Deep networks with shape priors for nucleus detection

Mohammad Tofighi, Tiantong Guo, Jairam K.P. Vanamala, Vishal Monga

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

2 Citations (Scopus)

Abstract

Detection of cell nuclei in microscopic images is a challenging research topic, because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success shown by deep learning methods. These methods train for example convolutional neural networks (CNNs) with a training set of input images and known, labeled nuclei locations. Many of these methods are supplemented by spatial or morphological processing. We develop a new approach that we call Shape Priors with Convolutional Neural Networks (SP-CNN) to perform significantly enhanced nuclei detection. A set of canonical shapes is prepared with the help of a domain expert. Subsequently, we present a new network structure that can incorporate 'expected behavior' of nucleus shapes via two components: learnable layers that perform the nucleus detection and a fixed processing part that guides the learning with prior information. Analytically, we formulate a new regularization term that is targeted at penalizing false positives while simultaneously encouraging detection inside cell nucleus boundary. Experimental results on a challenging dataset reveal that SP-CNN is competitive with or outperforms several state-of-the-art methods.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages719-723
Number of pages5
ISBN (Electronic)9781479970612
DOIs
StatePublished - Aug 29 2018
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: Oct 7 2018Oct 10 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period10/7/1810/10/18

Fingerprint

Cells
Neural networks
Processing
Image quality
Deep learning

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Tofighi, M., Guo, T., Vanamala, J. K. P., & Monga, V. (2018). Deep networks with shape priors for nucleus detection. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 719-723). [8451797] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451797
Tofighi, Mohammad ; Guo, Tiantong ; Vanamala, Jairam K.P. ; Monga, Vishal. / Deep networks with shape priors for nucleus detection. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 719-723 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{70776771e1624e859e36d6a5be9cad22,
title = "Deep networks with shape priors for nucleus detection",
abstract = "Detection of cell nuclei in microscopic images is a challenging research topic, because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success shown by deep learning methods. These methods train for example convolutional neural networks (CNNs) with a training set of input images and known, labeled nuclei locations. Many of these methods are supplemented by spatial or morphological processing. We develop a new approach that we call Shape Priors with Convolutional Neural Networks (SP-CNN) to perform significantly enhanced nuclei detection. A set of canonical shapes is prepared with the help of a domain expert. Subsequently, we present a new network structure that can incorporate 'expected behavior' of nucleus shapes via two components: learnable layers that perform the nucleus detection and a fixed processing part that guides the learning with prior information. Analytically, we formulate a new regularization term that is targeted at penalizing false positives while simultaneously encouraging detection inside cell nucleus boundary. Experimental results on a challenging dataset reveal that SP-CNN is competitive with or outperforms several state-of-the-art methods.",
author = "Mohammad Tofighi and Tiantong Guo and Vanamala, {Jairam K.P.} and Vishal Monga",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451797",
language = "English (US)",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "719--723",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",
address = "United States",

}

Tofighi, M, Guo, T, Vanamala, JKP & Monga, V 2018, Deep networks with shape priors for nucleus detection. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451797, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 719-723, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 10/7/18. https://doi.org/10.1109/ICIP.2018.8451797

Deep networks with shape priors for nucleus detection. / Tofighi, Mohammad; Guo, Tiantong; Vanamala, Jairam K.P.; Monga, Vishal.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 719-723 8451797 (Proceedings - International Conference on Image Processing, ICIP).

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

TY - GEN

T1 - Deep networks with shape priors for nucleus detection

AU - Tofighi, Mohammad

AU - Guo, Tiantong

AU - Vanamala, Jairam K.P.

AU - Monga, Vishal

PY - 2018/8/29

Y1 - 2018/8/29

N2 - Detection of cell nuclei in microscopic images is a challenging research topic, because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success shown by deep learning methods. These methods train for example convolutional neural networks (CNNs) with a training set of input images and known, labeled nuclei locations. Many of these methods are supplemented by spatial or morphological processing. We develop a new approach that we call Shape Priors with Convolutional Neural Networks (SP-CNN) to perform significantly enhanced nuclei detection. A set of canonical shapes is prepared with the help of a domain expert. Subsequently, we present a new network structure that can incorporate 'expected behavior' of nucleus shapes via two components: learnable layers that perform the nucleus detection and a fixed processing part that guides the learning with prior information. Analytically, we formulate a new regularization term that is targeted at penalizing false positives while simultaneously encouraging detection inside cell nucleus boundary. Experimental results on a challenging dataset reveal that SP-CNN is competitive with or outperforms several state-of-the-art methods.

AB - Detection of cell nuclei in microscopic images is a challenging research topic, because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success shown by deep learning methods. These methods train for example convolutional neural networks (CNNs) with a training set of input images and known, labeled nuclei locations. Many of these methods are supplemented by spatial or morphological processing. We develop a new approach that we call Shape Priors with Convolutional Neural Networks (SP-CNN) to perform significantly enhanced nuclei detection. A set of canonical shapes is prepared with the help of a domain expert. Subsequently, we present a new network structure that can incorporate 'expected behavior' of nucleus shapes via two components: learnable layers that perform the nucleus detection and a fixed processing part that guides the learning with prior information. Analytically, we formulate a new regularization term that is targeted at penalizing false positives while simultaneously encouraging detection inside cell nucleus boundary. Experimental results on a challenging dataset reveal that SP-CNN is competitive with or outperforms several state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85062909090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062909090&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451797

DO - 10.1109/ICIP.2018.8451797

M3 - Conference contribution

AN - SCOPUS:85062909090

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 719

EP - 723

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

ER -

Tofighi M, Guo T, Vanamala JKP, Monga V. Deep networks with shape priors for nucleus detection. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 719-723. 8451797. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451797