Active learning effectively reduces annotation costs while enhancing model performance in medical image segmentation tasks. One-shot active learning presents a highly practical scenario where valuable samples for annotation are selected in a single round. However, current one-shot active learning methods predominantly rely on sampling selection methods based on global information. In contrast, focusing on the selection of features specific to local lesion regions would be more targeted and effective. In this work, we introduce a novel deep active learning framework specifically designed for pathological lesion segmentation tasks. To enable the model to effectively capture lesion-related regions of interest, we propose a strong augmentation strategy for image samples in self-supervised contrastive training. These strong augmentation samples are generated through cluster-based background subtraction using cluster projector, thereby emphasizing the features of the target lesion and improving the model's sensitivity to these areas. We utilize the Segment Anything Model as the base model to facilitate training and sample selection in a one-shot manner. Experimental results on two lesion segmentation datasets demonstrate that the proposed framework outperforms several existing active learning methods.

The Segment Anything Model (SAM), serving as a foundational vision model, has demonstrated an extraordinary capability in segmenting natural images. However, its efficacy in the domain of medical image analysis leaves much to be desired, primarily due to the irregular shapes and indistinct edges characteristic of lesions. There is a pressing need to augment SAM’s proficiency in recognizing lesion boundaries. Achieving precise segmentation of such lesions requires a blend of high-level global semantic information and low-level local boundary details. In response to this challenge, we introduce an auxiliary boundary-aware Convolutional Neural Network (CNN) module, equipped with a boundary generator, to enhance the model’s focus on boundary feature extraction. Furthermore, to leverage both the intricate low-level features in the lower layers and the high-level textural features in the deeper layers, we employ feature adapters to fuse the multi-scale features derived from the SAM encoder, thereby aggregating a wealth of enriched information. The performance superiority of our model is demonstrated through comprehensive evaluation on three different medical image segmentation tasks, and experimental results highlight the effectiveness of our proposed model.

The impairment of sperm maturation is one of the major pathogenic factors in male subfertility, a serious medical and social problem affecting millions of global couples. Regrettably, the existing research on sperm maturation is slow, limited, and fragmented, largely attributable to the lack of a global molecular view. To fill the data gap, we newly established a database, namely the Sperm Maturation Database (SperMD, http://bio-add.org/SperMD ). SperMD integrates heterogeneous multi-omics data (170 transcriptomes, 91 proteomes, and five human metabolomes) to illustrate the transcriptional, translational, and metabolic manifestations during the entire lifespan of sperm maturation. These data involve almost all crucial scenarios related to sperm maturation, including the tissue components of the epididymal microenvironment, cell constituents of tissues, different pathological states, and so on. To the best of our knowledge, SperMD could be one of the limited repositories that provide focused and comprehensive information on sperm maturation. Easy-to-use web services are also implemented to enhance the experience of data retrieval and molecular comparison between humans and mice. Furthermore, the manuscript illustrates an example application demonstrated to systematically characterize novel gene functions in sperm maturation. Nevertheless, SperMD undertakes the endeavor to integrate the islanding omics data, offering a panoramic molecular view of how the spermatozoa gain full reproductive abilities. It will serve as a valuable resource for the systematic exploration of sperm maturation and for prioritizing the biomarkers and targets for precise diagnosis and therapy of male subfertility.

Typically, synthetic aperture radar (SAR) utilizes linear frequency modulation (LFM) signal to acquire high-resolution images, requiring spectral windowing to suppress sidelobes while sacrificing signal-to-noise ratio (SNR). In contrast to LFM signal, nonlinear frequency modulation (NLFM) signal can reconstruct the signal power spectral density (PSD) without sacrificing SNR, providing autocorrelation outputs with lower sidelobes. Despite the excellent application potential of NLFM signal, the real-time generation of NLFM faces numerous challenges due to the high complexity of the systems involved and constraints imposed by waveform generator devices. In this letter, a low-complexity, high-precision and high-resolution intermediate-frequency NLFM signal generation device is developed, requiring only eleven parameters to generate real-time NLFM signal of arbitrary time width and bandwidth, with a maximum bandwidth reaching 1.2 GHz. This NLFM signal generator will be employed in the unmanned aerial vehicle (UAV) SAR system. Finally, the performance of the NLFM signal generator has been validated through ground experimental results.

Coronavirus disease-2019 (COVID-19) as a new pneumonia which is extremely infectious, the classification of this coronavirus is essential to effectively control the development of the epidemic. Pathological changes in the chest computed tomography (CT) scans are often used as one of the diagnostic criteria of COVID-19. Meanwhile, deep learning-based transfer learning is currently an effective strategy for computer-aided diagnosis (CAD). To further improve the performance of deep transfer learning model used for COVID-19 classification with CT images, in this article, we propose a hybrid model combined with a semi-supervised domain adaption model and extreme learning machine (ELM) classifier, and the application of a novel multikernel correntropy induced loss function in transfer learning is also presented. The proposed model is evaluated on open-source datasets. The experimental results are compared to some baseline models to verify the effectiveness, while adopting accuracy, precision, recall,$F_{1}$score and area under curve (AUC) as the evaluation metrics. Experimental results show that the proposed method improves the performance of original model and is more suitable for CT images analysis.

Research on orthodontic treatment monitoring from oralscan video is a new direction in dental digitalization. We designed an approach to reconstruct, segment, and estimate the pose of individual teeth to measure orthodontic treatment. To handle the semantic gap in heterogeneous data on the condition that they are combined linearly, we present a multimedia interaction network (MIN) to combine heterogeneous information in point cloud segmentation by extending the graph attention mechanism. Moreover, a structure-aware quadruple loss is designed to explore the relation between multiple and diverse unmatched points in point cloud registration. The performance of our approach is evaluated on multiple tooth registration datasets, and extensive experiments show that our approach improves the accuracy by a margin of 1.4% in the inlier ratio on the Aoralscan3 dataset when it is compared with prevailing approaches.

In vehicle retrieval, the vehicle patch should first be localized to remove the irrelevant background information. Moreover, the negative samples are much more prevalent than the positive samples, and the information from the negative samples is not fully exploited in the triple loss. What we need is a way to incorporate global knowledge and structure information to address these two issues. Therefore, we introduce a local-global context network for landmark alignment to update the predicted results by using the semantic information and the local compatibility and propose a structure-aware quadruple loss to use multiple and diverse negative samples in retrieval. Experiments on the VehicleID and the ENJOYOR vehicle retrieval datasets demonstrate that our approach obtains accuracy comparable to state-of-the-art approaches in vehicle retrieval.

With the popularization of computer-aided diagnosis (CAD) technologies, more and more deep learning methods are developed to facilitate the detection of ophthalmic diseases. In this article, the deep learning-based detections for some common eye diseases, including cataract, glaucoma, and age-related macular degeneration (AMD), are analyzed. Generally speaking, morphological change in retina reveals the presence of eye disease. Then, while using some existing deep learning methods to achieve this analysis task, the satisfactory performance may not be given, since fundus images usually suffer from the impact of data imbalance and outliers. It is, therefore, expected that with the exploration of effective and robust deep learning algorithms, the detection performance could be further improved. Here, we propose a deep learning model combined with a novel mixture loss function to automatically detect eye diseases, through the analysis of retinal fundus color images. Specifically, given the good generalization and robustness of focal loss and correntropy-induced loss functions in addressing complex dataset with class imbalance and outliers, we present a mixture of those two losses in deep neural network model to improve the recognition performance of classifier for biomedical data. The proposed model is evaluated on a real-life ophthalmic dataset. Meanwhile, the performance of deep learning model with our proposed loss function is compared with the baseline models, while adopting accuracy, sensitivity, specificity, Kappa, and area under the receiver operating characteristic curve (AUC) as the evaluation metrics. The experimental results verify the effectiveness and robustness of the proposed algorithm.

Traffic sign detection plays an important role in intelligent transportation systems. But traffic signs are still not well-detected by deep convolution neural network-based methods because the sizes of their feature maps are constrained, and the environmental context information has not been fully exploited by other researchers. What we need is a way to incorporate relevant context detail from the neighboring layers into the detection architecture. We have developed a novel traffic sign detection approach based on recurrent attention for multi-scale analysis and use of local context in the image. Experiments on the German traffic sign detection benchmark and the Tsinghua-Tencent 100K data set demonstrated that our approach obtained an accuracy comparable to the state-of-the-art approaches in traffic sign detection.

This paper presents a notion of location-sensitive online-offline hybrid social system. What makes it distinct from other mobile social media is that it supports not simply online interaction but also online-offline hybrid interaction, and location sensitivity is a feature designed to lower cost for users to participant in offline activities. We designed and implemented a prototype mobile Application called USee, and danmaku - an emerging socio-digital paradigm, was employed as the main user interface. We introduce the design and implementation of USee, and conduct a preliminary study to understand how it works in reality. Findings of the preliminary study suggest promises of the notion of location-sensitive online-offline hybrid social system. We highlight that USee provides users a free and safe social place, in which users express high and unique enthusiasm and engagement. This paper contributes to provide meaningful insights and design implication to mobile social media.

Constrained spectral clustering (CSC) algorithms have shown great promise in significantly improving clustering accuracy by encoding side information into spectral clustering algorithms. However, existing CSC algorithms are inefficient in handling moderate and large datasets. In this paper, we aim to develop a scalable and efficient CSC algorithm by integrating sparse coding based graph construction into a framework called constrained normalized cuts. To this end, we formulate a scalable constrained normalized-cuts problem and solve it based on a closed-form mathematical analysis. We demonstrate that this problem can be reduced to a generalized eigenvalue problem that can be solved very efficiently. We also describe a principled k-way CSC algorithm for handling moderate and large datasets. Experimental results over benchmark datasets demonstrate that the proposed algorithm is greatly cost-effective, in the sense that (1) with less side information, it can obtain significant improvements in accuracy compared to the unsupervised baseline; (2) with less computational time, it can achieve high clustering accuracies close to those of the state-of-the-art.