检索结果-内蒙古大学图书馆

Unsupervised many-to-many stain translation for histological image augmentation to improve classification accuracy

学校读者我要写书评

暂无评论

Journal of Pathology Informatics 2023年 14卷 100195-100195页

作者： Berijanian, Maryam Schaadt, Nadine S. Huang, Boqiang Lotz, Johannes Feuerhake, Friedrich Merhof, Dorit Department of Computational Mathematics Science and Engineering (CMSE) Michigan State University East Lansing United States Institute for Pathology Hannover Medical School Hannover Germany Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Lübeck Germany Institute for Neuropathology University Clinic Freiburg Freiburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Background: Deep learning tasks, which require large numbers of images, are widely applied in digital pathology. This poses challenges especially for supervised tasks since manual image annotation is an expensive and laborious process. This situation deteriorates even more in the case of a large variability of images. Coping with this problem requires methods such as image augmentation and synthetic image generation. In this regard, unsupervised stain translation via GANs has gained much attention recently, but a separate network must be trained for each pair of source and target domains. This work enables unsupervised many-to-many translation of histopathological stains with a single network while seeking to maintain the shape and structure of the tissues. Methods: StarGAN-v2 is adapted for unsupervised many-to-many stain translation of histopathology images of breast tissues. An edge detector is incorporated to motivate the network to maintain the shape and structure of the tissues and to have an edge-preserving translation. Additionally, a subjective test is conducted on medical and technical experts in the field of digital pathology to evaluate the quality of generated images and to verify that they are indistinguishable from real images. As a proof of concept, breast cancer classifiers are trained with and without the generated images to quantify the effect of image augmentation using the synthetized images on classification accuracy. Results: The results show that adding an edge detector helps to improve the quality of translated images and to preserve the general structure of tissues. Quality control and subjective tests on our medical and technical experts show that the real and artificial images cannot be distinguished, thereby confirming that the synthetic images are technically plausible. Moreover, this research shows that, by augmenting the training dataset with the outputs of the proposed stain translation method, the accuracy of breast cancer classifie

关键词： Adversarial networks Breast cancer classifier Deep learning Digital pathology Stain translation Unsupervised

nnDetection: A Self-configuring Method for Medical Object Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Baumgartner, Michael Jäger, Paul F. Isensee, Fabian Maier-Hein, Klaus H. Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Interactive Machine Learning Group German Cancer Research Center Germany HIP Applied Computer Vision Lab. German Cancer Research Center Germany Pattern Analysis and Learning Group Heidelberg University Hospital Germany

Simultaneous localisation and categorization of objects in medical images, also referred to as medical object detection, is of high clinical relevance because diagnostic decisions often depend on rating of objects rather than e.g. pixels. For this task, the cumbersome and iterative process of method configuration constitutes a major research bottleneck. Recently, nnU-Net has tackled this challenge for the task of image segmentation with great success. Following nnU-Net’s agenda, in this work we systematize and automate the configuration process for medical object detection. The resulting self-configuring method, nnDetection, adapts itself without any manual intervention to arbitrary medical detection problems while achieving results en par with or superior to the state-of-the-art. We demonstrate the effectiveness of nnDetection on two public benchmarks, ADAM and LUNA16, and propose 11 further medical object detection tasks on public data sets for comprehensive method evaluation. Code is at https://***/MIC-DKFZ/nnDetection. Copyright © 2021, The Authors. All rights reserved.

关键词： Object recognition

Neuron segmentation using 3D wavelet integrated encoder-decoder network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Qiufu Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen518060 China

Motivation: 3D neuron segmentation is a key step for the neuron digital reconstruction, which is essential for exploring brain circuits and understanding brain functions. However, the fine line-shaped nerve fibers of neuron could spread in a large region, which brings great computational cost to the neuron segmentation. Meanwhile, the strong noises and disconnected nerve fibers bring great challenges to the task. Results: In this paper, we propose a 3D wavelet and deep learning based 3D neuron segmentation method. The neuronal image is first partitioned into neuronal cubes to simplify the segmentation task. Then, we design 3D WaveUNet, the first 3D wavelet integrated encoder-decoder network, to segment the nerve fibers in the cubes;the wavelets could assist the deep networks in suppressing data noises and connecting the broken fibers. We also produce a Neuronal Cube Dataset (NeuCuDa) using the biggest available annotated neuronal image dataset, BigNeuron, to train 3D WaveUNet. Finally, the nerve fibers segmented in cubes are assembled to generate the complete neuron, which is digitally reconstructed using an available automatic tracing algorithm. The experimental results show that our neuron segmentation method could completely extract the target neuron in noisy neuronal images. The integrated 3D wavelets can efficiently improve the performance of 3D neuron segmentation and reconstruction. © 2021, CC BY.

关键词： Neurons

Self-supervised linear motion deblurring

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Peidong Janai, Joel Pollefeys, Marc Sattler, Torsten Geiger, Andreas Computer Vision and Geometry Group Department of Computer Science ETH Zürich Switzerland Autonomous Vision Group Max Planck Institute for Intelligent Systems Univeristy of Tübingen Tübingen Germany Microsoft Mixed Reality and Artificial Intelligence Lab Zürich Switzerland Computer Vision and Medical Image Analysis Group Chalmers University of Technology Sweden

Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this paper, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results. Both the code and datasets are available at https://***/ethliup/SelfDeblur. Copyright © 2020, The Authors. All rights reserved.

关键词： image enhancement

Face recognition - A one-shot learning perspective 15

学校读者我要写书评

暂无评论

Face recognition - A one-shot learning perspective

15th International Conference on Signal image Technology and Internet Based Systems, SISITS 2019

作者： Chanda, Sukalpa Gv, Asish Chakrapani Brun, Anders Hast, Anders Pal, Umapada Doermann, David Department of Information Technology Østfold University College Norway Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Centre for Image Analysis Uppsala University Sweden Computer Science and Engineering University at Buffalo United States

ISBN: (纸本)9781728156866

Ability to learn from a single instance is something unique to the human species and One-shot learning algorithms try to mimic this special capability. On the other hand, despite the fantastic performance of Deep Learning-based methods on various image classification problems, performance often depends having on a huge number of annotated training samples per class. This fact is certainly a hindrance in deploying deep neural network-based systems in many real-life applications like face recognition. Furthermore, an addition of a new class to the system will require the need to re-train the whole system from scratch. Nevertheless, the prowess of deep learned features could also not be ignored. This research aims to combine the best of deep learned features with a traditional One-Shot learning framework. Results obtained on 2 publicly available datasets are very encouraging achieving over 90% accuracy on 5-way One-Shot tasks, and 84% on 50-way One-Shot problems. © 2019 IEEE.

关键词： Face recognition

Artificial Intelligence Could Alert for Focal Skeleton/Bone Marrow Uptake in Hodgkińs Lymphoma Patients Staged With FDG-PET/CT

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Sadik, May López-Urdaneta, Jesús Ulén, Johannes Enqvist, Olof Krupic, Armin Kumar, Rajender Andersson, Per-Ola Trägårdh, Elin Molecular and Clinical Medicine Clinical Physiology Sahlgrenska University Hospital Sahlgrenska Academy The University of Gothenburg Sweden Eigenvision AB Signals and Systems Image Analysis and Computer Vision Chalmers University of Technology Sweden Post Graduate Institute of Medical Education and Research Haematology Södra Älvsborg Hospital Sweden Clinical Physiology and Nuclear Medicine Skåne University Hospital Sweden

Purpose: To develop an artificial intelligence (AI)-based method for the detection of focal skeleton/bone marrow uptake (BMU) in patients with Hodgkińs lymphoma (HL) undergoing staging with FDG-PET/CT. The results of the AI in a separate test group were compared to the interpretations of independent physicians. Methods: The skeleton and bone marrow were segmented using a convolutional neural network. The training of AI was based on 153 un-treated patients. Bone uptake significantly higher than the mean BMU was marked as abnormal, and an index, based on the total squared abnormal uptake, was computed to identify the focal uptake. Patients with an index above a predefined threshold were interpreted as having focal uptake. As the test group, 48 un-treated patients who had undergone a staging FDG-PET/CT between 2017-2018 with biopsy-proven HL were retrospectively included. Ten physicians classified the 48 cases regarding focal skeleton/BMU. Results: The majority of the physicians agreed with the AI in 39/48 cases (81%) regarding focal skeleton/bone marrow involvement. Inter-observer agreement between the physicians was moderate, Kappa 0.51 (range 0.25-0.80). Conclusion: An AI-based method can be developed to highlight suspicious focal skeleton/BMU in HL patients staged with FDG-PET/CT. Inter-observer agreement regarding focal BMU is moderate among nuclear medicine physicians. © 2021, CC BY.

关键词： Musculoskeletal system

Machine learning with multi-site imaging data: An empirical study on the impact of scanner effects

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Glocker, Ben Robinson, Robert Castro, Daniel C. Dou, Qi Konukoglu, Ender Biomedical Image Analysis Group Imperial College London United Kingdom Computer Vision Laboratory ETH Zurich Zurich Switzerland

This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data. We utilize structural T1-weighted brain MRI obtained from two different studies, Cam-CAN and UK Biobank. For the purpose of our investigation, we construct a dataset consisting of brain scans from 592 age- and sex-matched individuals, 296 subjects from each original study. Our results demonstrate that even after careful pre-processing with state-of-the-art neuroimaging pipelines a classifier can easily distinguish between the origin of the data with very high accuracy. Our analysis on the example application of sex classification suggests that current approaches to harmonize data are unable to remove scanner-specific bias leading to overly optimistic performance estimates and poor generalization. We conclude that multi-site data harmonization remains an open challenge and particular care needs to be taken when using such data with advanced machine learning methods for predictive modelling. Copyright © 2019, The Authors. All rights reserved.

关键词： Scanning

Attention alignment by linear space projection for video features extraction

学校读者我要写书评

暂无评论

Attention alignment by linear space projection for video fea...

IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO

作者： Yuan Shenqiang Mei Xue He Yi Zhang Jin dedicate in computer vision deep learning action recognition Computer Vision Image Processing Video Data Analysis and Research Nanjing Tech University in N. Jing J. Su CN

Video feature extraction is the basis of research on video data. At present, many models based on convolution neural networks for features extracting need to stack deeper network layers to improve the robustness, which means that the amount of parameters and computation is greatly increased while the practicability of such models is constrained. In this paper, a global projection self-attention mechanism is proposed to empower shallow models generate robust video representations. Compared to Non-local [17] and Squeeze Excitation [18] networks, we adopt more succinct but sufficient context modeling strategy to establish complete global interaction space, introduce a lighter transform block for attention coefficients predicting, which improves the running efficiency of attention models greatly. We further embed our attention module to several modern networks including ResNet[3], R(2+1)D[9] and I3D[7], in that ResNet-18 and R(2+1)D-18 meet considerably promotion upon its original version by more than 18.9 percent on UCF101 dataset, this result implies huge potential of proposed attention blocks.

关键词：

Geometric image labeling with global convex labeling constraints 11th

学校读者我要写书评

暂无评论

Geometric image labeling with global convex labeling constra...

11th International Conference on Energy Minimization Methods in computer vision and Pattern Recognition, EMMVCPR 2017

作者： Zern, Artjom Rohr, Karl Schnörr, Christoph Image and Pattern Analysis Group Heidelberg University Heidelberg Germany Biomedical Computer Vision Group BIOQUANT Heidelberg University Heidelberg Germany

ISBN: (纸本)9783319781983

In [2], a smooth geometric labeling approach was introduced by following the Riemannian gradient flow of a given objective function on the so-called assignment manifold. The approach evaluates a user-defined data term and performs spatial regularization by Riemannian averaging of the assignment vectors. In this paper, we extend this approach in order to impose global convex constraints on the labeling results based on linear filter statistics in the label space. The smoothness of the approach is preserved by using logarithmic barrier functions to handle the new constraints. We discuss how suitable filters can be determined from example data of a given image class, and we demonstrate numerically the effectiveness of the constraints in several academic labeling scenarios. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Geometry