检索结果-内蒙古大学图书馆

Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qiu, Jingna Wilm, Frauke Öttl, Mathias Schlereth, Maja Liu, Chang Heimann, Tobias Aubreville, Marc Breininger, Katharina Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Pattern Recognition Lab Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Digital Technology and Innovation Siemens Healthineers Erlangen Germany Technische Hochschule Ingolstadt Ingolstadt Germany

The process of annotating histological gigapixel-sized whole slide images (WSIs) at the pixel level for the purpose of training a supervised segmentation model is time-consuming. Region-based active learning (AL) involves training the model on a limited number of annotated image regions instead of requesting annotations of the entire images. These annotation regions are iteratively selected, with the goal of optimizing model performance while minimizing the annotated area. The standard method for region selection evaluates the informativeness of all square regions of a specified size and then selects a specific quantity of the most informative regions. We find that the efficiency of this method highly depends on the choice of AL step size (i.e., the combination of region size and the number of selected regions per WSI), and a suboptimal AL step size can result in redundant annotation requests or inflated computation costs. This paper introduces a novel technique for selecting annotation regions adaptively, mitigating the reliance on this AL hyperparameter. Specifically, we dynamically determine each region by first identifying an informative area and then detecting its optimal bounding box, as opposed to selecting regions of a uniform predefined shape and size as in the standard method. We evaluate our method using the task of breast cancer metastases segmentation on the public CAMELYON16 dataset and show that it consistently achieves higher sampling efficiency than the standard method across various AL step sizes. With only 2.6% of tissue area annotated, we achieve full annotation performance and thereby substantially reduce the costs of annotating a WSI dataset. The source code is available at https://***/DeepMicroscopy/AdaptiveRegionSelection Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

Graph Neural Networks in Multi-Stained Pathological Imaging: Extended Comparative Analysis of Radiomic Features

学校读者我要写书评

暂无评论

Research Square

Research Square 2024年

作者： Monroy, Luis Carlos Rivera Rist, Leonhard Ostalecki, Christian Bauer, Andreas Vera, Julio Breininger, Katharina Maier, Andreas Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Martensstr. 3 Bayern Erlangen91058 Germany Department of Dermatology Universitätsklinikum Erlangen Hartmannstr. 14 Bayern Erlangen91052 Germany Department of Artificial Intelligence in Biomedical Engineering FAU Erlangen-Nürnberg Werner-von-Siemens Str. 61 Bayern Erlangen91052 Germany

Purpose: This study investigates Radiomics features for Graph Neural Networks (GNNs) in MELC pathology sample classification focusing on often misdiagnosed skin diseases. Methods: GNNs processing multiple pathological slides together as cell-level graphs are compared to XGBoost and Random Forest. The analysis assesses the use of MELC vs. Radiomics features, their dimensionality reduction with UMAP or tSNE and the graph connectivity based on spatial and feature closeness. Results: Integrating Radiomics features in a spatially connected graph markedly outperforms standard models when classifying pathologically similar diseases. Additionally, the UMAP dimensionality reduction techniques improves GNN classification performance. Conclusion: Radiomics, processed with GNNs, shows promise for multi-disease classification, enhancing diagnosis accuracy. Considering the potential, future research should extend these methods to a broader range of diseases. © 2024, CC BY.

关键词： Graph neural networks

Robust Augmentations for Small Object Detection of Aerial Images

学校读者我要写书评

暂无评论

Robust Augmentations for Small Object Detection of Aerial Im...

IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)

作者： Weiyu Xiong Zhanyu Ma Yi-Zhe Song Pattern Recognition and Intelligent Systems Lab School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Beijing Academy of Artificial Intelligence Beijing China SketchX CVSSP University of Surrey London United Kingdom

ISBN: (纸本)9781665405836

Object detection is one of the most fundamental but important computer vision tasks. However, small object detection remains an unsolved challenge due to insufficient detailed appearances and additional noises. Meanwhile, aerial images and intelligent transportation systems are under the restriction of difficulties such as dense object arrangement, a large number of small objects, and different perspectives, compared with natural images. To deal with these problems, an adversarial-like data augmentation training is proposed in this paper to narrow the data gap between remote sensing images and natural ones. The difficulty of the remote sensing object detection is verified and analyzed firstly by the classic single-stage anchor-based detector RetinaNet. Then, the multi-scale and data augmentations are introduced to alleviate the mismatch between general detector training and aerial images based on the anchor-free state-of-the-art (SOTA) model FCOS. Experiments on the remote sensing dataset, NWPU VHR10, demonstrate the quasi-antagonism data augmentation method improves the both anchor-based and anchor-free SOTA detectors for natural images with significant margins and shows the effectiveness on aerial images, especially small objects.

关键词： Training Image resolution Conferences Object detection Detectors Data models Noise measurement

Activating More Pixels in Image Super-Resolution Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Xiangyu Wang, Xintao Zhou, Jiantao Qiao, Yu Dong, Chao State Key Laboratory of Internet of Things for Smart City University of Macau China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China ARC Lab Tencent PCG China

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

Structured DropConnect for uncertainty inference in image classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zheng, Wenqing Xie, Jiyang Liu, Weidong Ma, Zhanyu Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China China Mobile Research Institute Beijing China Beijing Academy of Artificial Intelligence

With the complexity of the network structure, uncertainty inference has become an important task to improve classification accuracy for artificial intelligence systems. For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution. We introduce a DropConnect strategy on weights in the fully connected layers during training. In test, we split the network into several sub-networks, and then model the Dirichlet distribution by match its moments with the mean and variance of the outputs of these sub-networks. The entropy of the estimated Dirichlet distribution is finally utilized for uncertainty inference. In this paper, this framework is implemented on LeNet5 and VGG16 models for misclassification detection and out-of-distribution detection on MNIST and CIFAR-10 datasets. Experimental results show that the performance of the proposed SDC can be comparable to other uncertainty inference methods. Furthermore, the SDC is adapted well to different network structures with certain generalization capabilities and research *** Codes 14J60 (Primary) 14F05, 14J26 (Secondary) Copyright © 2021, The Authors. All rights reserved.

关键词： Image classification

Multi-level cancer profiling through joint cell-graph representations

学校读者我要写书评

暂无评论

Smart Health 2024年 32卷

作者： Rivera Monroy, Luis Carlos Rist, Leonhard Wilm, Frauke Ostalecki, Christian Baur, Andreas Vera, Julio Breininger, Katharina Maier, Andreas Pattern Recognition Lab - Friedrich-Alexander-Universität Erlangen-Nürnberg Martensstr. 3 Erlangen 91058 Germany Department of Dermatology - Universitätsklinikum Erlangen Hartmannstr. 14 Erlangen 91052 Germany Department of Artificial Intelligence in Biomedical Engineering - FAU Erlangen-Nürnberg Werner-von-Siemens Str. 61 Erlangen 91052 Germany

Computer-aided analysis of digitized pathology samples has significantly advanced with the rapid progression of machine and Deep Learning (DL) methods. However, most existing approaches primarily focus on features extracted from patches due to the large image sizes. This focus limits the ability of Convolutional Neural Networks (CNNs) to capture global information from the samples, resulting in an incomplete phenotypical and topological representation and thereby restricting the diagnostic capabilities of these methods. The recent emergence of Graph Neural Networks (GNNs) offers new opportunities to overcome these limitations through graph-driven representations of pathological samples. This work introduces a graph-based framework that encompasses diverse cancer types and integrates different imaging modalities. In this framework, histopathology samples are represented as graphs, and a pipeline facilitating cell-wise and disease classification is developed. The results support this motivation: for cell-wise classification, we achieved an average accuracy of 88%, and for disease-wise classification, an average accuracy of 83%, outperforming reference models such as XGBoost and standard CNNs. This approach not only provides flexibility in combining various diseases but also extends to integrating different staining techniques. © 2024 The Authors

关键词： Digital pathology Fluorescence microscopy image Graph deep learning Multiplex imaging

Automatic Classification of Neuromuscular Diseases in Children Using Photoacoustic Imaging

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Schlereth, Maja Stromer, Daniel Breininger, Katharina Wagner, Alexandra Tan, Lina Maier, Andreas Knieling, Ferdinand Department of Artificial Intelligence in Biomedical Engineering FAU Erlangen-Nürnberg Erlangen Germany Pattern Recognition Lab FAU Erlangen-Nürnberg Erlangen Germany Department of Pediatrics and Adolescent Medicine Universitätsklinik Erlangen FAU Erlangen-Nürnberg Erlangen Germany

Neuromuscular diseases (NMDs) cause a significant burden for both healthcare systems and society. They can lead to severe progressive muscle weakness, muscle degeneration, contracture, deformity and progressive disability. The NMDs evaluated in this study often manifest in early childhood. As subtypes of disease, e.g. Duchenne Muscular Dystropy (DMD) and Spinal Muscular Atrophy (SMA), are difficult to differentiate at the beginning and worsen quickly, fast and reliable differential diagnosis is crucial. Photoacoustic and ultrasound imaging has shown great potential to visualize and quantify the extent of different diseases. The addition of automatic classification of such image data could further improve standard diagnostic procedures. We compare deep learning-based 2-class and 3-class classifiers based on VGG16 for differentiating healthy from diseased muscular tissue. This work shows promising results with high accuracies above 0.86 for the 3-class problem and can be used as a proof of concept for future approaches for earlier diagnosis and therapeutic monitoring of NMDs. © 2022, CC BY-NC-SA.

关键词： Neurophysiology

Manual-Guided Dialogue for Flexible Conversational Agents

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Takanobu, Ryuichi Zhou, Hao Lin, Yankai Li, Peng Zhou, Jie Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Pattern Recognition Center WeChat AI Tencent Inc. China

How to build and use dialogue data efficiently, and how to deploy models in different domains at scale can be two critical issues in building a task-oriented dialogue system. In this paper, we propose a novel manual-guided dialogue scheme to alleviate these problems, where the agent learns the tasks from both dialogue and manuals. The manual is an unstructured textual document that guides the agent in interacting with users and the database during the conversation. Our proposed scheme reduces the dependence of dialogue models on fine-grained domain ontology, and makes them more flexible to adapt to various domains. We then contribute a fully-annotated multi-domain dataset MagDial to support our scheme. It introduces three dialogue modeling subtasks: instruction matching, argument filling, and response generation. Modeling these subtasks is consistent with the human agent’s behavior patterns. Experiments demonstrate that the manual-guided dialogue scheme improves data efficiency and domain scalability in building dialogue systems. The dataset and benchmark will be publicly available for promoting future research. © 2022, CC BY.

关键词： Speech processing

Low-Resolution Action recognition for Tiny Actions Challenge

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Boyu Qiao, Yu Wang, Yali ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and appear in a small resolution without much discriminative clue. Second, these activities are naturally distributed in a long-tailed way. It is hard to alleviate data bias for such heavy category imbalance. To tackle these problems, we propose a comprehensive recognition solution in this paper. First, we train video backbones with data balance, in order to alleviate overfitting in the challenge benchmark. Second, we design a dual-resolution distillation framework, which can effectively guide low-resolution action recognition by super-resolution knowledge. Finally, we apply model ensemble with post-processing, which can further boost performance on the long-tailed categories. Our solution ranks Top-1 on the leaderboard. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation