Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis

Non-tumorous skin pigmentation disorders can have a huge negative emotional impact on patients. The correct diagnosis of these disorders is essential for proper treatments to be instituted. In this paper, we present a computerized method for classifying five non-tumorous skin pigmentation disorders...

Full description

Saved in:
Bibliographic Details
Main Authors: Liang, Yunfeng, Sun, Lei, Ser, Wee, Lin, Feng, Thng, Steven Tien Guan, Chen, Qiping, Lin, Zhiping
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/136676
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-136676
record_format dspace
spelling sg-ntu-dr.10356-1366762020-11-01T04:45:51Z Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis Liang, Yunfeng Sun, Lei Ser, Wee Lin, Feng Thng, Steven Tien Guan Chen, Qiping Lin, Zhiping School of Computer Science and Engineering School of Electrical and Electronic Engineering Interdisciplinary Graduate School (IGS) Engineering::Computer science and engineering Engineering::Electrical and electronic engineering V-PLDA Non-tumorous Non-tumorous skin pigmentation disorders can have a huge negative emotional impact on patients. The correct diagnosis of these disorders is essential for proper treatments to be instituted. In this paper, we present a computerized method for classifying five non-tumorous skin pigmentation disorders (i.e., freckles, lentigines, Hori's nevus, melasma and nevus of Ota) based on probabilistic linear discriminant analysis (PLDA). To address the large within-class variance problem with pigmentation images, a voting based PLDA (V-PLDA) approach is proposed. The proposed V-PLDA method is tested on a dataset that contains 150 real-world images taken from patients. It is shown that the proposed V-PLDA method obtains significantly higher classification accuracy (4% or more with p< 0.001 in the analysis of variance (ANOVA) test) than the original PLDA method, as well as several state-of-the-art image classification methods. To the authors' best knowledge, this is the first study that focuses on the non-tumorous skin pigmentation image classification problem. Therefore, this paper could provide a benchmark for subsequent research on this topic. Additionally, the proposed V-PLDA method demonstrates promising performance in clinical applications related to skin pigmentation disorders. Accepted version 2020-01-10T01:35:05Z 2020-01-10T01:35:05Z 2018 Journal Article Liang, Y., Sun, L., Lin, F., Thng, S. T. G., Chen, Q., & Lin, Z. (2018). Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis. Computers in Biology and Medicine, 99, 123-132. doi:10.1016/j.compbiomed.2018.05.026 1879-0534 https://hdl.handle.net/10356/136676 10.1016/j.compbiomed.2018.05.026 29909227 2-s2.0-85048420781 99 123 132 en Computers in Biology and Medicine © 2018 Elsevier Ltd. All rights reserved. This paper was published in Computers in Biology and Medicine and is made available with permission of Elsevier Ltd. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Engineering::Electrical and electronic engineering
V-PLDA
Non-tumorous
spellingShingle Engineering::Computer science and engineering
Engineering::Electrical and electronic engineering
V-PLDA
Non-tumorous
Liang, Yunfeng
Sun, Lei
Ser, Wee
Lin, Feng
Thng, Steven Tien Guan
Chen, Qiping
Lin, Zhiping
Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
description Non-tumorous skin pigmentation disorders can have a huge negative emotional impact on patients. The correct diagnosis of these disorders is essential for proper treatments to be instituted. In this paper, we present a computerized method for classifying five non-tumorous skin pigmentation disorders (i.e., freckles, lentigines, Hori's nevus, melasma and nevus of Ota) based on probabilistic linear discriminant analysis (PLDA). To address the large within-class variance problem with pigmentation images, a voting based PLDA (V-PLDA) approach is proposed. The proposed V-PLDA method is tested on a dataset that contains 150 real-world images taken from patients. It is shown that the proposed V-PLDA method obtains significantly higher classification accuracy (4% or more with p< 0.001 in the analysis of variance (ANOVA) test) than the original PLDA method, as well as several state-of-the-art image classification methods. To the authors' best knowledge, this is the first study that focuses on the non-tumorous skin pigmentation image classification problem. Therefore, this paper could provide a benchmark for subsequent research on this topic. Additionally, the proposed V-PLDA method demonstrates promising performance in clinical applications related to skin pigmentation disorders.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Liang, Yunfeng
Sun, Lei
Ser, Wee
Lin, Feng
Thng, Steven Tien Guan
Chen, Qiping
Lin, Zhiping
format Article
author Liang, Yunfeng
Sun, Lei
Ser, Wee
Lin, Feng
Thng, Steven Tien Guan
Chen, Qiping
Lin, Zhiping
author_sort Liang, Yunfeng
title Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
title_short Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
title_full Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
title_fullStr Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
title_full_unstemmed Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
title_sort classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
publishDate 2020
url https://hdl.handle.net/10356/136676
_version_ 1683494507594645504