Diabetic Plantar Foot Segmentation in Active Thermography Using a Two-Stage Adaptive Gamma Transform and a Deep Neural Network

作者全名："Cao, Zhenjie; Zeng, Zhi; Xie, Jinfang; Zhai, Hao; Yin, Ying; Ma, Yue; Tian, Yibin"

作者地址："[Cao, Zhenjie; Ma, Yue; Tian, Yibin] Shenzhen Univ, Coll Mechatron & Control Engn, Shenzhen 518000, Peoples R China; [Cao, Zhenjie; Zeng, Zhi; Xie, Jinfang; Zhai, Hao] Chongqing Normal Univ, Coll Comp & Informat Sci, Chongqing 401331, Peoples R China; [Zeng, Zhi] Southern Med Univ, Shunde Hosp, Foshan 528000, Peoples R China; [Yin, Ying] Chongqing Med Univ, Dept Rheumatol & Immunol, Affiliated Hosp 2, Chongqing 400010, Peoples R China"

通信作者："Tian, YB (通讯作者)，Shenzhen Univ, Coll Mechatron & Control Engn, Shenzhen 518000, Peoples R China.; Zeng, Z (通讯作者)，Chongqing Normal Univ, Coll Comp & Informat Sci, Chongqing 401331, Peoples R China.; Zeng, Z (通讯作者)，Southern Med Univ, Shunde Hosp, Foshan 528000, Peoples R China."

来源：SENSORS

ESI学科分类：CHEMISTRY

WOS号：WOS:001089511600001

JCR分区：Q2

影响因子：3.4

年份：2023

卷号：23

期号：20

开始页：　

结束页：　

文献类型：Article

关键词：diabetic foot; active thermography; image segmentation; adaptive gamma transform; deep neural network

摘要："Pathological conditions in diabetic feet cause surface temperature variations, which can be captured quantitatively using infrared thermography. Thermal images captured during recovery of diabetic feet after active cooling may reveal richer information than those from passive thermography, but diseased foot regions may exhibit very small temperature differences compared with the surrounding area, complicating plantar foot segmentation in such cold-stressed active thermography. In this study, we investigate new plantar foot segmentation methods for thermal images obtained via cold-stressed active thermography without the complementary information from color or depth channels. To better deal with the temporal variations in thermal image contrast when planar feet are recovering from cold immersion, we propose an image pre-processing method using a two-stage adaptive gamma transform to alleviate the impact of such contrast variations. To improve upon existing deep neural networks for segmenting planar feet from cold-stressed infrared thermograms, a new deep neural network, the Plantar Foot Segmentation Network (PFSNet), is proposed to better extract foot contours. It combines the fundamental U-shaped network structure, a multi-scale feature extraction module, and a convolutional block attention module with a feature fusion network. The PFSNet, in combination with the two-stage adaptive gamma transform, outperforms multiple existing deep neural networks in plantar foot segmentation for single-channel infrared images from cold-stressed infrared thermography, achieving an accuracy of 97.3% and 95.4% as measured by Intersection over Union (IOU) and Dice Similarity Coefficient (DSC) respectively."

基金机构：Litemaze Technology provided some technical support for the project.

基金资助正文：Litemaze Technology provided some technical support for the project.