TY - JOUR
T1 - A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images
AU - Ardhianto, Peter
AU - Subiakto, Raden Bagus Reinaldy
AU - Lin, Chih-Yang
AU - Jan, Yih-Kuen
AU - Liau, Ben-Yi
AU - Tsai, Jen-Yung
AU - Akbari, Veit Babak Hamun
AU - Lung, Chi-Wen
N1 - Funding Information:
This study was supported by a grant from the Ministry of Science and Technology of the Republic of China (MOST 110-2221-E-468-005, MOST 110-2637-E-241-002, and MOST 110-2221-E-155-039-MY3). The funding agency did not involve data collection, data analysis, and data interpretation. Data collection and sharing for this project were found SHUI-MU International Co., Ltd., Taiwan, which is available on the AIdea platform (https://aidea-web.tw (accessed on 13 March 2022)) provided by Industrial Technology Research Institute (ITRI) of Taiwan. The authors wish to express gratitude to Sunardi, Fahni Haris, Jifeng Wang, Taufiq Ismail, Jovi Sulistiawan, Wei-Cheng Shen, and Quanxin Lin for their assistance.
Funding Information:
Funding: This study was supported by a grant from the Ministry of Science and Technology of the Republic of China (MOST 110-2221-E-468-005, MOST 110-2637-E-241-002, and MOST 110-2221-E-155-039-MY3). The funding agency did not involve data collection, data analysis, and data interpretation.
Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2022/4/5
Y1 - 2022/4/5
N2 - Foot progression angle (FPA) analysis is one of the core methods to detect gait pathologies as basic information to prevent foot injury from excessive in-toeing and out-toeing. Deep learning-based object detection can assist in measuring the FPA through plantar pressure images. This study aims to establish a precision model for determining the FPA. The precision detection of FPA can provide information with in-toeing, out-toeing, and rearfoot kinematics to evaluate the effect of physical therapy programs on knee pain and knee osteoarthritis. We analyzed a total of 1424 plantar images with three different You Only Look Once (YOLO) networks: YOLO v3, v4, and v5x, to obtain a suitable model for FPA detection. YOLOv4 showed higher performance of the profile-box, with average precision in the left foot of 100.00% and the right foot of 99.78%, respectively. Besides, in detecting the foot angle-box, the ground-truth has similar results with YOLOv4 (5.58 ± 0.10
◦ vs. 5.86 ± 0.09
◦, p = 0.013). In contrast, there was a significant difference in FPA between ground-truth vs. YOLOv3 (5.58 ± 0.10
◦ vs. 6.07 ± 0.06
◦, p < 0.001), and ground-truth vs. YOLOv5x (5.58 ± 0.10
◦ vs. 6.75 ± 0.06
◦, p < 0.001). This result implies that deep learning with YOLOv4 can enhance the detection of FPA.
AB - Foot progression angle (FPA) analysis is one of the core methods to detect gait pathologies as basic information to prevent foot injury from excessive in-toeing and out-toeing. Deep learning-based object detection can assist in measuring the FPA through plantar pressure images. This study aims to establish a precision model for determining the FPA. The precision detection of FPA can provide information with in-toeing, out-toeing, and rearfoot kinematics to evaluate the effect of physical therapy programs on knee pain and knee osteoarthritis. We analyzed a total of 1424 plantar images with three different You Only Look Once (YOLO) networks: YOLO v3, v4, and v5x, to obtain a suitable model for FPA detection. YOLOv4 showed higher performance of the profile-box, with average precision in the left foot of 100.00% and the right foot of 99.78%, respectively. Besides, in detecting the foot angle-box, the ground-truth has similar results with YOLOv4 (5.58 ± 0.10
◦ vs. 5.86 ± 0.09
◦, p = 0.013). In contrast, there was a significant difference in FPA between ground-truth vs. YOLOv3 (5.58 ± 0.10
◦ vs. 6.07 ± 0.06
◦, p < 0.001), and ground-truth vs. YOLOv5x (5.58 ± 0.10
◦ vs. 6.75 ± 0.06
◦, p < 0.001). This result implies that deep learning with YOLOv4 can enhance the detection of FPA.
KW - YOLO
KW - object detection
KW - foot problems
KW - angle parameter
KW - foot clinic
UR - http://www.scopus.com/inward/record.url?scp=85127555196&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127555196&partnerID=8YFLogxK
U2 - 10.3390/s22072786
DO - 10.3390/s22072786
M3 - Article
C2 - 35408399
SN - 1424-8220
VL - 22
JO - Sensors (Basel, Switzerland)
JF - Sensors (Basel, Switzerland)
IS - 7
M1 - 2786
ER -