A Multi-Organ Nucleus Segmentation Challenge

Journal article

Neeraj Kumar, R. Verma, Deepak Anand, Yanning Zhou, O. F. Onder, E. Tsougenis, Hao Chen, P. Heng, Jiahui Li, Zhiqiang Hu, Yunzhi Wang, Navid Alemi Koohbanani, M. Jahanifar, Neda Zamani Tajeddin, A. Gooya, N. Rajpoot, Xuhua Ren, Sihang Zhou, Qian Wang, D. Shen, Cheng-Kun Yang, C. Weng, Wei-Hsiang Yu, Chao-Yuan Yeh, Shuang Yang, Shuoyu Xu, P. Yeung, Peng Sun, A. Mahbod, G. Schaefer, I. Ellinger, R. Ecker, O. Smedby, Chunliang Wang, Benjamin Chidester, That-Vinh Ton, M. Tran, Jian Ma, M. Do, S. Graham, Q. Vu, J. T. Kwak, Akshaykumar Gunda, R. Chunduri, Corey Hu, Xiao-xiao Zhou, Dariush Lotfi, Reza Safdari, Antanas Kascenas, Alison Q. O'Neil, Dennis Eschweiler, J. Stegmaier, Yanping Cui, Baocai Yin, Kailin Chen, Xinmei Tian, P. Gruening, E. Barth, E. Arbel, I. Remer, A. Ben-Dor, E. Sirazitdinova, Matthias Kohl, S. Braunewell, Yuexiang Li, Xinpeng Xie, Linlin Shen, Jun Ma, K. D. Baksi, Mohammad Azam Khan, J. Choo, Adrián Colomer, V. Naranjo, L. Pei, K. Iftekharuddin, K. Roy, D. Bhattacharjee, Aníbal Pedraza, M. G. Bueno, S. Devanathan, Saravanan Radhakrishnan, Praveen Koduganty, Zihan Wu, Guanyu Cai, Xiaojie Liu, Yuqin Wang, A. Sethi
IEEE Transactions on Medical Imaging, 2020

Semantic Scholar DBLP DOI PubMed

Cite

APA Click to copy
Kumar, N., Verma, R., Anand, D., Zhou, Y., Onder, O. F., Tsougenis, E., … Sethi, A. (2020). A Multi-Organ Nucleus Segmentation Challenge. IEEE Transactions on Medical Imaging.

Chicago/Turabian Click to copy
Kumar, Neeraj, R. Verma, Deepak Anand, Yanning Zhou, O. F. Onder, E. Tsougenis, Hao Chen, et al. “A Multi-Organ Nucleus Segmentation Challenge.” IEEE Transactions on Medical Imaging (2020).

MLA Click to copy
Kumar, Neeraj, et al. “A Multi-Organ Nucleus Segmentation Challenge.” IEEE Transactions on Medical Imaging, 2020.

BibTeX Click to copy

@article{neeraj2020a,
  title = {A Multi-Organ Nucleus Segmentation Challenge},
  year = {2020},
  journal = {IEEE Transactions on Medical Imaging},
  author = {Kumar, Neeraj and Verma, R. and Anand, Deepak and Zhou, Yanning and Onder, O. F. and Tsougenis, E. and Chen, Hao and Heng, P. and Li, Jiahui and Hu, Zhiqiang and Wang, Yunzhi and Koohbanani, Navid Alemi and Jahanifar, M. and Tajeddin, Neda Zamani and Gooya, A. and Rajpoot, N. and Ren, Xuhua and Zhou, Sihang and Wang, Qian and Shen, D. and Yang, Cheng-Kun and Weng, C. and Yu, Wei-Hsiang and Yeh, Chao-Yuan and Yang, Shuang and Xu, Shuoyu and Yeung, P. and Sun, Peng and Mahbod, A. and Schaefer, G. and Ellinger, I. and Ecker, R. and Smedby, O. and Wang, Chunliang and Chidester, Benjamin and Ton, That-Vinh and Tran, M. and Ma, Jian and Do, M. and Graham, S. and Vu, Q. and Kwak, J. T. and Gunda, Akshaykumar and Chunduri, R. and Hu, Corey and Zhou, Xiao-xiao and Lotfi, Dariush and Safdari, Reza and Kascenas, Antanas and O'Neil, Alison Q. and Eschweiler, Dennis and Stegmaier, J. and Cui, Yanping and Yin, Baocai and Chen, Kailin and Tian, Xinmei and Gruening, P. and Barth, E. and Arbel, E. and Remer, I. and Ben-Dor, A. and Sirazitdinova, E. and Kohl, Matthias and Braunewell, S. and Li, Yuexiang and Xie, Xinpeng and Shen, Linlin and Ma, Jun and Baksi, K. D. and Khan, Mohammad Azam and Choo, J. and Colomer, Adrián and Naranjo, V. and Pei, L. and Iftekharuddin, K. and Roy, K. and Bhattacharjee, D. and Pedraza, Aníbal and Bueno, M. G. and Devanathan, S. and Radhakrishnan, Saravanan and Koduganty, Praveen and Wu, Zihan and Cai, Guanyu and Liu, Xiaojie and Wang, Yuqin and Sethi, A.}
}

Abstract

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Mohammad Azam Khan

A Multi-Organ Nucleus Segmentation Challenge

Journal article

Cite

Abstract

Follow this website