An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index

S. Lakshmi, Deepu Vijayasenan, David S. Sumam, Saraswathy Sreeram, Pooja K. Suresh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Ki-67 labeling index is a widely used biomarker for the diagnosis and monitoring of cancer. Many automated techniques have been proposed for evaluating Ki-67 index. In this paper, we introduce an integrated deep learning based approach. We use MobileUnet model for segmentation and classification and connected component based algorithm for the estimation of Ki-67 index in bladder cancer cases. The average F1 score is 0.92 and dice score is 0.96. The mean absolute error in the evaluated Ki-67 index is 2.1. We also explore possible pre-processing steps to generalize the segmentation model to at least one another type of cancer. Histogram matching and re-sizing improve the performance in breast cancer data by 12% in F1 score and 8% in dice score.

Original languageEnglish
Title of host publicationProceedings of the TENCON 2019
Subtitle of host publicationTechnology, Knowledge, and Society
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2310-2314
Number of pages5
ISBN (Electronic)9781728118956
DOIs
Publication statusPublished - 10-2019
Event2019 IEEE Region 10 Conference: Technology, Knowledge, and Society, TENCON 2019 - Kerala, India
Duration: 17-10-201920-10-2019

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume2019-October
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2019 IEEE Region 10 Conference: Technology, Knowledge, and Society, TENCON 2019
CountryIndia
CityKerala
Period17-10-1920-10-19

Fingerprint

Labeling
Biomarkers
Monitoring
Processing
Deep learning

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Lakshmi, S., Vijayasenan, D., Sumam, D. S., Sreeram, S., & Suresh, P. K. (2019). An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index. In Proceedings of the TENCON 2019: Technology, Knowledge, and Society (pp. 2310-2314). [8929640] (IEEE Region 10 Annual International Conference, Proceedings/TENCON; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TENCON.2019.8929640
Lakshmi, S. ; Vijayasenan, Deepu ; Sumam, David S. ; Sreeram, Saraswathy ; Suresh, Pooja K. / An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index. Proceedings of the TENCON 2019: Technology, Knowledge, and Society. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 2310-2314 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).
@inproceedings{1b4f79364cfa4acfa4366899f8a6739e,
title = "An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index",
abstract = "Ki-67 labeling index is a widely used biomarker for the diagnosis and monitoring of cancer. Many automated techniques have been proposed for evaluating Ki-67 index. In this paper, we introduce an integrated deep learning based approach. We use MobileUnet model for segmentation and classification and connected component based algorithm for the estimation of Ki-67 index in bladder cancer cases. The average F1 score is 0.92 and dice score is 0.96. The mean absolute error in the evaluated Ki-67 index is 2.1. We also explore possible pre-processing steps to generalize the segmentation model to at least one another type of cancer. Histogram matching and re-sizing improve the performance in breast cancer data by 12{\%} in F1 score and 8{\%} in dice score.",
author = "S. Lakshmi and Deepu Vijayasenan and Sumam, {David S.} and Saraswathy Sreeram and Suresh, {Pooja K.}",
year = "2019",
month = "10",
doi = "10.1109/TENCON.2019.8929640",
language = "English",
series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2310--2314",
booktitle = "Proceedings of the TENCON 2019",
address = "United States",

}

Lakshmi, S, Vijayasenan, D, Sumam, DS, Sreeram, S & Suresh, PK 2019, An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index. in Proceedings of the TENCON 2019: Technology, Knowledge, and Society., 8929640, IEEE Region 10 Annual International Conference, Proceedings/TENCON, vol. 2019-October, Institute of Electrical and Electronics Engineers Inc., pp. 2310-2314, 2019 IEEE Region 10 Conference: Technology, Knowledge, and Society, TENCON 2019, Kerala, India, 17-10-19. https://doi.org/10.1109/TENCON.2019.8929640

An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index. / Lakshmi, S.; Vijayasenan, Deepu; Sumam, David S.; Sreeram, Saraswathy; Suresh, Pooja K.

Proceedings of the TENCON 2019: Technology, Knowledge, and Society. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2310-2314 8929640 (IEEE Region 10 Annual International Conference, Proceedings/TENCON; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index

AU - Lakshmi, S.

AU - Vijayasenan, Deepu

AU - Sumam, David S.

AU - Sreeram, Saraswathy

AU - Suresh, Pooja K.

PY - 2019/10

Y1 - 2019/10

N2 - Ki-67 labeling index is a widely used biomarker for the diagnosis and monitoring of cancer. Many automated techniques have been proposed for evaluating Ki-67 index. In this paper, we introduce an integrated deep learning based approach. We use MobileUnet model for segmentation and classification and connected component based algorithm for the estimation of Ki-67 index in bladder cancer cases. The average F1 score is 0.92 and dice score is 0.96. The mean absolute error in the evaluated Ki-67 index is 2.1. We also explore possible pre-processing steps to generalize the segmentation model to at least one another type of cancer. Histogram matching and re-sizing improve the performance in breast cancer data by 12% in F1 score and 8% in dice score.

AB - Ki-67 labeling index is a widely used biomarker for the diagnosis and monitoring of cancer. Many automated techniques have been proposed for evaluating Ki-67 index. In this paper, we introduce an integrated deep learning based approach. We use MobileUnet model for segmentation and classification and connected component based algorithm for the estimation of Ki-67 index in bladder cancer cases. The average F1 score is 0.92 and dice score is 0.96. The mean absolute error in the evaluated Ki-67 index is 2.1. We also explore possible pre-processing steps to generalize the segmentation model to at least one another type of cancer. Histogram matching and re-sizing improve the performance in breast cancer data by 12% in F1 score and 8% in dice score.

UR - http://www.scopus.com/inward/record.url?scp=85077723602&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077723602&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2019.8929640

DO - 10.1109/TENCON.2019.8929640

M3 - Conference contribution

AN - SCOPUS:85077723602

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

SP - 2310

EP - 2314

BT - Proceedings of the TENCON 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lakshmi S, Vijayasenan D, Sumam DS, Sreeram S, Suresh PK. An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index. In Proceedings of the TENCON 2019: Technology, Knowledge, and Society. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2310-2314. 8929640. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). https://doi.org/10.1109/TENCON.2019.8929640