacy reasons, institutions in charge of quantification operations may not obtain the original images. Based on this circumstance, current data-based quantization methods are no longer applicable, and data-free methods have poor performance for low-bit quantization. To address this problem, we propose a data-free quantization method for the CNN-based RS detection model. First, we use a generative adversarial network (GAN) to generate fake scene images. These images represent the global contextual information of each category. Second, we quantify the full-precision pretrained detection network. Finally, we train the quantized model to mimic the performance of the full-precision model by the proposed alternate training strategy with the generated fake scene images. We apply our method on CenterNet with a ResNet-18 backbone and evaluate the quantized model on the NWPU VHR-10 and DOTA datasets. The results show that our 5 bit quantized detection network obtains 94.1% mAP on NWPU VHR-10 and compresses the memory size to 0.158 times that of the full-precision network. Experiments verify that our data-free scene generation quantization algorithm maintains high performance with a large model compression ratio.