Filters








238 Hits in 7.4 sec

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
: Fully automated segmentation of cardiac MR images in patients with pulmonary hypertension 618 MS-Net: Mixed-Supervision Fully-Convolutional Networks for Full-Resolution Segmentation 624 Uncertainty in  ...  345 Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology 351 Combining Convolutional and Recurrent Neural Networks for Classification of Focal Liver Lesions in Multi-Phase  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Uncertainty Driven Pooling Network for Microvessel Segmentation in Routine Histology Images [chapter]

M. M. Fraz, M. Shaban, S. Graham, S. A. Khurram, N. M. Rajpoot
2018 Lecture Notes in Computer Science  
The framework extends DeepLabV3+ by using an improved dice coefficient based custom loss function and also incorporating an uncertainty prediction mechanism.  ...  Moreover, it is often beneficial to account for the uncertainty of a prediction when making a diagnosis.  ...  Most recently, a fully convolutional neural network (FCN) based method for microvessel detection in H&E stained images is presented [16] .  ... 
doi:10.1007/978-3-030-00949-6_19 fatcat:wirc2dmz2bhu3dnurhbm3ieleu

Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear [chapter]

Jianing Wang, Yiyuan Zhao, Jack H. Noble, Benoit M. Dawant
2018 Lecture Notes in Computer Science  
with a Recurrent Visual Attention Model for Histopathology Images Aicha BenTaieb*; Ghassan Hamarneh M-122 A Deep Model with Shape-preserving Loss for Gland Instance Segmentation Zengqiang Yan*; Xin Yang  ...  for Bayesian Registration Uncertainty Quantification Jian Wang*; William Wells; Polina Golland; Miaomiao Zhang M-101 Uncertainty in Multitask Learning: Joint Representations for Probabilistic MR-only  ... 
doi:10.1007/978-3-030-00928-1_1 fatcat:ypoj3zplm5awljf6u5c2spgiea

Deep neural network models for computational histopathology: A survey [article]

Chetan L. Srinidhi, Ozan Ciga, Anne L. Martel
2019 arXiv   pre-print
Histopathological images contain rich phenotypic information that can be used to monitor underlying mechanisms contributing to diseases progression and patient survival outcomes.  ...  In this paper, we present a comprehensive review of state-of-the-art deep learning approaches that have been used in the context of histopathological image analysis.  ...  Xie et al. (2015a Xie et al. ( , 2018b proposed a structured regression model based on fully residual convolutional networks for detecting cells in four different tissue images.  ... 
arXiv:1912.12378v1 fatcat:xdfkzzwzb5alhjfhffqpcurb2u

Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation [article]

Dwarikanath Mahapatra
2021 arXiv   pre-print
We demonstrate the benefits of the proposed approach, termed Interpretability-Driven Sample Selection (IDEAL), in an active learning setup aimed at lung disease classification and histopathology image  ...  We compare IDEAL to other baselines using the publicly available NIH chest X-ray dataset for lung disease classification, and a public histopathology segmentation dataset (GLaS), demonstrating the potential  ...  Uncertainty-driven sample selection This corresponds to our second baseline.  ... 
arXiv:2104.06087v1 fatcat:ismejlq3mre4ng4cjvn5enjy54

Structure-aware scale-adaptive networks for cancer segmentation in whole-slide images [article]

Yibao Sun, Giussepi Lopez, Yaqi Wang, Xingru Huang, Huiyu Zhou, Qianni Zhang
2021 arXiv   pre-print
In addition, advanced designs including several attention mechanisms and the selective-kernel convolutions are applied to the baseline network for comparative study purposes.  ...  Considering the usefulness of multi-scale features in various vision-related tasks, we present a structure-aware scale-adaptive feature selection method for efficient and accurate cancer segmentation.  ...  To address the drawbacks of patch-based methods, fully convolutional networks (FCN) have been proposed since 2015 [14] , which has driven recent advances in applying CNN for image segmentation.  ... 
arXiv:2109.12617v1 fatcat:56m5xuq7cfeszp2mc53sbea73q

Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applications [article]

Kexin Ding, Mu Zhou, Zichen Wang, Qiao Liu, Corey W. Arnold, Shaoting Zhang, Dimitri N. Metaxas
2022 arXiv   pre-print
The development of graph convolutional networks (GCNs) has created the opportunity to address this information complexity via graph-driven architectures, since GCNs can perform feature aggregation, interaction  ...  Yet daunting challenges remain for designing the important image-to-graph transformation for multi-modality medical imaging and gaining insights into model interpretation and enhanced clinical decision  ...  for uncertainty-aware disease prediction.  ... 
arXiv:2202.08916v3 fatcat:zskcqvgjpnb6vdklmyy5rozswq

Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation [article]

K. Ruwani M. Fernando, Chris P. Tsokos
2021 arXiv   pre-print
The results do highlight that model-driven classical statistics and data-driven deep learning is a potent combination for developing automated systems in clinical oncology.  ...  Integrated statistical and deep learning methods have recently emerged as a new direction in the automation of the medical practice unifying multi-disciplinary knowledge in medicine, statistics, and artificial  ...  Fully Convolutional Net To address limitations in CNNs, Long et al. (2015) devised a fully convolutional network (FCN) by transforming fully connected layers in the default CNN with convolutional layers  ... 
arXiv:2103.05529v1 fatcat:iqu5ix5tgre6pnokdmoejywh74

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models

Jialin Peng, Ye Wang
2021 IEEE Access  
The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling.  ...  Despite the remarkable performance of deep learning methods on various tasks, most cutting-edge models rely heavily on large-scale annotated training examples, which are often unavailable for clinical  ...  loss in the context of deep convolutional networks.  ... 
doi:10.1109/access.2021.3062380 fatcat:r5vsec2yfzcy5nk7wusiftyayu

Deep Learning in Multi-organ Segmentation [article]

Yang Lei, Yabo Fu, Tonghe Wang, Richard L.J. Qiu, Walter J. Curran, Tian Liu, Xiaofeng Yang
2020 arXiv   pre-print
This paper presents a review of deep learning (DL) in multi-organ segmentation. We summarized the latest DL-based methods for medical image segmentation and applications.  ...  These methods were classified into six categories according to their network design.  ...  Judging from the statistics of the cited works, there is a clear trend of using fully convolution network to perform end-to-end semantic segmentation for multi-organ automatic delineating.  ... 
arXiv:2001.10619v1 fatcat:6uwqwnzydzccblh5cajhsgdpea

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation [article]

Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding
2020 arXiv   pre-print
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks.  ...  body of research has studied the problem of medical image segmentation with imperfect datasets, tackling two major dataset limitations: scarce annotations where only limited annotated data is available for  ...  The discriminator, a fully convolutional network, serves two purposes: 1) distinguishing between ground truth and predicted masks at the pixel level, 2) providing a confidence (reliability) value for each  ... 
arXiv:1908.10454v2 fatcat:mjvfbhx75bdkbheysq3r7wmhdi

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models [article]

Jialin Peng, Ye Wang
2021 arXiv   pre-print
The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling.  ...  Despite the remarkable performance of deep learning methods on various tasks, most cutting-edge models rely heavily on large-scale annotated training examples, which are often unavailable for clinical  ...  loss in the context of deep convolutional networks.  ... 
arXiv:2103.00429v1 fatcat:p44a5e34sre4nasea5kjvva55e

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 8187-8198 Multi-Atlas Brain Parcellation Using Squeeze-and-Excitation Fully Convolutional Networks.  ...  ., +, TIP 2020 8187-8198 Multi-Atlas Brain Parcellation Using Squeeze-and-Excitation Fully Convolutional Networks.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labels [article]

Chu Han, Jiatai Lin, Jinhai Mai, Yi Wang, Qingling Zhang, Bingchao Zhao, Xin Chen, Xipeng Pan, Zhenwei Shi, Xiaowei Xu, Su Yao, Lixu Yan (+6 others)
2021 arXiv   pre-print
Note that we can achieve comparable quantitative and qualitative results with the fully-supervised model, with only around a 2% gap for MIoU and FwIoU.  ...  In the segmentation phase, we achieved tissue semantic segmentation by our proposed Multi-Layer Pseudo-Supervision.  ...  Multi-label soft margin loss is applied in the classification network.  ... 
arXiv:2110.08048v1 fatcat:vw2fptt5cbeijptzctyrw7xx5a

From CNNs to Vision Transformers – A Comprehensive Evaluation of Deep Learning Models for Histopathology [article]

Maximilian Springenberg, Annika Frommholz, Markus Wenzel, Eva Weicken, Jackie Ma, Nils Strodthoff
2022 arXiv   pre-print
In order to fill this gap, we conducted an extensive evaluation by benchmarking a wide range of classification models, including recent vision transformers, convolutional neural networks and hybrid models  ...  comprising transformer and convolutional models.  ...  ACKNOWLEDGMENT The authors would like to thank Angel Cruz-Roa and Anant Madabhushi for helpful correspondence on the IDC dataset.  ... 
arXiv:2204.05044v1 fatcat:enusfvfy55e5diuecqqlpz5nxe
« Previous Showing results 1 — 15 out of 238 results