Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/136857
Title: Automated characterization of diabetic foot using nonlinear features extracted from thermograms
Authors: Muhammad Adam
Ng, Eddie Yin Kwee
Oh, Shu Lih
Heng, Marabelle L.
Hagiwara, Yuki
Tan, Jen Hong
Tong, Jasper W. K.
Acharya, U. Rajendra
Keywords: Engineering::Mechanical engineering
Issue Date: 2018
Source: Muhammad Adam, Ng, E. Y. K., Oh, S. L., Heng, M. L., Hagiwara, Y., Tan, J. H., . . . Acharya, U. R. (2018). Automated characterization of diabetic foot using nonlinear features extracted from thermograms. Infrared Physics & Technology, 89, 325-337. doi:10.1016/j.infrared.2018.01.022
Journal: Infrared Physics and Technology 
Abstract: Diabetic foot is a major complication of diabetes mellitus (DM). The blood circulation to the foot decreases due to DM and hence, the temperature reduces in the plantar foot. Thermography is a non-invasive imaging method employed to view the thermal patterns using infrared (IR) camera. It allows qualitative and visual documentation of temperature fluctuation in vascular tissues. But it is difficult to diagnose these temperature changes manually. Thus, computer assisted diagnosis (CAD) system may help to accurately detect diabetic foot to prevent traumatic outcomes such as ulcerations and lower extremity amputation. In this study, plantar foot thermograms of 33 healthy persons and 33 individuals with type 2 diabetes are taken. These foot images are decomposed using discrete wavelet transform (DWT) and higher order spectra (HOS) techniques. Various texture and entropy features are extracted from the decomposed images. These combined (DWT + HOS) features are ranked using t-values and classified using support vector machine (SVM) classifier. Our proposed methodology achieved maximum accuracy of 89.39%, sensitivity of 81.81% and specificity of 96.97% using only five features. The performance of the proposed thermography-based CAD system can help the clinicians to take second opinion on their diagnosis of diabetic foot.
URI: https://hdl.handle.net/10356/136857
ISSN: 1350-4495
DOI: 10.1016/j.infrared.2018.01.022
Rights: © 2018 Elsevier B.V. All rights reserved. This paper was published in Infrared Physics and Technology and is made available with permission of Elsevier B.V.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:MAE Journal Articles

Files in This Item:
File Description SizeFormat 
Automated characterization of diabetic foot using nonlinear features extracted from.pdf4.2 MBAdobe PDFView/Open

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.