A Multi-Organ Nucleus Segmentation Challenge

Neeraj Kumar; Ruchika Verma; Deepak Anand; Yanning Zhou; Omer Fahri Onder; Efstratios Tsougenis; Hao Chen; Pheng Ann Heng; Jiahui Li; Zhiqiang Hu; Yunzhi Wang; Navid Alemi Koohbanani; Mostafa Jahanifar; Neda Zamani Tajeddin; Ali Gooya; Nasir Rajpoot; Xuhua Ren; Sihang Zhou; Qian Wang; Dinggang Shen; Cheng Kun Yang; Chi Hung Weng; Wei Hsiang Yu; Chao Yuan Yeh; Shuang Yang; Shuoyu Xu; Pak Hei Yeung; Peng Sun; Amirreza Mahbod; Gerald Schaefer; Isabella Ellinger; Rupert Ecker; Orjan Smedby; Chunliang Wang; Benjamin Chidester; That Vinh Ton; Minh Triet Tran; Jian Ma; Minh N. Do; Simon Graham; Quoc Dang Vu; Jin Tae Kwak; Akshaykumar Gunda; Raviteja Chunduri; Corey Hu; Xiaoyang Zhou; Dariush Lotfi; Reza Safdari; Antanas Kascenas; Alison O'Neil; Dennis Eschweiler; Johannes Stegmaier; Yanping Cui; Baocai Yin; Kailin Chen; Xinmei Tian; Philipp Gruening; Erhardt Barth; Elad Arbel; Itay Remer; Amir Ben-Dor; Ekaterina Sirazitdinova; Matthias Kohl; Stefan Braunewell; Yuexiang Li; Xinpeng Xie; Linlin Shen; Jun Ma; Krishanu Das Baksi; Mohammad Azam Khan; Jaegul Choo; Adrian Colomer; Valery Naranjo; Linmin Pei; Khan M. Iftekharuddin; Kaushiki Roy; Debotosh Bhattacharjee; Anibal Pedraza; Maria Gloria Bueno; Sabarinathan Devanathan; Saravanan Radhakrishnan; Praveen Koduganty; Zihan Wu; Guanyu Cai; Xiaojie Liu; Yuqin Wang; Amit Sethi

doi:10.1109/TMI.2019.2947628

A Multi-Organ Nucleus Segmentation Challenge

Neeraj Kumar, Ruchika Verma, Deepak Anand, Yanning Zhou, Omer Fahri Onder, Efstratios Tsougenis, Hao Chen, Pheng Ann Heng, Jiahui Li, Zhiqiang Hu, Yunzhi Wang, Navid Alemi Koohbanani, Mostafa Jahanifar, Neda Zamani Tajeddin, Ali Gooya, Nasir Rajpoot, Xuhua Ren, Sihang Zhou, Qian Wang, Dinggang ShenCheng Kun Yang, Chi Hung Weng, Wei Hsiang Yu, Chao Yuan Yeh, Shuang Yang, Shuoyu Xu, Pak Hei Yeung, Peng Sun, Amirreza Mahbod, Gerald Schaefer, Isabella Ellinger, Rupert Ecker, Orjan Smedby, Chunliang Wang, Benjamin Chidester, That Vinh Ton, Minh Triet Tran, Jian Ma, Minh N. Do, Simon Graham, Quoc Dang Vu, Jin Tae Kwak, Akshaykumar Gunda, Raviteja Chunduri, Corey Hu, Xiaoyang Zhou, Dariush Lotfi, Reza Safdari, Antanas Kascenas, Alison O'Neil, Dennis Eschweiler, Johannes Stegmaier, Yanping Cui, Baocai Yin, Kailin Chen, Xinmei Tian, Philipp Gruening, Erhardt Barth, Elad Arbel, Itay Remer, Amir Ben-Dor, Ekaterina Sirazitdinova, Matthias Kohl, Stefan Braunewell, Yuexiang Li, Xinpeng Xie, Linlin Shen, Jun Ma, Krishanu Das Baksi, Mohammad Azam Khan, Jaegul Choo, Adrian Colomer, Valery Naranjo, Linmin Pei, Khan M. Iftekharuddin, Kaushiki Roy, Debotosh Bhattacharjee, Anibal Pedraza, Maria Gloria Bueno, Sabarinathan Devanathan, Saravanan Radhakrishnan, Praveen Koduganty, Zihan Wu, Guanyu Cai, Xiaojie Liu, Yuqin Wang, Amit Sethi

Research output: Journal Publication › Article › peer-review

328 Citations (Scopus)

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.

Original language	English
Article number	8880654
Pages (from-to)	1380-1391
Number of pages	12
Journal	IEEE Transactions on Medical Imaging
Volume	39
Issue number	5
DOIs	https://doi.org/10.1109/TMI.2019.2947628
Publication status	Published - May 2020
Externally published	Yes

Keywords

Multi-organ
aggregated Jaccard index
digital pathology
instance segmentation
nucleus segmentation

ASJC Scopus subject areas

Software
Radiological and Ultrasound Technology
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/TMI.2019.2947628

Cite this

Kumar, N., Verma, R., Anand, D., Zhou, Y., Onder, O. F., Tsougenis, E., Chen, H., Heng, P. A., Li, J., Hu, Z., Wang, Y., Koohbanani, N. A., Jahanifar, M., Tajeddin, N. Z., Gooya, A., Rajpoot, N., Ren, X., Zhou, S., Wang, Q., ... Sethi, A. (2020). A Multi-Organ Nucleus Segmentation Challenge. IEEE Transactions on Medical Imaging, 39(5), 1380-1391. Article 8880654. https://doi.org/10.1109/TMI.2019.2947628

@article{54d8db4e3ed0402eadf13cd6b194092c,

title = "A Multi-Organ Nucleus Segmentation Challenge",

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.",

keywords = "Multi-organ, aggregated Jaccard index, digital pathology, instance segmentation, nucleus segmentation",

author = "Neeraj Kumar and Ruchika Verma and Deepak Anand and Yanning Zhou and Onder, {Omer Fahri} and Efstratios Tsougenis and Hao Chen and Heng, {Pheng Ann} and Jiahui Li and Zhiqiang Hu and Yunzhi Wang and Koohbanani, {Navid Alemi} and Mostafa Jahanifar and Tajeddin, {Neda Zamani} and Ali Gooya and Nasir Rajpoot and Xuhua Ren and Sihang Zhou and Qian Wang and Dinggang Shen and Yang, {Cheng Kun} and Weng, {Chi Hung} and Yu, {Wei Hsiang} and Yeh, {Chao Yuan} and Shuang Yang and Shuoyu Xu and Yeung, {Pak Hei} and Peng Sun and Amirreza Mahbod and Gerald Schaefer and Isabella Ellinger and Rupert Ecker and Orjan Smedby and Chunliang Wang and Benjamin Chidester and Ton, {That Vinh} and Tran, {Minh Triet} and Jian Ma and Do, {Minh N.} and Simon Graham and Vu, {Quoc Dang} and Kwak, {Jin Tae} and Akshaykumar Gunda and Raviteja Chunduri and Corey Hu and Xiaoyang Zhou and Dariush Lotfi and Reza Safdari and Antanas Kascenas and Alison O'Neil and Dennis Eschweiler and Johannes Stegmaier and Yanping Cui and Baocai Yin and Kailin Chen and Xinmei Tian and Philipp Gruening and Erhardt Barth and Elad Arbel and Itay Remer and Amir Ben-Dor and Ekaterina Sirazitdinova and Matthias Kohl and Stefan Braunewell and Yuexiang Li and Xinpeng Xie and Linlin Shen and Jun Ma and Baksi, {Krishanu Das} and Khan, {Mohammad Azam} and Jaegul Choo and Adrian Colomer and Valery Naranjo and Linmin Pei and Iftekharuddin, {Khan M.} and Kaushiki Roy and Debotosh Bhattacharjee and Anibal Pedraza and Bueno, {Maria Gloria} and Sabarinathan Devanathan and Saravanan Radhakrishnan and Praveen Koduganty and Zihan Wu and Guanyu Cai and Xiaojie Liu and Yuqin Wang and Amit Sethi",

note = "Publisher Copyright: {\textcopyright} 1982-2012 IEEE.",

year = "2020",

month = may,

doi = "10.1109/TMI.2019.2947628",

language = "English",

volume = "39",

pages = "1380--1391",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

Kumar, N, Verma, R, Anand, D, Zhou, Y, Onder, OF, Tsougenis, E, Chen, H, Heng, PA, Li, J, Hu, Z, Wang, Y, Koohbanani, NA, Jahanifar, M, Tajeddin, NZ, Gooya, A, Rajpoot, N, Ren, X, Zhou, S, Wang, Q, Shen, D, Yang, CK, Weng, CH, Yu, WH, Yeh, CY, Yang, S, Xu, S, Yeung, PH, Sun, P, Mahbod, A, Schaefer, G, Ellinger, I, Ecker, R, Smedby, O, Wang, C, Chidester, B, Ton, TV, Tran, MT, Ma, J, Do, MN, Graham, S, Vu, QD, Kwak, JT, Gunda, A, Chunduri, R, Hu, C, Zhou, X, Lotfi, D, Safdari, R, Kascenas, A, O'Neil, A, Eschweiler, D, Stegmaier, J, Cui, Y, Yin, B, Chen, K, Tian, X, Gruening, P, Barth, E, Arbel, E, Remer, I, Ben-Dor, A, Sirazitdinova, E, Kohl, M, Braunewell, S, Li, Y, Xie, X, Shen, L, Ma, J, Baksi, KD, Khan, MA, Choo, J, Colomer, A, Naranjo, V, Pei, L, Iftekharuddin, KM, Roy, K, Bhattacharjee, D, Pedraza, A, Bueno, MG, Devanathan, S, Radhakrishnan, S, Koduganty, P, Wu, Z, Cai, G, Liu, X, Wang, Y & Sethi, A 2020, 'A Multi-Organ Nucleus Segmentation Challenge', IEEE Transactions on Medical Imaging, vol. 39, no. 5, 8880654, pp. 1380-1391. https://doi.org/10.1109/TMI.2019.2947628

TY - JOUR

T1 - A Multi-Organ Nucleus Segmentation Challenge

AU - Kumar, Neeraj

AU - Verma, Ruchika

AU - Anand, Deepak

AU - Zhou, Yanning

AU - Onder, Omer Fahri

AU - Tsougenis, Efstratios

AU - Chen, Hao

AU - Heng, Pheng Ann

AU - Li, Jiahui

AU - Hu, Zhiqiang

AU - Wang, Yunzhi

AU - Koohbanani, Navid Alemi

AU - Jahanifar, Mostafa

AU - Tajeddin, Neda Zamani

AU - Gooya, Ali

AU - Rajpoot, Nasir

AU - Ren, Xuhua

AU - Zhou, Sihang

AU - Wang, Qian

AU - Shen, Dinggang

AU - Yang, Cheng Kun

AU - Weng, Chi Hung

AU - Yu, Wei Hsiang

AU - Yeh, Chao Yuan

AU - Yang, Shuang

AU - Xu, Shuoyu

AU - Yeung, Pak Hei

AU - Sun, Peng

AU - Mahbod, Amirreza

AU - Schaefer, Gerald

AU - Ellinger, Isabella

AU - Ecker, Rupert

AU - Smedby, Orjan

AU - Wang, Chunliang

AU - Chidester, Benjamin

AU - Ton, That Vinh

AU - Tran, Minh Triet

AU - Ma, Jian

AU - Do, Minh N.

AU - Graham, Simon

AU - Vu, Quoc Dang

AU - Kwak, Jin Tae

AU - Gunda, Akshaykumar

AU - Chunduri, Raviteja

AU - Hu, Corey

AU - Zhou, Xiaoyang

AU - Lotfi, Dariush

AU - Safdari, Reza

AU - Kascenas, Antanas

AU - O'Neil, Alison

AU - Eschweiler, Dennis

AU - Stegmaier, Johannes

AU - Cui, Yanping

AU - Yin, Baocai

AU - Chen, Kailin

AU - Tian, Xinmei

AU - Gruening, Philipp

AU - Barth, Erhardt

AU - Arbel, Elad

AU - Remer, Itay

AU - Ben-Dor, Amir

AU - Sirazitdinova, Ekaterina

AU - Kohl, Matthias

AU - Braunewell, Stefan

AU - Li, Yuexiang

AU - Xie, Xinpeng

AU - Shen, Linlin

AU - Ma, Jun

AU - Baksi, Krishanu Das

AU - Khan, Mohammad Azam

AU - Choo, Jaegul

AU - Colomer, Adrian

AU - Naranjo, Valery

AU - Pei, Linmin

AU - Iftekharuddin, Khan M.

AU - Roy, Kaushiki

AU - Bhattacharjee, Debotosh

AU - Pedraza, Anibal

AU - Bueno, Maria Gloria

AU - Devanathan, Sabarinathan

AU - Radhakrishnan, Saravanan

AU - Koduganty, Praveen

AU - Wu, Zihan

AU - Cai, Guanyu

AU - Liu, Xiaojie

AU - Wang, Yuqin

AU - Sethi, Amit

PY - 2020/5

Y1 - 2020/5

N2 - 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.

AB - 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.

KW - Multi-organ

KW - aggregated Jaccard index

KW - digital pathology

KW - instance segmentation

KW - nucleus segmentation

UR - http://www.scopus.com/inward/record.url?scp=85078353052&partnerID=8YFLogxK

U2 - 10.1109/TMI.2019.2947628

DO - 10.1109/TMI.2019.2947628

M3 - Article

C2 - 31647422

AN - SCOPUS:85078353052

SN - 0278-0062

VL - 39

SP - 1380

EP - 1391

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 5

M1 - 8880654

ER -

A Multi-Organ Nucleus Segmentation Challenge

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this