Automatic Skin Lesion SegmentationA Novel Approach of Lesion Filling through Pixel Path

Title

Automatic Skin Lesion SegmentationA Novel Approach of Lesion Filling through Pixel Path

Creator

Nikesh P.; Raju G.

Description

Abstract: Lesion segmentation is a vital step in a melanoma recognition system. Many algorithms were developed for the efficient skin lesion segmentation. Most of them fails to realize a perfect segmentation. This paper proposes a novel, fully automatic system, for the lesion segmentation in dermatograms. The proposed approach executes in two steps. Selection of root seed is the first step. All the lesion pixels in the dermatogram are identified during the second step. Traversal through a predefined lesion pixel path ensures the reachability of all lesion pixels irrespective of the possible lesion discontinuity. The proposed algorithm is tested with two publically available dataset, PH2 and images of ISBI2016 challenge. Out of the six evaluation parameters, the proposed method shows the best values for specificity, accuracy, Hammuode distance and XOR. This confirms the merit of the proposal with respect to existing popular methods. 2020, Pleiades Publishing, Ltd.

Source

Pattern Recognition and Image Analysis, Vol-30, No. 4, pp. 815-826.

Date

2020-01-01

Publisher

Pleiades journals

Subject

directional seed; lesion filling; lesion pixel path; melanoma; most probable seed region

Coverage

Nikesh P., School of Computer Sciences, Mahathma Gandhi University, Kottayam, 686560, Kerala, India; Raju G., Department of Data Science, Christ (Deemed to be University), Lavasa Campus, Pune, 412112, Maharashtra, India

Rights

Restricted Access

Relation

ISSN: 10546618

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.1134/S1054661820040215

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099414961&doi=10.1134%2fS1054661820040215&partnerID=40&md5=81083b67874ade9ebbdaa26db8fbbd47