27,234 Hits in 4.2 sec

MoNuSAC2020: A Multi-organ Nuclei Segmentation and Classification Challenge

Ruchika Verma, Neeraj Kumar, Abhijeet Patil, Nikhil Cherian Kurian, Swapnil Rane, Simon Graham, Quoc Dang Vu, Mieke Zwager, Shan E Ahmed Raza, Nasir Rajpoot, Xiyi Wu, Huai Chen (+46 others)
2021 IEEE Transactions on Medical Imaging  
We also organized a challenge around this dataset as a satellite event at the International Symposium on Biomedical Imaging (ISBI) in April 2020.  ...  The dataset has over 46,000 nuclei from 37 hospitals, 71 patients, four organs, and four nucleus types.  ...  MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge of cells in and around a tumor.  ... 
doi:10.1109/tmi.2021.3085712 pmid:34086562 fatcat:7qk3rgphlrcjzks4amm4dqkiy4

Switching Loss for Generalized Nucleus Detection in Histopathology [article]

Deepak Anand, Gaurav Patel, Yaman Dang, Amit Sethi
2020 arXiv   pre-print
A nucleus detector trained using the proposed loss function on a source dataset outperformed those trained using cross-entropy, Dice, or focal losses.  ...  To establish a broad utility of the proposed loss, we also confirmed that it led to more accurate ventricle segmentation in MRI as compared to the other loss functions.  ...  We used MICCAI 2012 right ventricle segmentation challenge(RVSC) dataset. 48 The challenge was to automatically segment right ventricle endocardium and epicardium segmentation from short-axis cine MRI  ... 
arXiv:2008.03750v1 fatcat:z767o6e2ezhd5ep6nfjsnmeqgq

Nuclear Instance Segmentation using a Proposal-Free Spatially Aware Deep Learning Framework [article]

Navid Alemi Koohbanani, Mostafa Jahanifar, Ali Gooya, Nasir Rajpoot
2019 arXiv   pre-print
We applied our method on a publicly available multi-organ data set and achieved state-of-the-art performance for nuclear segmentation.  ...  Nuclear segmentation in histology images is a challenging task due to significant variations in the shape and appearance of nuclei.  ...  clump, iv) achieving state-of-the-art results on a well-known publicly available multi-organ data set.  ... 
arXiv:1908.10356v1 fatcat:77fwd5ivmvew3pekkkacid7fhe

Exploiting the Multiscale Information Fusion Capabilities for Aiding the Leukemia Diagnosis Through White Blood Cells Segmentation

Nadeem Akram, Sharjeel Adnan, Muhammad Asif, Syed Muhammad Ali Imran, Muhammad Naveed Yasir, Rizwan Ali Naqvi, Dildar Hussain
2022 IEEE Access  
To overcome these problems, we propose a multi-scale information fusion network (MIF-Net) for WBC segmentation.  ...  challenging.  ...  Since NRBC also has a nucleus therefore its segmentation becomes challenging.  ... 
doi:10.1109/access.2022.3171916 fatcat:xu2pyxf5xfbl3cp2w7ulbrfiqa

Convolutional Blur Attention Network for Cell Nuclei Segmentation

Phuong Thi Le, Tuan Pham, Yi-Chiung Hsu, Jia-Ching Wang
2022 Sensors  
the multi-organ nucleus segmentation (MoNuSeg) at MICCAI 2018.  ...  However, the diversity of cell types, various external factors, and illumination conditions make nucleus segmentation a challenging task.  ...  Secondly, the multi-organ nucleus segmentation (MoNuSeg) at MICCAI 2018 includes digital microscopic tissue images as implemented in this paper [19] .  ... 
doi:10.3390/s22041586 pmid:35214488 pmcid:PMC8878074 fatcat:xpnkecco5zclrccsiw6tmaocoi

Contextual Mixing Feature Unet for Multi-Organ Nuclei Segmentation

Xi Xue, Sei-Ichiro Kamata
2022 Frontiers in Signal Processing  
We test the proposed method on the multi-organ nuclei segmentation (MoNuSeg) dataset.  ...  In order to capture each nucleus on different organs precisely, characteristics about both nuclei and boundaries are of equal importance.  ...  Challenges of multi-organ nuclei segmentation task.  ... 
doi:10.3389/frsip.2022.833433 fatcat:c2yevtjqovdd3gsnrhet65ibxi

AI and Pathology: Steering Treatment and Predicting Outcomes [article]

Rajarsi Gupta, Jakub Kaczmarzyk, Soma Kobayashi, Tahsin Kurc, Joel Saltz
2022 arXiv   pre-print
We describe the rich set of application challenges related to tissue interpretation and survey AI methods currently used to address these challenges.  ...  The combination of data analysis methods, increasing computing capacity, and improved sensors enable quantitative granular, multi-scale, cell-based analyses.  ...  In a more recent work, the top scoring participants of a digital pathology challenge proposed a multi-step deep learning pipeline for nucleus segmentation [17] .  ... 
arXiv:2206.07573v1 fatcat:c32agl3m5bbthlcncr6s7ng4om

Automatic histopathology image analysis with CNNs

Le Hou, Kunal Singh, Dimitris Samaras, Tahsin M. Kurc, Yi Gao, Roberta J. Seidman, Joel H. Saltz
2016 2016 New York Scientific Data Summit (NYSDS)  
Executing a Pathomics workflow on a dataset of thousands of very high resolution (gigapixels) and heterogeneous histopathology images is a computationally challenging problem.  ...  We constructed a comprehensive multi-label dataset of glioma nuclei and applied two CNN based methods on this dataset.  ...  Recently, CNN models have achieved the best results in multiple MICCAI challenges; for example, a multi-column CNN detection method won the MICCAI mitosis detection challenge in breast cancer [13] .  ... 
doi:10.1109/nysds.2016.7747812 fatcat:3t7xv6d44jcivkacteynag52om

A Deep Learning Framework for Nuclear Segmentation and Classification in Histopathological Images [article]

Sen Yang, Jingxi Xiang, Xiyue Wang
2022 arXiv   pre-print
Nucleus segmentation and classification are the prerequisites in the workflow of digital pathology processing. However, it is very challenging due to its high-level heterogeneity and wide variations.  ...  This work proposes a deep neural network to simultaneously achieve nuclear classification and segmentation, which is designed using a unified framework with three different branches, including segmentation  ...  the organizer of the challenge [6] .  ... 
arXiv:2203.03420v1 fatcat:louozoa7zrhy7ig5zzmbsgyyau

Review of Nuclei Detection, Segmentation in Microscopic Images

Rujuta O, Vyavahare AJ
2017 Journal of Bioengineering and Biomedical Sciences  
This paper is a review of some recent state-of-art nucleus/cell segmentation approaches on different types of microscopic images.  ...  We and discussed and studied here various trends on nucleus detection, and segmentation.  ...  The multidimensional representation generated for each nucleus defines its signature and organization.  ... 
doi:10.4172/2155-9538.1000227 fatcat:xxvyqhsghzgplddods4bjlulq4

Author's Reply to "MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge"

Ruchika Verma, Neeraj Kumar, Abhijeet Patil, Nikhil Cherian Kurian, Swapnil Rane, Amit Sethi
2022 IEEE Transactions on Medical Imaging  
Based on this dataset, we had organized a challenge at the International Symposium on Biomedical Imaging (ISBI) 2020.  ...  We had released MoNuSAC2020 as one of the largest publicly available, manually annotated, curated, multi-class, and multi-instance medical image segmentation datasets.  ...  INTRODUCTION The main objective of creating the multi-organ nucleus segmentation and classification (MoNuSAC) dataset [3] was to encourage the computer vision and computational pathology research community  ... 
doi:10.1109/tmi.2022.3157048 pmid:35363607 fatcat:opqaig5nmndoxicqf6sqpo7aiy

Automatic cell segmentation in fluorescence images of confluent cell monolayers using multi-object geometric deformable model

Zhen Yang, John A. Bogovic, Aaron Carass, Mao Ye, Peter C. Searson, Jerry L. Prince, David R. Haynor, Sebastien Ourselin
2013 Medical Imaging 2013: Image Processing  
This method addresses several challenges through a combination of ideas. 1) It realizes a fully automatic segmentation process by first detecting the cell nuclei as initial seeds and then using a multi-object  ...  In this paper, we propose a fully automatic method for segmenting cells in fluorescence images of confluent cell monolayers.  ...  The main challenge for cell nucleus detection is overlap due to clustering or multiple nuclei.  ... 
doi:10.1117/12.2006603 pmid:24386546 pmcid:PMC3877311 dblp:conf/miip/YangBCYSP13 fatcat:v43wpdv73bh5bcbdwfr5nfzon4

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  
The techniques of residual blocks, multi-scale and channel attention mechanism are applied on RIC-Unet to segment nuclei more accurately.  ...  It is quite a challenging task due to the diversity in staining procedure, cell morphology, and cell arrangement between different histopathology images, especially with different color contrasts.  ...  [12] in the segmentation of gland instances, adopting a multi-task learning framework, allowing the network to learn to segment the nucleus and cell contour at the same time.  ... 
doi:10.1109/access.2019.2896920 fatcat:eaexxiydjjdgxizg7vxiahau6u

Using Multi-scale SwinTransformer-HTC with Data augmentation in CoNIC Challenge [article]

Chia-Yen Lee, Hsiang-Chin Chien, Ching-Ping Wang, Hong Yen, Kai-Wen Zhen, Hong-Kun Lin
2022 arXiv   pre-print
We proposed a multi-scale Swin transformer with HTC for this challenge, and also applied the known normalization methods to generate more augmentation data.  ...  Therefore, automatic segmentation and classification task and counting the cellular composition of H&E images from pathological sections is proposed by CoNIC Challenge 2022.  ...  Hence, we proposed a multi-scale deep learning method, and the general workflow of our method is as follows (Fig. 2 ). A.  ... 
arXiv:2202.13588v2 fatcat:mqks6hl6ubcfpewf7hb7cd4xmy

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.  ...  We refer to 'S' and 'I' as the semantic and instance models respectively, and 'B' as the baseline provided by the challenge organizers. 'DataAug' refers to data augmentation.  ... 
arXiv:2203.00157v2 fatcat:h7vstvvorvddfmwkgpxzw5isei
« Previous Showing results 1 — 15 out of 27,234 results