Investigating deep side layers for skin lesion segmentation

Behzad Bozorgtabar, Zongyuan Ge, Rajib Chakravorty, Mani Abedini, Sergey Demyanov, Rahil Garnavi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.

Original languageEnglish
Title of host publication2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
EditorsSimon Warfield, Arrate Munoz-Barrutia
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages256-260
Number of pages5
ISBN (Electronic)9781509011728
ISBN (Print)9781509011735
DOIs
Publication statusPublished - 15 Jun 2017
Externally publishedYes
EventIEEE International Symposium on Biomedical Imaging (ISBI) 2017 - Melbourne Convention and Exhibition Centre, Melbourne, Australia
Duration: 18 Apr 201721 Apr 2017
Conference number: 14th
http://biomedicalimaging.org/2017/

Conference

ConferenceIEEE International Symposium on Biomedical Imaging (ISBI) 2017
Abbreviated titleISBI 2017
CountryAustralia
CityMelbourne
Period18/04/1721/04/17
OtherISBI is a joint initiative from the IEEE Signal Processing Society (SPS) and the IEEE Engineering in Medicine and Biology Society (EMBS). The 2017 meeting will include tutorials, and a scientific program composed of plenary talks, invited special sessions, challenges, as well as oral and poster presentations of peer-reviewed papers.
Internet address

Keywords

  • Convolutional neural network
  • Fusion
  • Multi-layer net architectures
  • Skin lesion segmentation

Cite this

Bozorgtabar, B., Ge, Z., Chakravorty, R., Abedini, M., Demyanov, S., & Garnavi, R. (2017). Investigating deep side layers for skin lesion segmentation. In S. Warfield, & A. Munoz-Barrutia (Eds.), 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) (pp. 256-260). [7950514] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2017.7950514
Bozorgtabar, Behzad ; Ge, Zongyuan ; Chakravorty, Rajib ; Abedini, Mani ; Demyanov, Sergey ; Garnavi, Rahil. / Investigating deep side layers for skin lesion segmentation. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). editor / Simon Warfield ; Arrate Munoz-Barrutia. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 256-260
@inproceedings{c05e4d7571844e2d988ffa4ec4f3984d,
title = "Investigating deep side layers for skin lesion segmentation",
abstract = "Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.",
keywords = "Convolutional neural network, Fusion, Multi-layer net architectures, Skin lesion segmentation",
author = "Behzad Bozorgtabar and Zongyuan Ge and Rajib Chakravorty and Mani Abedini and Sergey Demyanov and Rahil Garnavi",
year = "2017",
month = "6",
day = "15",
doi = "10.1109/ISBI.2017.7950514",
language = "English",
isbn = "9781509011735",
pages = "256--260",
editor = "Simon Warfield and Munoz-Barrutia, {Arrate }",
booktitle = "2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Bozorgtabar, B, Ge, Z, Chakravorty, R, Abedini, M, Demyanov, S & Garnavi, R 2017, Investigating deep side layers for skin lesion segmentation. in S Warfield & A Munoz-Barrutia (eds), 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)., 7950514, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 256-260, IEEE International Symposium on Biomedical Imaging (ISBI) 2017, Melbourne, Australia, 18/04/17. https://doi.org/10.1109/ISBI.2017.7950514

Investigating deep side layers for skin lesion segmentation. / Bozorgtabar, Behzad; Ge, Zongyuan; Chakravorty, Rajib; Abedini, Mani; Demyanov, Sergey; Garnavi, Rahil.

2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). ed. / Simon Warfield; Arrate Munoz-Barrutia. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 256-260 7950514.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Investigating deep side layers for skin lesion segmentation

AU - Bozorgtabar, Behzad

AU - Ge, Zongyuan

AU - Chakravorty, Rajib

AU - Abedini, Mani

AU - Demyanov, Sergey

AU - Garnavi, Rahil

PY - 2017/6/15

Y1 - 2017/6/15

N2 - Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.

AB - Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.

KW - Convolutional neural network

KW - Fusion

KW - Multi-layer net architectures

KW - Skin lesion segmentation

UR - http://www.scopus.com/inward/record.url?scp=85023181428&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2017.7950514

DO - 10.1109/ISBI.2017.7950514

M3 - Conference Paper

SN - 9781509011735

SP - 256

EP - 260

BT - 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)

A2 - Warfield, Simon

A2 - Munoz-Barrutia, Arrate

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Bozorgtabar B, Ge Z, Chakravorty R, Abedini M, Demyanov S, Garnavi R. Investigating deep side layers for skin lesion segmentation. In Warfield S, Munoz-Barrutia A, editors, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 256-260. 7950514 https://doi.org/10.1109/ISBI.2017.7950514