检索结果-内蒙古大学图书馆

Weakly-Supervised Learning via Multi-Lateral Decoder Branching for Tool Segmentation in Robot-Assisted Cardiovascular Catheterization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Omisore, Olatunji Mumini Akinyemi, Toluwanimi Nguyen, Anh Wang, Lei Research Center for Medical Robotics and Minimally Invasive Surgical Devices Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Smart Robotic Lab Department of Computer Science University of Liverpool United Kingdom

Robot-assisted catheterization has garnered a good attention for its potentials in treating cardiovascular diseases. However, advancing surgeon-robot collaboration still requires further research, particularly on task-specific automation. For instance, automated tool segmentation can assist surgeons in visualizing and tracking of endovascular tools during cardiac procedures. While learning-based models have demonstrated state-of-the-art segmentation performances, generating ground-truth labels for fully-supervised methods is both labor-intensive time consuming, and costly. In this study, we propose a weakly-supervised learning method with multi-lateral pseudo labeling for tool segmentation in cardiovascular angiogram datasets. The method utilizes a modified U-Net architecture featuring one encoder and multiple laterally branched decoders. The decoders generate diverse pseudo labels under different perturbations, augmenting available partial labels. The pseudo labels are self-generated using a mixed loss function with shared consistency across the decoders. The weakly-supervised model was trained end-to-end and validated using partially annotated angiogram data from three cardiovascular catheterization procedures. Validation results show that the model could perform closer to fully-supervised models. Also, the proposed weakly-supervised multi-lateral method outperforms three well known methods used for weakly-supervised learning, offering the highest segmentation performance across the three angiogram datasets. Furthermore, numerous ablation studies confirmed the model’s consistent performance under different parameters. Finally, the model was applied for tool segmentation in a robot-assisted catheterization experiments. The model enhanced visualization with high connectivity indices for guidewire and catheter, and a mean processing time of 35.26±11.29 ms per frame. This study provides a fast, stable and less expensive method for real-time tool segmentation and visua

关键词： Self-supervised learning

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

学校读者我要写书评

暂无评论

Augmented Box Replay: Overcoming Foreground Shift for Increm...

International Conference on computer vision (ICCV)

作者： Yuyang Liu Yang Cong Dipam Goswami Xialei Liu Joost van de Weijer State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences South China University of Technology Computer Vision Center Barcelona VCIP CS Nankai University Department of Computer Science Universitat Autònoma de Barcelona

In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model 1 .

关键词：

A Real- Time Multi-Camera Auto-Adjustment Framework for Infrastructure Inspections

学校读者我要写书评

暂无评论

A Real- Time Multi-Camera Auto-Adjustment Framework for Infr...

IEEE/SICE International Symposium on System Integration

作者： Chuong Phuoc Le Charles Ellison Steven Bunkley Hung La Anton Netchaev Department of Computer Science and Engineering Advanced Robotics and Automation (ARA) Lab University of Nevada Reno NV USA USACE Engineer Research and Development Center (ERDC) Information Technology Lab Vicksburg MS USA

In this paper, we proposed a novel multi-camera auto-adjustment framework for infrastructure inspections, specifically 3D point cloud mapping via lidar-camera fusion. Our method uses a single controller for consensus target brightness and adaptive lighting. In addition, a vignette correction filter was created to apply to images outputted from cameras to avoid dark strips on the point cloud data. This approach is designed to be a versatile, real-time friendly, and platform agnostic software stack.

关键词：

A Machine Learning Approach to Predicting Dry Eye-Related Signs, Symptoms and Diagnoses from Meibography Images

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Graham, Andrew D. Kothapalli, Tejasvi Wang, Jiayun Ding, Jennifer Tse, Vivien Asbell, Penny A. Yu, Stella X. Lin, Meng C. Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Vision Science Group University of California Berkeley United States Clinical Research Center School of Optometry University of California Berkeley United States Department of Bioengineering University of Memphis United States International Computer Science Institute Berkeley United States

Purpose: To use artificial intelligence to identify relationships between morphological characteristics of the Meibomian glands (MGs), subject factors, clinical outcomes, and subjective symptoms of dry eye. Methods: A total of 562 infrared meibography images were collected from 363 subjects (170 contact lens wearers, 193 non-wearers). Subjects were 67.2% female and were 54.8% Caucasian. Subjects were 18 years of age or older. A deep learning model was trained to take meibography as input, segment the individual MG in the images, and learn their detailed morphological features. Morphological characteristics were then combined with clinical and symptom data in prediction models of MG function, tear film stability, ocular surface health, and subjective discomfort and dryness. The models were analyzed to identify the most heavily weighted features used by the algorithm for predictions. Results: MG morphological characteristics were heavily weighted predictors for eyelid notching and vascularization, MG expressate quality and quantity, tear film stability, corneal staining, and comfort and dryness ratings, with accuracies ranging from 65% to 99%. Number of visible MG, along with other clinical parameters, were able to predict MG dysfunction, aqueous deficiency and blepharitis with accuracies ranging from 74% to 85%. Conclusions: Machine learning-derived MG morphological characteristics were found to be important in predicting multiple signs, symptoms, and diagnoses related to MG dysfunction and dry eye. This deep learning method illustrates the rich clinical information that detailed morphological analysis of the MGs can provide, and shows promise in advancing our understanding of the role of MG morphology in ocular surface health. © 2024, The Authors. All rights reserved.

关键词： Morphology

Leveraging Historical Medical Records as a Proxy via Multimodal Modeling and Visualization to Enrich Medical Diagnostic Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ouyang, Yang Wu, Yuchen Wang, He Zhang, Chenyang Cheng, Furui Jiang, Chang Jin, Lixia Cao, Yuanwu Li, Quan The School of Information Science and Technology ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging China The Department of Computer Science University of Illinois at Urbana-Champaign United States The Department of Computer Science ETH Zürich Switzerland Zhongshan Hospital Fudan University China

Simulation-based Medical Education (SBME) has been developed as a cost-effective means of enhancing the diagnostic skills of novice physicians and interns, thereby mitigating the need for resource-intensive mentor-apprentice training. However, feedback provided in most SBME is often directed towards improving the operational proficiency of learners, rather than providing summative medical diagnoses that result from experience and time. Additionally, the multimodal nature of medical data during diagnosis poses significant challenges for interns and novice physicians, including the tendency to overlook or over-rely on data from certain modalities, and difficulties in comprehending potential associations between modalities. To address these challenges, we present DiagnosisAssistant, a visual analytics system that leverages historical medical records as a proxy for multimodal modeling and visualization to enhance the learning experience of interns and novice physicians. The system employs elaborately designed visualizations to explore different modality data, offer diagnostic interpretive hints based on the constructed model, and enable comparative analyses of specific patients. Our approach is validated through two case studies and expert interviews, demonstrating its effectiveness in enhancing medical training. © 2023, CC BY.

关键词： Diagnosis

Convergent effects of peptides on the initiation of feeding motor programs in the mollusk Aplysia

学校读者我要写书评

暂无评论

Journal of Neurophysiology 2025年第5期133卷 1368-1379页

作者： Evans, Colin G. Barry, Michael A. Reaver, Carrie N. Patel, Paras R. Chestek, Cynthia A. Perkins, Matthew H. Jing, Jian Cropper, Elizabeth C. Department of Neuroscience Friedman Brain Institute Icahn School of Medicine at Mount Sinai New York NY United States Department of Biomedical Engineering Biointerfaces Institute University of Michigan Ann Arbor MI United States Department of Electrical Engineering and Computer Science Neurosciences Program Robotics Program University of Michigan Ann Arbor MI United States State Key Laboratory of Pharmaceutical Biotechnology Institute for Brain Sciences Chemistry and Biomedicine Innovation Center Jiangsu Engineering Research Center for MicroRNA Biology and Biotechnology Advanced Institute for Life Sciences School of Life Sciences Nanjing University Nanjing China

Neuropeptides configure the feeding network of Aplysia. For example, egestive activity is promoted by small cardioactive peptide (SCP), and ingestive activity is promoted by a combination of feeding circuit activating peptide (FCAP) and cerebral peptide 2 (CP-2). In addition, SCP and FCAP/CP-2 have a common network effect that does not contribute to motor program specification. They increase the excitability of an interneuron, B63. In this report, we further characterized the effects of peptides on B63. We performed voltage-clamp experiments and used a step protocol to look at steady-state currents. We found that SCP and FCAP/CP-2 both induced an inward current that was virtually absent in low-sodium saline. Previous work has established that B63 is unusual in the feeding circuit in that subthreshold depolarizations are autonomously generated that can trigger motor programs. Here, we show that this autonomous activity is more frequent in the presence of peptides. Previous studies have also shown that activity of the feeding central pattern generator (CPG) can be initiated by neurons that excite B63, e.g., by cerebral buccal interneuron 2 (CBI-2), a projection neuron that triggers biting-like motor programs. Here, we show that the latency of CBI-2-induced activity is decreased by stimulation of the esophageal nerve (EN) (which releases endogenous SCP). These results, taken together with previous results, indicate that peptides that act divergently to configure network activity additionally act convergently to promote motor program induction. We present data that suggest that this arrangement facilitates brief switches between ingestive and egestive motor activity. © 2025 The Authors.

关键词： central pattern generator invertebrate modulation motor program neuropeptide

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Goswami, Dipam Liu, Yuyang Twardowski, Bartlomiej van de Weijer, Joost Department of Computer Science Universitat Autònoma de Barcelona Spain Computer Vision Center Barcelona Spain University of Chinese Academy of Sciences China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM. © 2023, CC BY.

关键词： Normal distribution

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

International Journal of computer vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

S3-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Gui Li, Yuexiang Chen, Wenting Ding, Meidan Cheah, Wooi Ping Qu, Rong Ren, Jianfeng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen China School of Computer Science University of Nottingham Ningbo China Zhejiang Ningbo China Group University Engineering Research Center of Digital Medicine and Healthcare Guangxi Medical University Guangxi Nanning China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong School of Computer Science University of Nottingham Nottingham United Kingdom

Small lesions play a critical role in early disease diagnosis and intervention of severe infections. Popular models often face challenges in segmenting small lesions, as it occupies only a minor portion of an image, while down sampling operations may inevitably lose focus on local features of small lesions. To tackle the challenges, we propose a Small-Size-Sensitive Mamba (S3-Mamba), which promotes the sensitivity to small lesions across three dimensions: channel, spatial, and training strategy. Specifically, an Enhanced Visual State Space block is designed to focus on small lesions through multiple residual connections to preserve local features, and selectively amplify important details while suppressing irrelevant ones through channel-wise attention. A Tensor-based Cross-feature Multi-scale Attention is designed to integrate input image features and intermediate-layer features with edge features and exploit the attentive support of features across multiple scales, thereby retaining spatial details of small lesions at various granularities. Finally, we introduce a novel regularized curriculum learning to automatically assess lesion size and sample difficulty, and gradually focus from easy samples to hard ones like small lesions. Extensive experiments on three medical image segmentation datasets show the superiority of our S3-Mamba, especially in segmenting small lesions. Our code is available at https://***/ErinWang2023/S3-Mamba. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation