Publication detail

An Imaging Method for Automated SkinLesion Segmentation using Statistical Analysis and Bit Plane Slicing

GUPTA, A. ISSAC, A. DUTTA, M. ŘÍHA, K.

Original Title

An Imaging Method for Automated SkinLesion Segmentation using Statistical Analysis and Bit Plane Slicing

English Title

An Imaging Method for Automated SkinLesion Segmentation using Statistical Analysis and Bit Plane Slicing

Type

conference paper

Language

en

Original Abstract

Melanoma can prove fatal if not diagnosed at early stage. Computer aided identification of diseases can equip normal people in performing a screening test of diseases. The accurate lesion segmentation plays a crucial role in correct diagnosis of skin diseases. This work proposes a skin lesion segmentation method using statistical analysis and bit plane slicing. Hole filling operation is competent enough to sufficiently reject the noisy pixels from the finally segmented image. The results of skin lesion segmentation obtained from the proposed algorithm has been compared with the annotated images available with the database. The results arepresented in form of overlapping score and correlation coefficient. An average overlapping score and correlation coefficient of 91.59% and 92.07%, respectively, is obtained from the proposed algorithm. Also, an image based performance analysis of segmented lesion has been done and an average sensitivity of 94.33% has been achieved. The results are convincing and suggests that the proposed work can be used for some real-time application.

English abstract

Melanoma can prove fatal if not diagnosed at early stage. Computer aided identification of diseases can equip normal people in performing a screening test of diseases. The accurate lesion segmentation plays a crucial role in correct diagnosis of skin diseases. This work proposes a skin lesion segmentation method using statistical analysis and bit plane slicing. Hole filling operation is competent enough to sufficiently reject the noisy pixels from the finally segmented image. The results of skin lesion segmentation obtained from the proposed algorithm has been compared with the annotated images available with the database. The results arepresented in form of overlapping score and correlation coefficient. An average overlapping score and correlation coefficient of 91.59% and 92.07%, respectively, is obtained from the proposed algorithm. Also, an image based performance analysis of segmented lesion has been done and an average sensitivity of 94.33% has been achieved. The results are convincing and suggests that the proposed work can be used for some real-time application.

Keywords

Medical Images; Dermoscopic Images; Skin Lesion;Melanoma; Statistical Analysis;

Released

09.02.2018

Publisher

IEEE

Location

GHAZIABAD, India

ISBN

978-1-5386-0886-9

Book

International Conference on "Computational Intelligence and Communication Technology"

Pages from

1

Pages to

5

Pages count

5

BibTex


@inproceedings{BUT150509,
  author="Ashmita {Gupta} and Ashish {Issac} and Malay Kishore {Dutta} and Kamil {Říha}",
  title="An Imaging Method for Automated SkinLesion Segmentation using Statistical Analysis and Bit Plane Slicing",
  annote="Melanoma can prove fatal if not diagnosed at early stage. Computer aided identification of diseases can equip normal people in performing a screening test of diseases. The accurate lesion segmentation plays a crucial role in correct diagnosis of skin diseases. This work proposes a skin lesion segmentation method using statistical analysis and bit plane slicing. Hole filling operation is competent enough to sufficiently reject the noisy pixels from the finally segmented image. The results of skin lesion segmentation obtained from the proposed algorithm has been compared with the annotated images available with the database. The results arepresented in form of overlapping score and correlation coefficient. An average overlapping score and correlation coefficient of 91.59% and 92.07%, respectively, is obtained from the proposed algorithm. Also, an image based performance analysis of segmented lesion has been done and an average sensitivity of 94.33% has been achieved. The results are convincing and suggests that the
proposed work can be used for some real-time application.",
  address="IEEE",
  booktitle="International Conference on "Computational Intelligence and Communication Technology"",
  chapter="150509",
  doi="10.1109/CIACT.2018.8480175",
  howpublished="online",
  institution="IEEE",
  year="2018",
  month="february",
  pages="1--5",
  publisher="IEEE",
  type="conference paper"
}