Filters








259 Hits in 6.1 sec

Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting [article]

Lihao Liu, Chenyang Hong, Angelica I. Aviles-Rivero, Carola-Bibiane Schönlieb
2022 arXiv   pre-print
In this work, we present a solution framed as a simultaneous semantic and instance segmentation framework. Our solution is part of the Colon Nuclei Identification and Counting (CoNIC) Challenge.  ...  In our framework, the semantic model computes a class prediction for the cells whilst the instance model provides a refined segmentation.  ...  Conclusion In this paper, we introduce a framework for colon nuclei identification and counting. Our solution is framed as a simultaneous semantic and instance segmentation framework.  ... 
arXiv:2203.00157v2 fatcat:h7vstvvorvddfmwkgpxzw5isei

Panoptic segmentation with highly imbalanced semantic labels [article]

Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Andrew Janowczyk, Inti Zlobec, Dagmar Kainmueller
2022 arXiv   pre-print
We describe here the panoptic segmentation method we devised for our participation in the CoNIC: Colon Nuclei Identification and Counting Challenge at ISBI 2022.  ...  Key features of our method are a weighted loss specifically engineered for semantic segmentation of highly imbalanced cell types, and a state-of-the art nuclei instance segmentation model, which we combine  ...  The CoNIC: Colon Nuclei Identification and Counting Challenge [4] establishes a benchmark for respective comparative evaluation.  ... 
arXiv:2203.11692v4 fatcat:3daqp7m4dnck5pjna5qdtyvafq

A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge [article]

Jijun Cheng, Xipeng Pan, Feihu Hou, Bingchao Zhao, Jiatai Lin, Zhenbing Liu, Zaiyi Liu, Chu Han
2022 arXiv   pre-print
TIA lab from Warwick University organized a nuclear segmentation and classification challenge (CoNIC) for H&E stained histopathology images in colorectal cancer with two highly correlated tasks, nuclei  ...  Nuclear segmentation and classification is an essential step for computational pathology.  ...  NP was designed for nuclear semantic segmentation, and the HoVer learned the horizontal and vertical map of the nuclei.  ... 
arXiv:2203.00171v2 fatcat:tzzsu4mtvrgvja3j4xho7papyy

DeepLIIF: Deep Learning-Inferred Multiplex ImmunoFluorescence for IHC Quantification [article]

Parmida Ghahremani, Yanyun Li, Arie Kaufman, Rami Vanguri, Noah Greenwald, Michael Angelo, Travis J Hollmann, Saad Nadeem
2021 bioRxiv   pre-print
Leveraging a unique de novo dataset of co-registered IHC and multiplex immunoflourescence (mpIF) data generated from the same tissue section, we simultaneously segment and translate low-cost and prevalent  ...  By formulating the IHC quantification as cell instance segmentation/classification rather than cell detection problem, we show that our model trained on clean IHC Ki67 data can generalize to more noisy  ...  ACKNOWLEDGEMENTS This project was supported by MSK Cancer Center Support Grant/Core Grant (P30 CA008748) and in part by MSK DigITs Hybrid Research Initiative and NSF grants CNS1650499, OAC1919752, and  ... 
doi:10.1101/2021.05.01.442219 fatcat:ugt6rsfre5b7poymdxooq43thq

RIC-Unet: An Improved Neural Network Based on Unet for Nuclei Segmentation in Histology Images

Zitao Zeng, Weihao Xie, Yunzhe Zhang, Yao Lu
2019 IEEE Access  
As a prerequisite for cell detection, cell classification, and cancer grading, nuclei segmentation in histology images has attracted wide attention in recent years.  ...  In this paper, an Unet-based neural network, RIC-Unet (residual-inception-channel attention-Unet), for nuclei segmentation is proposed.  ...  ACKNOWLEDGEMENT Zitao Zeng and Weihao Xie contributed equally to this work.  ... 
doi:10.1109/access.2019.2896920 fatcat:eaexxiydjjdgxizg7vxiahau6u

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

Chetan L. Srinidhi, Ozan Ciga, Anne L. Martel
2019 arXiv   pre-print
Recently, deep learning has become the mainstream methodological choice for analyzing and interpreting cancer histology images.  ...  Finally, we summarize several existing open datasets and highlight critical challenges and limitations with current deep learning approaches, along with possible avenues for future research.  ...  as cell-level classification, nuclei segmentation, and cell counting (Hu et al., 2018a) .  ... 
arXiv:1912.12378v1 fatcat:xdfkzzwzb5alhjfhffqpcurb2u

One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification [article]

Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Fayyaz Minhas, David Snead, Nasir Rajpoot
2022 arXiv   pre-print
In this paper we present a multi-task learning approach for segmentation and classification of nuclei, glands, lumen and different tissue regions that leverages data from multiple independent data sources  ...  As part of this work, we use a large dataset consisting of over 600K objects for segmentation and 440K patches for classification and make the data publicly available.  ...  Precision Medicine strand of the governments Industrial Strategy Challenge Fund, managed and delivered by UK Research and Innovation (UKRI).  ... 
arXiv:2203.00077v1 fatcat:jywndktq6jcrlllwx2ve75fdk4

Machine Learning Methods for Histopathological Image Analysis: A Review

Jonathan de Matos, Steve Tsham Mpinda Ataky, Alceu de Souza Britto, Luiz Eduardo Soares de Oliveira, Alessandro Lameiras Koerich
2021 Electronics  
We also cover the most common tasks in HI analysis, such as segmentation and feature extraction.  ...  The analysis of such images is time and resource-consuming and very challenging even for experienced pathologists, resulting in inter-observer and intra-observer disagreements.  ...  Some works used the concept of semantic features, based on the e.g. counting of nuclei, its relation to the stroma, the distance between nuclei.  ... 
doi:10.3390/electronics10050562 fatcat:7kkj7qncxvdhdm3qvliwcqm3tq

Machine Learning Methods for Histopathological Image Analysis: A Review [article]

Jonathan de Matos and Steve Tsham Mpinda Ataky and Alceu de Souza Britto Jr. and Luiz Eduardo Soares de Oliveira and Alessandro Lameiras Koerich
2021 arXiv   pre-print
We also cover the most common tasks in HI analysis, such as segmentation and feature extraction.  ...  The analysis of such images is not only time and resource consuming, but also very challenging even for experienced pathologists, resulting in inter- and intra-observer disagreements.  ...  Some works used the concept of semantic features, based on the e.g. counting of nuclei, its relation to the stroma, the distance between nuclei.  ... 
arXiv:2102.03889v1 fatcat:ylrsildl4nenho22erndvpjcjy

Histopathological Image Analysis: A Review

M.N. Gurcan, L.E. Boucheron, A. Can, A. Madabhushi, N.M. Rajpoot, B. Yener
2009 IEEE Reviews in Biomedical Engineering  
This paper also briefly describes the development and application of novel image analysis technology for a few specific histopathology related problems being pursued in the United States and Europe.  ...  In this paper, we review the recent state of the art CAD technology for digitized histopathology.  ...  Another motivation for detecting and segmenting histological structures has to do with the need for counting of objects, generally cells or cell nuclei.  ... 
doi:10.1109/rbme.2009.2034865 pmid:20671804 pmcid:PMC2910932 fatcat:a6sm4iy5gffbhlc23dtlp7xe2q

Automated discourse generation using discourse structure relations

Eduard H. Hovy
1993 Artificial Intelligence  
Acknowledgments Many people have contributed to the work described here, directly and indirectly, particularly:  ...  The underlying representation for this example consisted of a semantic network of 18 instances, defined in terms of 27 air traffic domain concepts and 8 domain relations, implemented as frames in the Loom  ...  between them (either there is a relation between every 0 two adjacent segments in the list, or a relation holds among all the segments in the list simultaneously); or -a single discourse segment; or -  ... 
doi:10.1016/0004-3702(93)90021-3 fatcat:v5xvp3whpvfuxm6gf27esuogca

How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations

Vera Demberg, Merel C.J. Scholman, Fatemeh Torabi Asr
2019 Dialogue and Discourse  
We propose a method for automatically aligning the discourse segments, and then evaluate existing mapping proposals by comparing the empirically observed against the proposed mappings.  ...  Our analysis highlights the influence of segmentation on subsequent discourse relation labelling, and shows that while agreement between frameworks is reasonable for explicit relations, agreement on implicit  ...  The alignment data can also be used directly to select easy vs. difficult relation instances for training and evaluation of automatic relation identification systems.  ... 
doi:10.5087/dad.2019.104 fatcat:ziio3tsw5zfctc6xw3ikohrlxa

A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis [article]

Yixin Li, Chen Li, Xiaoyan Li, Kai Wang, Md Mamunur Rahaman, Changhao Sun, Hao Chen, Xinran Wu, Hong Zhang, Qian Wang
2021 arXiv   pre-print
Pathology image analysis is an essential procedure for clinical diagnosis of many diseases.  ...  Firstly, we introduce the background of two random fields and pathology images. Secondly, we summarize the basic mathematical knowledge of MRFs and CRFs from modelling to optimization.  ...  N2019003) and the "China Scholarship Council" (No. 2018GBJ001757). We thank Miss Zixian Li and Mr. Guoxian Li for their importantsupport and discussion in this work.  ... 
arXiv:2009.13721v3 fatcat:q46wb3rhwjcode3b46h6v2lhoa

Translational AI and Deep Learning in Diagnostic Pathology

Ahmed Serag, Adrian Ion-Margineanu, Hammad Qureshi, Ryan McMillan, Marie-Judith Saint Martin, Jim Diamond, Paul O'Reilly, Peter Hamilton
2019 Frontiers in Medicine  
The clearance of digital pathology for primary diagnosis in the US by some manufacturers provides the platform on which to deliver practical AI.  ...  with new tools that accelerate workflow and improve diagnostic consistency and reduce errors.  ...  FIGURE 1 | 1 U-Net architecture for semantic segmentation, comprising encoder (downsampling), and decoder (upsampling) sections, and showing the skip connections between layers (in yellow).  ... 
doi:10.3389/fmed.2019.00185 pmid:31632973 pmcid:PMC6779702 fatcat:jd5arv2lc5aq3lbk7ztipt5mca

Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning [article]

Noah F. Greenwald, Geneva Miller, Erick Moen, Alex Kong, Adam Kagel, Christine Camacho Fullaway, Brianna J. McIntosh, Ke Leow, Morgan Sarah Schwartz, Thomas Dougherty, Cole Pavelchek, Sunny Cui (+16 others)
2021 bioRxiv   pre-print
for whole-cell segmentation.  ...  We created Mesmer, a deep learning-enabled segmentation algorithm trained on TissueNet that performs nuclear and whole-cell segmentation in tissue imaging data.  ...  Acknowledgments We thank Long Cai, Katy Borner, Matt Thomson, Steve Quake, and Markus Covert for interesting discussions; Sean Bendall, David Glass, and Erin McCaffrey for feedback on the manuscript; Roshan  ... 
doi:10.1101/2021.03.01.431313 fatcat:xob6ar7uwfh3bpuwowp2lvyp7u
« Previous Showing results 1 — 15 out of 259 results