Filters








652 Hits in 5.2 sec

A Survey on Deep Learning of Small Sample in Biomedical Image Analysis [article]

Pengyi Zhang, Yunxin Zhong, Yulin Deng, Xiaoying Tang, Xiaoqiong Li
2019 arXiv   pre-print
, and (5) miscellaneous techniques involving data augmentation, domain knowledge, traditional shallow methods and attention mechanism.  ...  We survey the key SSL techniques by dividing them into five categories: (1) explanation techniques, (2) weakly supervised learning techniques, (3) transfer learning techniques, (4) active learning techniques  ...  Acknowledgements The authors would like to thank members of the Medical Image Analysis for discussions and suggestions.  ... 
arXiv:1908.00473v1 fatcat:atotvdxp6janve2mz3swyf47xa

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

Chetan L. Srinidhi, Ozan Ciga, Anne L. Martel
2019 arXiv   pre-print
From the survey of over 130 papers, we review the fields progress based on the methodological aspect of different machine learning strategies such as supervised, weakly supervised, unsupervised, transfer  ...  We also provide an overview of deep learning based survival models that are applicable for disease-specific prognosis tasks.  ...  Domain adaptation Domain adaptation is a sub-field of transfer learning, where a task is learned from one or more source domains with labeled data (e.g., segmentation of tumour epithelium on Programmed  ... 
arXiv:1912.12378v1 fatcat:xdfkzzwzb5alhjfhffqpcurb2u

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  
246 Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays 248 Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image  ...  Tumor-aware, Adversarial Domain Adaptation from CT to MRI for Lung Cancer Segmentation 667 A Novel Method for Epileptic Seizure Detection Using Coupled Hidden Markov Models 668 Efficient Groupwise Registration  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Generalized fixation invariant nuclei detection through domain adaptation based deep learning

Mira Valkonen, Gunilla Hognas, G. Steven Bova, Pekka Ruusuvuori
2020 IEEE journal of biomedical and health informatics  
The dataset provides excellent basis for building an accurate and robust nuclei detection model, and combined with unsupervised domain adaptation, the workflow allows generalization to images from unseen  ...  Here, we studied the effect of histopathological sample fixation on the accuracy of a deep learning based nuclei detection model trained with hematoxylin and eosin stained images.  ...  Domain adaptation can be utilised in histopathological classification problems to address the requirement of labeled data in unsupervised [19] , [20] or weakly supervised [21] manner.  ... 
doi:10.1109/jbhi.2020.3039414 pmid:33211668 fatcat:yjerm7ifzzbjpfnjnv2buldyo4

Deep Learning for Computational Cytology: A Survey [article]

Hao Jiang, Yanning Zhou, Yi Lin, Ronald CK Chan, Jiang Liu, Hao Chen
2022 arXiv   pre-print
We first introduce various deep learning methods, including fully supervised, weakly supervised, unsupervised, and transfer learning.  ...  To investigate the advanced methods and comprehensive applications, we survey more than 120 publications of DL-based cytology image analysis in this article.  ...  Domain adaptation has been used for other medical scenarios with cross-domain data (e.g., CT and MRI (Chen et al., 2020) ), the potential of domain adaptation methods in cytology image analysis remains  ... 
arXiv:2202.05126v2 fatcat:d5ockk4ofjgv3oyxnuce4hmxpu

Generative Adversarial Networks in Digital Pathology: A Survey on Trends and Future Potential

Maximilian E. Tschuchnig, Gertie J. Oostingh, Michael Gadermayr
2020 Patterns  
However, GANs could exhibit a potential for introducing bias.  ...  In addition, we identify currently unavailable methods with potential for future applications.  ...  Specifically, we identify in the following subsections stain normalization, stain adaptation, segmentation using supervised models, the synthesis of image data for enabling weakly supervised and unsupervised  ... 
doi:10.1016/j.patter.2020.100089 pmid:33205132 pmcid:PMC7660380 fatcat:dcv2btvaung5tmgsxgklbqor3a

Weakly Supervised Nuclei Segmentation via Instance Learning [article]

Weizhen Liu, Qian He, Xuming He
2022 arXiv   pre-print
Weakly supervised nuclei segmentation is a critical problem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost.  ...  Adopting point annotations, previous methods mostly rely on less expressive representations for nuclei instances and thus have difficulty in handling crowded nuclei.  ...  A commonly-adopted weak supervision for nuclei segmentation is based on central point annotation due to the dense distribution and semi-regular shape of nuclei. In particular, Qu et al.  ... 
arXiv:2202.01564v2 fatcat:2vnfd5szlraovowsuhvpzejnja

DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis [article]

Tiange Xiang, Yang Song, Chaoyi Zhang, Dongnan Liu, Mei Chen, Fan Zhang, Heng Huang, Lauren O'Donnell, Weidong Cai
2022 arXiv   pre-print
We present a novel weakly-supervised framework for classifying whole slide images (WSIs).  ...  Experiments conducted on two large-scale public datasets demonstrate that our method outperforms all recent state-of-the-art weakly-supervised WSI classification methods.  ...  We reproduced all weakly-supervised methods [16] , [29] , [30] , [32] for fair comparison 1 except for the fully-supervised method [8] on Camelyon16, which we report the result from their paper  ... 
arXiv:2109.05788v2 fatcat:jbuftlyxijhyhfp7n4266a6laa

Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images

Hui Qu, Pengxiang Wu, Qiaoying Huang, Jingru Yi, Zhennan Yan, Kang Li, Gregory M. Riedlinger, Subhajyoti De, Shaoting Zhang, Dimitris N. Metaxas
2020 IEEE Transactions on Medical Imaging  
In the second stage, a segmentation model is trained from the detected nuclei locations in a weakly-supervised fashion.  ...  To alleviate such tedious and manual effort, in this paper we propose a novel weakly supervised segmentation framework based on partial points annotation, i.e., only a small portion of nuclei locations  ...  Our method consists of two stages: (1) semi-supervised nuclei detection and (2) weakly supervised nuclei segmentation.  ... 
doi:10.1109/tmi.2020.3002244 pmid:32746112 fatcat:qymqn4az4zdctn55o7f73xelli

NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images [article]

Navid Alemi Koohbanani, Mostafa Jahanifar, Neda Zamani Tajadin, Nasir Rajpoot
2020 arXiv   pre-print
As nuclei, cells and glands are fundamental objects for downstream analysis in computational pathology/cytology, in this paper we propose a simple CNN-based approach to speed up collecting annotations  ...  With detailed experiments, we show that NuClick is adaptable to the object scale, robust against variations in the user input, adaptable to new domains, and delivers reliable annotations.  ...  For instance, [12] and [13] introduced weakly supervised nucleus segmentation models which are trained based on nuclei centroid points instead of full segmentation masks.  ... 
arXiv:2005.14511v2 fatcat:yg6wig3nzfg25lh2gz6xvgnqay

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

Jialin Peng, Ye Wang
2021 IEEE Access  
Therefore, the strong capability of learning and generalizing from limited supervision, including a limited amount of annotations, sparse annotations, and inaccurate annotations, is crucial for the successful  ...  INDEX TERMS Medical image segmentation, semi-supervised segmentation, partially-supervised segmentation, noisy label, sparse annotation. 36828  ...  Please refer to [42] for comprehensive reviews of domain adaptation for semantic segmentation.  ... 
doi:10.1109/access.2021.3062380 fatcat:r5vsec2yfzcy5nk7wusiftyayu

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

Jialin Peng, Ye Wang
2021 arXiv   pre-print
Therefore, the strong capability of learning and generalizing from limited supervision, including a limited amount of annotations, sparse annotations, and inaccurate annotations, is crucial for the successful  ...  However, due to its intrinsic difficulty, segmentation with limited supervision is challenging and specific model design and/or learning strategies are needed.  ...  Please refer to [42] for comprehensive reviews of domain adaptation for semantic segmentation.  ... 
arXiv:2103.00429v1 fatcat:p44a5e34sre4nasea5kjvva55e

Deep Learning Models for Digital Pathology [article]

Aïcha BenTaieb, Ghassan Hamarneh
2019 arXiv   pre-print
In this survey, we summarize the different challenges facing computational systems for digital pathology and provide a review of state-of-the-art works that developed deep learning-based solutions for  ...  We then discuss the challenges facing the validation and integration of such deep learning-based computational systems in clinical workflow and reflect on future opportunities for histopathology derived  ...  Weakly Supervised Models Weakly supervised models leverage patch-based representation to classify WSIs while only using slide-level annotations during training.  ... 
arXiv:1910.12329v2 fatcat:2b7h7i2zwbautewneabghm3bzi

In Defense of LSTMs for Addressing Multiple Instance Learning Problems [article]

Kaili Wang, Jose Oramas, Tinne Tuytelaars
2021 arXiv   pre-print
Thus, they can be used to learn instance-level models in a weakly supervised manner.  ...  While not often used for this, we show LSTMs excell under this setting too.  ...  Fig. 5 : 5 a) The original H&E image. b) The epithelial nuclei patches (Ground-Truth). c) The epithelial nuclei patches detected by our MIL model. d) The epithelial nuclei patches detected by attention-based  ... 
arXiv:1909.05690v5 fatcat:q6ndnjynkzhgnoo5ojuklnctsm

WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images

Julio Silva-Rodríguez, Adrián Colomer, Valery Naranjo
2021 Computerized Medical Imaging and Graphics  
The methodological core of this work is the proposed weakly-supervised-trained convolutional neural network, WeGleNet, based on a multi-class segmentation layer after the feature extraction module, a global-aggregation  ...  In this work, we propose a deep-learning-based system able to detect local cancerous patterns in the prostate tissue using only the global-level Gleason score obtained from clinical records during training  ...  probabilities for colon cancer detection.  ... 
doi:10.1016/j.compmedimag.2020.101846 pmid:33485056 fatcat:3466aib7efbjthc6x7es75ottm
« Previous Showing results 1 — 15 out of 652 results