Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma

M. Hossein Jafari, Ebrahim Nasr-Esfahani, Nader Karimi, S. M Reza Soroushmehr, Shadrokh Samavi, Kayvan Najarian

Research output: Contribution to journalArticle

Abstract

Purpose: Computerized prescreening of suspicious moles and lesions for malignancy is of great importance for assessing the need and the priority of the removal surgery. Detection can be done by images captured by standard cameras, which are more preferable due to low cost and availability. One important step in computerized evaluation is accurate detection of lesion’s region, i.e., segmentation of an image into two regions as lesion and normal skin. Methods: In this paper, a new method based on deep neural networks is proposed for accurate extraction of a lesion region. The input image is preprocessed, and then, its patches are fed to a convolutional neural network. Local texture and global structure of the patches are processed in order to assign pixels to lesion or normal classes. A method for effective selection of training patches is proposed for more accurate detection of a lesion’s border. Results: Our results indicate that the proposed method could reach the accuracy of 98.7% and the sensitivity of 95.2% in segmentation of lesion regions over the dataset of clinical images. Conclusion: The experimental results of qualitative and quantitative evaluations demonstrate that our method can outperform other state-of-the-art algorithms exist in the literature.

Original languageEnglish (US)
Pages (from-to)1-10
Number of pages10
JournalInternational Journal of Computer Assisted Radiology and Surgery
DOIs
StateAccepted/In press - Mar 24 2017

Fingerprint

Melanoma
Skin
Costs and Cost Analysis
Datasets

Keywords

  • Convolutional neural network
  • Deep learning
  • Medical image segmentation
  • Melanoma excision
  • Skin cancer

ASJC Scopus subject areas

  • Surgery
  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma. / Jafari, M. Hossein; Nasr-Esfahani, Ebrahim; Karimi, Nader; Soroushmehr, S. M Reza; Samavi, Shadrokh; Najarian, Kayvan.

In: International Journal of Computer Assisted Radiology and Surgery, 24.03.2017, p. 1-10.

Research output: Contribution to journalArticle

Jafari, M. Hossein; Nasr-Esfahani, Ebrahim; Karimi, Nader; Soroushmehr, S. M Reza; Samavi, Shadrokh; Najarian, Kayvan / Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma.

In: International Journal of Computer Assisted Radiology and Surgery, 24.03.2017, p. 1-10.

Research output: Contribution to journalArticle

@article{fab7cb89b812463d8f32c6fa6eab5a5f,
title = "Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma",
abstract = "Purpose: Computerized prescreening of suspicious moles and lesions for malignancy is of great importance for assessing the need and the priority of the removal surgery. Detection can be done by images captured by standard cameras, which are more preferable due to low cost and availability. One important step in computerized evaluation is accurate detection of lesion’s region, i.e., segmentation of an image into two regions as lesion and normal skin. Methods: In this paper, a new method based on deep neural networks is proposed for accurate extraction of a lesion region. The input image is preprocessed, and then, its patches are fed to a convolutional neural network. Local texture and global structure of the patches are processed in order to assign pixels to lesion or normal classes. A method for effective selection of training patches is proposed for more accurate detection of a lesion’s border. Results: Our results indicate that the proposed method could reach the accuracy of 98.7% and the sensitivity of 95.2% in segmentation of lesion regions over the dataset of clinical images. Conclusion: The experimental results of qualitative and quantitative evaluations demonstrate that our method can outperform other state-of-the-art algorithms exist in the literature.",
keywords = "Convolutional neural network, Deep learning, Medical image segmentation, Melanoma excision, Skin cancer",
author = "Jafari, {M. Hossein} and Ebrahim Nasr-Esfahani and Nader Karimi and Soroushmehr, {S. M Reza} and Shadrokh Samavi and Kayvan Najarian",
year = "2017",
month = "3",
doi = "10.1007/s11548-017-1567-8",
pages = "1--10",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma

AU - Jafari,M. Hossein

AU - Nasr-Esfahani,Ebrahim

AU - Karimi,Nader

AU - Soroushmehr,S. M Reza

AU - Samavi,Shadrokh

AU - Najarian,Kayvan

PY - 2017/3/24

Y1 - 2017/3/24

N2 - Purpose: Computerized prescreening of suspicious moles and lesions for malignancy is of great importance for assessing the need and the priority of the removal surgery. Detection can be done by images captured by standard cameras, which are more preferable due to low cost and availability. One important step in computerized evaluation is accurate detection of lesion’s region, i.e., segmentation of an image into two regions as lesion and normal skin. Methods: In this paper, a new method based on deep neural networks is proposed for accurate extraction of a lesion region. The input image is preprocessed, and then, its patches are fed to a convolutional neural network. Local texture and global structure of the patches are processed in order to assign pixels to lesion or normal classes. A method for effective selection of training patches is proposed for more accurate detection of a lesion’s border. Results: Our results indicate that the proposed method could reach the accuracy of 98.7% and the sensitivity of 95.2% in segmentation of lesion regions over the dataset of clinical images. Conclusion: The experimental results of qualitative and quantitative evaluations demonstrate that our method can outperform other state-of-the-art algorithms exist in the literature.

AB - Purpose: Computerized prescreening of suspicious moles and lesions for malignancy is of great importance for assessing the need and the priority of the removal surgery. Detection can be done by images captured by standard cameras, which are more preferable due to low cost and availability. One important step in computerized evaluation is accurate detection of lesion’s region, i.e., segmentation of an image into two regions as lesion and normal skin. Methods: In this paper, a new method based on deep neural networks is proposed for accurate extraction of a lesion region. The input image is preprocessed, and then, its patches are fed to a convolutional neural network. Local texture and global structure of the patches are processed in order to assign pixels to lesion or normal classes. A method for effective selection of training patches is proposed for more accurate detection of a lesion’s border. Results: Our results indicate that the proposed method could reach the accuracy of 98.7% and the sensitivity of 95.2% in segmentation of lesion regions over the dataset of clinical images. Conclusion: The experimental results of qualitative and quantitative evaluations demonstrate that our method can outperform other state-of-the-art algorithms exist in the literature.

KW - Convolutional neural network

KW - Deep learning

KW - Medical image segmentation

KW - Melanoma excision

KW - Skin cancer

UR - http://www.scopus.com/inward/record.url?scp=85015983521&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015983521&partnerID=8YFLogxK

U2 - 10.1007/s11548-017-1567-8

DO - 10.1007/s11548-017-1567-8

M3 - Article

SP - 1

EP - 10

JO - Computer-Assisted Radiology and Surgery

T2 - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

ER -