Search

Humans can easily distinguish the known and unknown categories and can recognize the unknown object by learning it once instead of repeating it many times without forgetting the learned object. Hence, we aim to make deep learning models simulate the way people learn. We refer to such a learning manner as OnLine Open World Object Detection(OLOWOD). Existing OWOD approaches pay more attention to the identification of unknown categories, while the incremental learning part is also very important. Besides, some neuroscience research shows that specific noises allow the brain to form new connections and neural pathways which may improve learning speed and efficiency. In this paper, we take the dual-level information of old samples as perturbations on new samples to make the model good at learning new knowledge without forgetting the old knowledge. Therefore, we propose a simple plug-and-play method, called Brain-inspired Streaming Dual-level Perturbations(BSDP), to solve the OLOWOD problem. Specifically, (1) we first calculate the prototypes of previous categories and use the distance between samples and the prototypes as the sample selecting strategy to choose old samples for replay; (2) then take the prototypes as the streaming feature-level perturbations of new samples, so as to improve the plasticity of the model through revisiting the old knowledge; (3) and also use the distribution of the features of the old category samples to generate adversarial data in the form of streams as the data-level perturbations to enhance the robustness of the model to new categories. We empirically evaluate BSDP on PASCAL VOC and MS-COCO, and the excellent results demonstrate the promising performance of our proposed method and learning manner., Comment: 29 pages, 12 figures

Generating radiology reports automatically reduces the workload of radiologists and helps the diagnoses of specific diseases. Many existing methods take this task as modality transfer process. However, since the key information related to disease accounts for a small proportion in both image and report, it is hard for the model to learn the latent relation between the radiology image and its report, thus failing to generate fluent and accurate radiology reports. To tackle this problem, we propose a memory-based cross-modal semantic alignment model (MCSAM) following an encoder-decoder paradigm. MCSAM includes a well initialized long-term clinical memory bank to learn disease-related representations as well as prior knowledge for different modalities to retrieve and use the retrieved memory to perform feature consolidation. To ensure the semantic consistency of the retrieved cross modal prior knowledge, a cross-modal semantic alignment module (SAM) is proposed. SAM is also able to generate semantic visual feature embeddings which can be added to the decoder and benefits report generation. More importantly, to memorize the state and additional information while generating reports with the decoder, we use learnable memory tokens which can be seen as prompts. Extensive experiments demonstrate the promising performance of our proposed method which generates state-of-the-art performance on the MIMIC-CXR dataset., Comment: 12 pages, 8 figures

Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. Compared to standard object detection, the OWOD setting is task to: 1) detect objects seen during training while identifying unseen classes, and 2) incrementally learn the knowledge of the identified unknown objects when the corresponding annotations is available. We propose a novel and efficient OWOD solution from a prototype perspective, which we call OCPL: Open-world object detection via discriminative Class Prototype Learning, which consists of a Proposal Embedding Aggregator (PEA), an Embedding Space Compressor (ESC) and a Cosine Similarity-based Classifier (CSC). All our proposed modules aim to learn the discriminative embeddings of known classes in the feature space to minimize the overlapping distributions of known and unknown classes, which is beneficial to differentiate known and unknown classes. Extensive experiments performed on PASCAL VOC and MS-COCO benchmark demonstrate the effectiveness of our proposed method., Comment: 4 pages, 3 figures, ICIP2022

Gait recognition is a promising biometric technology for identification due to its non-invasiveness and long-distance. However, external variations such as clothing changes and viewpoint differences pose significant challenges to gait recognition. Silhouette-based methods preserve body shape but neglect internal structure information, while skeleton-based methods preserve structure information but omit appearance. To fully exploit the complementary nature of the two modalities, a novel triple branch gait recognition framework, TriGait, is proposed in this paper. It effectively integrates features from the skeleton and silhouette data in a hybrid fusion manner, including a two-stream network to extract static and motion features from appearance, a simple yet effective module named JSA-TC to capture dependencies between all joints, and a third branch for cross-modal learning by aligning and fusing low-level features of two modalities. Experimental results demonstrate the superiority and effectiveness of TriGait for gait recognition. The proposed method achieves a mean rank-1 accuracy of 96.0% over all conditions on CASIA-B dataset and 94.3% accuracy for CL, significantly outperforming all the state-of-the-art methods. The source code will be available at https://github.com/feng-xueling/TriGait/., Comment: Accepted by IJCB 2023

Wei Sun,* Liyan Ma,* Yana Li, Ying Xu, Jingjuan Wei, Lei Sa, Xinxin Chen, Jianrong Su Department of Clinical Laboratory, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People’s Republic of China*These authors contributed equally to this workCorrespondence: Jianrong Su, Department of Clinical Laboratory, Beijing Friendship Hospital, Capital Medical University, No. 95, Yong’an Road, Xicheng District, Beijing, 100050, People’s Republic of China, Email youyilab@163.comObjective: This study aimed to investigate the antimicrobial susceptibilities, drug resistance mechanisms, and biofilm formation capacities of non-diphtheriae Corynebacterium strains isolated from sterile midstream urine of hospitalized patients with clinical urinary tract infections (UTIs).Methods: A total of 45 non-diphtheriae Corynebacterium isolates were recovered from sterile midstream urine. The available data of 45 patients were collected. Minimum inhibitory concentrations (MICs) of 10 commonly used antibiotics were determined. Meanwhile, the molecular resistance mechanisms of each agent were performed through PCR with specific primers. Moreover, the biofilm formation capability of each isolate on abiotic surfaces was detected with the MTT method.Results: In this study, the most prevalent three species were C. striatum (15/45, 33.3%), C. glucuronolyticum (9/45, 20.0%) and C. urealyticum (8/45, 17.8%). These three species also accounted for most renal and ureteral calculi cases. Male patients older than 50 years, especially those with underlying diseases, were more susceptible to non-diphtheriae Corynebacterium infection. All the 45 isolates were 100% susceptible to vancomycin and linezolid, but highly resistant to macrolide–lincosamide–streptogramin B (MLSB), fluoroquinolones, tetracyclines and β-lactams with corresponding mechanisms. The detection rate of multidrug–resistant (MDR) non-diphtheriae Corynebacterium is 91.1%. All isolates

Shuai Xia,1 Liyan Ma,2 Guoxing Wang,1 Jie Yang,1 Meiying Zhang,3 Xuechen Wang,1 Jianrong Su,2 Miaorong Xie1 1Department of Emergency and Critical Care Center, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People’s Republic of China; 2Department of Clinical Laboratory, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People’s Republic of China; 3Department of Emergency Center, Peking University First Hospital, Peking University, Beijing, 100050, People’s Republic of ChinaCorrespondence: Miaorong Xie, Department of Emergency and Critical Care, Center, Beijing Friendship Hospital, Capital Medical University, No. 95, Yong’an Road, Xicheng District, Beijing, 100050, People’s Republic of China, Email xiemiao27@126.com View the original paper by Mr Xia and colleagues This is in response to the Letter to the Editor

Shuai Xia,1,* Liyan Ma,2,* Guoxing Wang,1 Jie Yang,1 Meiying Zhang,3 Xuechen Wang,1 Jianrong Su,2 Miaorong Xie1 1Department of Emergency and Critical Care Center, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People’s Republic of China; 2Department of Clinical Laboratory, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People’s Republic of China; 3Department of Emergency Center, Peking University First Hospital, Peking University, Beijing, 100050, People’s Republic of China*These authors contributed equally to this workCorrespondence: Jianrong Su, Department of Clinical Laboratory, Beijing Friendship Hospital, Capital Medical University, No. 95, Yong’an Road, Xicheng District, Beijing, 100050, People’s Republic of China, Email youyilab@163.com Miaorong Xie, Department of Emergency and Critical Care Center, Beijing Friendship Hospital, Capital Medical University, No. 95, Yong’an Road, Xicheng District, Beijing, 100050, People’s Republic of China, Email xiemiao27@126.comPurpose: To investigate the antimicrobial activity of berberine and the mechanism by which it combats methicillin-resistant Staphylococcus aureus (MRSA) strains isolated from patients with bloodstream infections.Methods: Fifteen clinical MRSA isolates were collected, and their Multi-locus Sequence Types (MLST) were examined. The minimum inhibitory concentration (MIC) and combined antibacterial activity of berberine alone, and when combined with clindamycin and rifampicin separately, were determined. Additionally, two MRSA strains (ST239 and ST5) were selected to perform the time-killing assay and biofilm formation test. Cell wall alterations and cell membrane integrity were measured by confocal laser scanning microscopy (CLSM) and electron microscopy to assess the influence on cell morphology.Results: Our data showed berberine was effective against MRSA at MIC values varying from

Baoya Wang,1 Wenjuan Dong,2 Liyan Ma,3 Yonghui Dong,4 Shanmei Wang,1 Youhua Yuan,1 Qiong Ma,1 Junhong Xu,1 Wenjuan Yan,1 Jing Nan,1 Qi Zhang,1 Wenbo Xu,1 Bing Ma,1 Yafei Chu,1 Jiangfeng Zhang,1 Li Li,1 Yi Li1 1Department of Clinical Microbiology, Henan Provincial People’s Hospital, People’s Hospital of Zhengzhou University, and People’s Hospital of Henan University, Zhengzhou, 450003, Henan, People’s Republic of China; 2Department of Clinical Microbiology, Xicheng District Pingan Hospital, Beijing, 100035, People’s Republic of China; 3Department of Clinical Microbiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, People’s Republic of China; 4Department of Osteology, Henan Provincial People’s Hospital, People’s Hospital of Zhengzhou University, and People’s Hospital of Henan University, Zhengzhou, 450003, Henan, People’s Republic of ChinaCorrespondence: Yi Li; Li LiDepartment of Clinical Microbiology, Henan Provincial People’s Hospital, People’s Hospital of Zhengzhou University, and People’s Hospital of Henan University, Weiwu Road 5, Zhengzhou, 450003, Henan, People’s Republic of ChinaTel +8637165580484Fax +8637187160318Email liyilabmed@henu.edu.cn; hnykylili@126.comObjective: This study aimed to investigate the prevalence, genetic diversity and clinical characteristics of Clostridium perfringens isolates from hospitalized clinical diarrheal patients.Methods: A prospective study was conducted on 1108 patients with diarrhea during hospitalization. Stool samples were cultured for C. perfringens, and the toxin genes were detected by PCR. The available clinical data of 112 patients were analyzed to study the clinical features of various isolates. Multi-locus sequence typing (MLST) was performed to assess phylogenetic relationship between different isolates.Results: A total of 153 (13.8%) isolates were obtained from patients’ stools. C. perfringens type F (49.0%) was the major toxin type in the isolates, follow

Diabetic retinopathy (DR) is one of the leading causes of blindness. However, no specific symptoms of early DR lead to a delayed diagnosis, which results in disease progression in patients. To determine the disease severity levels, ophthalmologists need to focus on the discriminative parts of the fundus images. In recent years, deep learning has achieved great success in medical image analysis. However, most works directly employ algorithms based on convolutional neural networks (CNNs), which ignore the fact that the difference among classes is subtle and gradual. Hence, we consider automatic image grading of DR as a fine-grained classification task, and construct a bilinear model to identify the pathologically discriminative areas. In order to leverage the ordinal information among classes, we use an ordinal regression method to obtain the soft labels. In addition, other than only using a categorical loss to train our network, we also introduce the metric loss to learn a more discriminative feature space. Experimental results demonstrate the superior performance of the proposed method on two public IDRiD and DeepDR datasets., Comment: 5 pages

To solve the red jujube classification problem, this paper designs a convolutional neural network model with low computational cost and high classification accuracy. The architecture of the model is inspired by the multi-visual mechanism of the organism and DenseNet. To further improve our model, we add the attention mechanism of SE-Net. We also construct a dataset which contains 23,735 red jujube images captured by a jujube grading system. According to the appearance of the jujube and the characteristics of the grading system, the dataset is divided into four classes: invalid, rotten, wizened and normal. The numerical experiments show that the classification accuracy of our model reaches to 91.89%, which is comparable to DenseNet-121, InceptionV3, InceptionV4, and Inception-ResNet v2. However, our model has real-time performance.