Contextual Mixing Feature Unet for Multi-Organ Nuclei Segmentation

被引:0
|
作者
Xue, Xi [1 ]
Kamata, Sei-Ichiro [1 ]
机构
[1] Waseda Univ, Grad Sch Informat Prod & Syst, Image Media Lab, Kitakyushu, Japan
来源
FRONTIERS IN SIGNAL PROCESSING | 2022年 / 2卷
关键词
nuclei segmentation; multi-organ; pathological images; deep learning; instance segmentation; mixing feature;
D O I
10.3389/frsip.2022.833433
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Nuclei segmentation is fundamental and crucial for analyzing histopathological images. Generally, a pathological image contains tens of thousands of nuclei, and there exists clustered nuclei, so it is difficult to separate each nucleus accurately. Challenges against blur boundaries, inconsistent staining, and overlapping regions have adverse effects on segmentation performance. Besides, nuclei from various organs appear quite different in shape and size, which may lead to the problems of over-segmentation and under-segmentation. In order to capture each nucleus on different organs precisely, characteristics about both nuclei and boundaries are of equal importance. Thus, in this article, we propose a contextual mixing feature Unet (CMF-Unet), which utilizes two parallel branches, nuclei segmentation branch and boundary extraction branch, and mixes complementary feature maps from two branches to obtain rich and integrated contextual features. To ensure good segmentation performance, a multiscale kernel weighted module (MKWM) and a dense mixing feature module (DMFM) are designed. MKWM, used in both nuclei segmentation branch and boundary extraction branch, contains a multiscale kernel block to fully exploit characteristics of images and a weight block to assign more weights on important areas, so that the network can extract discriminative information efficiently. To fuse more beneficial information and get integrated feature maps, the DMFM mixes the feature maps produced by the MKWM from two branches to gather both nuclei information and boundary information and links the feature maps in a densely connected way. Because the feature maps produced by the MKWM and DMFM are both sent into the decoder part, segmentation performance can be enhanced effectively. We test the proposed method on the multi-organ nuclei segmentation (MoNuSeg) dataset. Experiments show that the proposed method not only performs well on nuclei segmentation but also has good generalization ability on different organs.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Multiscale Dilated UNet for Segmentation of Multi-Organ Nuclei in Digital Histology Images
    Rashid, S. N.
    Fraz, M. M.
    Javed, S.
    2020 IEEE 17TH INTERNATIONAL CONFERENCE ON SMART COMMUNITIES: IMPROVING QUALITY OF LIFE USING ICT, IOT AND AI (IEEEHONET 2020), 2020, : 68 - 72
  • [2] WaveSeg-UNet model for overlapped nuclei segmentation from multi-organ histopathology images
    Khan, Hameed Ullah
    Raza, Basit
    Khan, Muhammad Asad Iqbal
    Faheem, Muhammad
    CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2025, 10 (01) : 253 - 267
  • [3] SequentialSegNet: Combination with Sequential Feature for Multi-organ Segmentation
    Zhang, Yao
    Jiang, Xuan
    Zhong, Cheng
    Zhang, Yang
    Shi, Zhongchao
    Li, Zhensheng
    He, Zhiqiang
    2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 3947 - 3952
  • [4] A Multi-Organ Segmentation Network Based on Densely Connected RL-Unet
    Zhang, Qirui
    Xu, Bing
    Liu, Hu
    Zhang, Yu
    Yu, Zhiqiang
    APPLIED SCIENCES-BASEL, 2024, 14 (17):
  • [5] Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images
    Mahmood, Faisal
    Borders, Daniel
    Chen, Richard J.
    Mckay, Gregory N.
    Salimian, Kevan J.
    Baras, Alexander
    Durr, Nicholas J.
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (11) : 3257 - 3267
  • [6] MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge
    Verma, Ruchika
    Kumar, Neeraj
    Patil, Abhijeet
    Kurian, Nikhil Cherian
    Rane, Swapnil
    Graham, Simon
    Quoc Dang Vu
    Zwager, Mieke
    Raza, Shan E. Ahmed
    Rajpoot, Nasir
    Wu, Xiyi
    Chen, Huai
    Huang, Yijie
    Wang, Lisheng
    Jung, Hyun
    Brown, G. Thomas
    Liu, Yanling
    Liu, Shuolin
    Jahromi, Seyed Alireza Fatemi
    Khani, Ali Asghar
    Montahaei, Ehsan
    Baghshah, Mahdieh Soleymani
    Behroozi, Hamid
    Semkin, Pavel
    Rassadin, Alexandr
    Dutande, Prasad
    Lodaya, Romil
    Baid, Ujjwal
    Baheti, Bhakti
    Talbar, Sanjay
    Mahbod, Amirreza
    Ecker, Rupert
    Ellinger, Isabella
    Luo, Zhipeng
    Dong, Bin
    Xu, Zhengyu
    Yao, Yuehan
    Lv, Shuai
    Feng, Ming
    Xu, Kele
    Zunair, Hasib
    Ben Hamza, Abdessamad
    Smiley, Steven
    Yin, Tang-Kai
    Fang, Qi-Rui
    Srivastava, Shikhar
    Mahapatra, Dwarikanath
    Trnavska, Lubomira
    Zhang, Hanyun
    Narayanan, Priya Lakshmi
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2021, 40 (12) : 3413 - 3423
  • [7] AMONuSeg: A Histological Dataset for African Multi-organ Nuclei Semantic Segmentation
    Zerouaoui, Hasnae
    Oderinde, Gbenga Peter
    Lefdali, Rida
    Echihabi, Karima
    Akpulu, Stephen Peter
    Agbon, Nosereme Abel
    Musa, Abraham Sunday
    Yeganeh, Yousef
    Farshad, Azade
    Navab, Nassir
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2024, PT IX, 2024, 15009 : 96 - 106
  • [8] Partial Label Multi-organ Segmentation based on Local Feature Enhancement
    Zhao, Yanxia
    Hu, Peijun
    Li, Jingsong
    2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,
  • [9] Segmentation of Multi-Organ Functional Tissue Units Using UNet-EfficientNet-B8
    Shen, Aoran
    Chen, Ruxin
    Zhu, Yueze
    Hu, Ruohan
    PROCEEDINGS OF 2023 4TH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE FOR MEDICINE SCIENCE, ISAIMS 2023, 2023, : 232 - 235
  • [10] Multi-organ Segmentation of Chest CT Images in Radiation Oncology: Comparison of Standard and Dilated UNet
    Javaid, Umair
    Dasnoy, Damien
    Lee, John A.
    ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2018, 2018, 11182 : 188 - 199