Large-scale annotated dataset for cochlear hair cell detection and classification

Christopher J. Buswinka; David B. Rosenberg; Rubina G. Simikyan; Richard T. Osgood; Katharine Fernandez; Hidetomi Nitta; Yushi Hayashi; Leslie W. Liberman; Emily Nguyen; Erdem Yildiz; Jinkyung Kim; Amandine Jarysta; Justine Renauld; Ella Wesson; Haobing Wang; Punam Thapa; Pierrick Bordiga; Noah McMurtry; Juan Llamas; Siân R. Kitcher; Ana I. López-Porras; Runjia Cui; Ghazaleh Behnammanesh; Jonathan E. Bird; Angela Ballesteros; A. Catalina Vélez-Ortega; Albert S.B. Edge; Michael R. Deans; Ksenia Gnedeva; Brikha R. Shrestha; Uri Manor; Bo Zhao; Anthony J. Ricci; Basile Tarchini; Martín L. Basch; Ruben Stepanyan; Lukas D. Landegger; Mark A. Rutherford; M. Charles Liberman; Bradley J. Walters; Corné J. Kros; Guy P. Richardson; Lisa L. Cunningham; Artur A. Indzhykulian

doi:10.1038/s41597-024-03218-y

Large-scale annotated dataset for cochlear hair cell detection and classification

Christopher J. Buswinka, David B. Rosenberg, Rubina G. Simikyan, Richard T. Osgood, Katharine Fernandez, Hidetomi Nitta, Yushi Hayashi, Leslie W. Liberman, Emily Nguyen, Erdem Yildiz, Jinkyung Kim, Amandine Jarysta, Justine Renauld, Ella Wesson, Haobing Wang, Punam Thapa, Pierrick Bordiga, Noah McMurtry, Juan Llamas, Siân R. KitcherAna I. López-Porras, Runjia Cui, Ghazaleh Behnammanesh, Jonathan E. Bird, Angela Ballesteros, A. Catalina Vélez-Ortega, Albert S.B. Edge, Michael R. Deans, Ksenia Gnedeva, Brikha R. Shrestha, Uri Manor, Bo Zhao, Anthony J. Ricci, Basile Tarchini, Martín L. Basch, Ruben Stepanyan, Lukas D. Landegger, Mark A. Rutherford, M. Charles Liberman, Bradley J. Walters, Corné J. Kros, Guy P. Richardson, Lisa L. Cunningham, Artur A. Indzhykulian

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Our sense of hearing is mediated by cochlear hair cells, of which there are two types organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains 5–15 thousand terminally differentiated hair cells, and their survival is essential for hearing as they do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. Machine learning can be used to automate the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, rat, guinea pig, pig, primate, and human cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 107,000 hair cells which have been identified and annotated as either inner or outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair-cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to give other hearing research groups the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.

Original language	English
Article number	416
Journal	Scientific data
Volume	11
Issue number	1
DOIs	https://doi.org/10.1038/s41597-024-03218-y
State	Published - Dec 2024

Bibliographical note

Publisher Copyright:
© The Author(s) 2024.

Funding

We would like to extend our sincere gratitude to the laboratories that generously offered to contribute data for our study, even though, for various reasons, we were unable to incorporate it. Your willingness to collaborate and share your expertise is greatly appreciated, and we are pleased to note that your views are aligned with the most recent NIH policies and guidelines on data sharing. This work was supported by: R01DC020190, R01DC017166 and R01DC017166-04S1 to AAI; T32 DC000038 to CJB; R01DC018827 to GB and JEB; R01DC016365, R21DC020312 and N00014-18-1-2716 to BJW; ZIA DC-000079 to LLC; R01DC000188 and P50DC015857 to MCL; NIDCD DIR DC000096 to AB; R01DC021325 to ACV; R01DC014712 to MAR; DBR and UM were supported by the David F. and Margaret T. Grohne Family Foundation, Core Grant application NCI CCSG (CA014195), R01DC021075 and the CZI Imaging Scientist Award https://doi.org/10.37921/694870itnyzk from the Chan Zuckerberg Initiative DAF, an advised fund of Silicon Valley Community Foundation (funder https://doi.org/10.13039/100014989).

Funders	Funder number
Chan Zuckerberg Initiative
Silicon Valley Community Foundation
David F. and Margaret T. Grohne Family Foundation
National Institutes of Health (NIH)	ZIA DC-000079, T32 DC000038, R21DC020312, P50DC015857, R01DC000188, N00014-18-1-2716, R01DC016365, R01DC017166, R01DC020190, R01DC018827
National Institutes of Health (NIH)
National Childhood Cancer Registry – National Cancer Institute	R01DC021075, CA014195
National Childhood Cancer Registry – National Cancer Institute
National Institute on Deafness and Other Communication Disorders	R01DC014712, R01DC021325, DIR DC000096
National Institute on Deafness and Other Communication Disorders

ASJC Scopus subject areas

Statistics and Probability
Information Systems
Education
Computer Science Applications
Statistics, Probability and Uncertainty
Library and Information Sciences

Access to Document

10.1038/s41597-024-03218-y

Cite this

Buswinka, C. J., Rosenberg, D. B., Simikyan, R. G., Osgood, R. T., Fernandez, K., Nitta, H., Hayashi, Y., Liberman, L. W., Nguyen, E., Yildiz, E., Kim, J., Jarysta, A., Renauld, J., Wesson, E., Wang, H., Thapa, P., Bordiga, P., McMurtry, N., Llamas, J., ... Indzhykulian, A. A. (2024). Large-scale annotated dataset for cochlear hair cell detection and classification. Scientific data, 11(1), Article 416. https://doi.org/10.1038/s41597-024-03218-y

@article{2e77b9b36e9341fcb01d5a4c87d70243,

title = "Large-scale annotated dataset for cochlear hair cell detection and classification",

abstract = "Our sense of hearing is mediated by cochlear hair cells, of which there are two types organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains 5–15 thousand terminally differentiated hair cells, and their survival is essential for hearing as they do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. Machine learning can be used to automate the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, rat, guinea pig, pig, primate, and human cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 107,000 hair cells which have been identified and annotated as either inner or outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair-cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to give other hearing research groups the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.",

author = "Buswinka, \{Christopher J.\} and Rosenberg, \{David B.\} and Simikyan, \{Rubina G.\} and Osgood, \{Richard T.\} and Katharine Fernandez and Hidetomi Nitta and Yushi Hayashi and Liberman, \{Leslie W.\} and Emily Nguyen and Erdem Yildiz and Jinkyung Kim and Amandine Jarysta and Justine Renauld and Ella Wesson and Haobing Wang and Punam Thapa and Pierrick Bordiga and Noah McMurtry and Juan Llamas and Kitcher, \{Si{\^a}n R.\} and L{\'o}pez-Porras, \{Ana I.\} and Runjia Cui and Ghazaleh Behnammanesh and Bird, \{Jonathan E.\} and Angela Ballesteros and V{\'e}lez-Ortega, \{A. Catalina\} and Edge, \{Albert S.B.\} and Deans, \{Michael R.\} and Ksenia Gnedeva and Shrestha, \{Brikha R.\} and Uri Manor and Bo Zhao and Ricci, \{Anthony J.\} and Basile Tarchini and Basch, \{Mart{\'i}n L.\} and Ruben Stepanyan and Landegger, \{Lukas D.\} and Rutherford, \{Mark A.\} and Liberman, \{M. Charles\} and Walters, \{Bradley J.\} and Kros, \{Corn{\'e} J.\} and Richardson, \{Guy P.\} and Cunningham, \{Lisa L.\} and Indzhykulian, \{Artur A.\}",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = dec,

doi = "10.1038/s41597-024-03218-y",

language = "English",

volume = "11",

journal = "Scientific data",

issn = "2052-4463",

publisher = "Nature Research",

number = "1",

}

Buswinka, CJ, Rosenberg, DB, Simikyan, RG, Osgood, RT, Fernandez, K, Nitta, H, Hayashi, Y, Liberman, LW, Nguyen, E, Yildiz, E, Kim, J, Jarysta, A, Renauld, J, Wesson, E, Wang, H, Thapa, P, Bordiga, P, McMurtry, N, Llamas, J, Kitcher, SR, López-Porras, AI, Cui, R, Behnammanesh, G, Bird, JE, Ballesteros, A, Vélez-Ortega, AC, Edge, ASB, Deans, MR, Gnedeva, K, Shrestha, BR, Manor, U, Zhao, B, Ricci, AJ, Tarchini, B, Basch, ML, Stepanyan, R, Landegger, LD, Rutherford, MA, Liberman, MC, Walters, BJ, Kros, CJ, Richardson, GP, Cunningham, LL & Indzhykulian, AA 2024, 'Large-scale annotated dataset for cochlear hair cell detection and classification', Scientific data, vol. 11, no. 1, 416. https://doi.org/10.1038/s41597-024-03218-y

TY - JOUR

T1 - Large-scale annotated dataset for cochlear hair cell detection and classification

AU - Buswinka, Christopher J.

AU - Rosenberg, David B.

AU - Simikyan, Rubina G.

AU - Osgood, Richard T.

AU - Fernandez, Katharine

AU - Nitta, Hidetomi

AU - Hayashi, Yushi

AU - Liberman, Leslie W.

AU - Nguyen, Emily

AU - Yildiz, Erdem

AU - Kim, Jinkyung

AU - Jarysta, Amandine

AU - Renauld, Justine

AU - Wesson, Ella

AU - Wang, Haobing

AU - Thapa, Punam

AU - Bordiga, Pierrick

AU - McMurtry, Noah

AU - Llamas, Juan

AU - Kitcher, Siân R.

AU - López-Porras, Ana I.

AU - Cui, Runjia

AU - Behnammanesh, Ghazaleh

AU - Bird, Jonathan E.

AU - Ballesteros, Angela

AU - Vélez-Ortega, A. Catalina

AU - Edge, Albert S.B.

AU - Deans, Michael R.

AU - Gnedeva, Ksenia

AU - Shrestha, Brikha R.

AU - Manor, Uri

AU - Zhao, Bo

AU - Ricci, Anthony J.

AU - Tarchini, Basile

AU - Basch, Martín L.

AU - Stepanyan, Ruben

AU - Landegger, Lukas D.

AU - Rutherford, Mark A.

AU - Liberman, M. Charles

AU - Walters, Bradley J.

AU - Kros, Corné J.

AU - Richardson, Guy P.

AU - Cunningham, Lisa L.

AU - Indzhykulian, Artur A.

PY - 2024/12

Y1 - 2024/12

N2 - Our sense of hearing is mediated by cochlear hair cells, of which there are two types organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains 5–15 thousand terminally differentiated hair cells, and their survival is essential for hearing as they do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. Machine learning can be used to automate the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, rat, guinea pig, pig, primate, and human cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 107,000 hair cells which have been identified and annotated as either inner or outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair-cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to give other hearing research groups the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.

AB - Our sense of hearing is mediated by cochlear hair cells, of which there are two types organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains 5–15 thousand terminally differentiated hair cells, and their survival is essential for hearing as they do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. Machine learning can be used to automate the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, rat, guinea pig, pig, primate, and human cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 107,000 hair cells which have been identified and annotated as either inner or outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair-cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to give other hearing research groups the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.

UR - https://www.scopus.com/pages/publications/85191196311

UR - https://www.scopus.com/inward/citedby.url?scp=85191196311&partnerID=8YFLogxK

U2 - 10.1038/s41597-024-03218-y

DO - 10.1038/s41597-024-03218-y

M3 - Article

C2 - 38653806

AN - SCOPUS:85191196311

SN - 2052-4463

VL - 11

JO - Scientific data

JF - Scientific data

IS - 1

M1 - 416

ER -

Large-scale annotated dataset for cochlear hair cell detection and classification

Abstract

Bibliographical note

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this