IJAR.2025.118
Type of Article: Original Research
Volume 13; Issue 1 (March 2025)
Page No.: 9172-9179
DOI: https://dx.doi.org/10.16965/ijar.2025.118
Advancing Foot Arch Diagnostics: A Comparison of plantar surface (PSA) index and convolution neural network (CNN) Deep Learning Models
Haripriya M 1, Vijayakumar S 2, Vijayakumar K *3.
1 Associate Professor, Department of Anatomy, Sri Ramachandra Institute of Higher Education and Research (SRIHER), Porur, Chennai, Tamil Nadu, India. ORCiD: https://orcid.org/0000-0001-6136-7576
2 Assistant Professor, Department of Anatomy, Sri Ramachandra Institute of Higher Education and Research (SRIHER), Porur, Chennai, Tamil Nadu, India. ORCiD: https://orcid.org/0000-0003-1672-6001
*3 Assistant Professor, Department of Anatomy, Symbiosis Medical College for Women (SMCW), Symbiosis International (Deemed University), Pune, Maharashtra, India. ORCiD: https://orcid.org/0000-0003-3032-8974
Corresponding Author: Vijayakumar K, Assistant Professor, Department of Anatomy, Symbiosis Medical College for Women (SMCW), Symbiosis International (Deemed University), Pune, India.
E-Mail: k.vijayakumar@smcw.siu.edu.in
ABSTRACT
Introduction: Accurate assessment of foot arch morphology is crucial for diagnosing and managing various musculoskeletal conditions. The objective of the study is to test and compare the ability of the plantar surface area (PSA) index and a convolutional neural network (CNN) deep learning model to classify various foot arches normal arched foot (NAF), (FAF) and high arched foot (HAF) from plantar scan images.
Methodology: This is a comparative study in which a total of 896 male participants, aged 25–45, were randomly selected and evaluated for foot arch classification into three categories: NAF, FAF, and HAF. 360 images were taken to train, test and validate the CNN model. The PSA index method involved traditional footprint analysis using a self-designed foot scanner, while the CNN model was trained on a dataset of foot images to automate classification.
Results: Descriptive statistics was used to tabulate the demographics, and the performance of CNN and PSA was done which showed 100% sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV); both approaches were able to classify all 130 instances in each category with flawless precision. For both approaches, there were no false positives (FP) or false negatives (FN) noted.
Conclusion: Future studies should develop hybrid models that harmonize anatomical precision and biomechanical accuracy with CNN efficiency paving the way to personalized medicine and real-time diagnostics. If these challenges are met, researchers would be able to fully leverage this interdisciplinary approach to affect both clinical practice and biomechanical work.
Key words: Foot arch classification, PSA index, Convolutional Neural Network, Deep learning, Biomechanics, Artificial intelligence.
REFERENCES
[1]. Ker RF, Bennett MB, Bibby SR, Kester RC, Alexander RMcN. The spring in the arch of the human foot. Nature. 1987 Jan;325(6100):147-9.
https://doi.org/10.1038/325147a0
PMid:3808070
[2]. HICKS JH. The mechanics of the foot. II. The plantar aponeurosis and the arch. J Anat. 1954 Jan;88(1):25-30.
[3]. Denyer JR, Hewitt NLA, Mitchell ACS. Foot Structure and Muscle Reaction Time to a Simulated Ankle Sprain. Journal of Athletic Training. 2013 May;48(3):326-30.
https://doi.org/10.4085/1062-6050-48.2.15
PMid:23675791 PMCid:PMC3655745
[4]. Riskowski JL, Dufour AB, Hagedorn TJ, Hillstrom HJ, Casey VA, Hannan MT. Associations of Foot Posture and Function to Lower Extremity Pain: Results From a Population-Based Foot Study. Arthritis Care & Research. 2013 Nov;65(11):1804-12.
https://doi.org/10.1002/acr.22049
PMid:24591410 PMCid:PMC4039193
[5]. Jahss MH. Spontaneous Rupture of the Tibialis Posterior Tendon: Clinical Findings, Tenographic Studies, and a New Technique of Repair. Foot & Ankle. 1982 Nov;3(3):158-66.
https://doi.org/10.1177/107110078200300308
PMid:7152401
[6]. Pfeiffer M, Kotz R, Ledl T, Hauser G, Sluga M. Prevalence of Flat Foot in Preschool-Aged Children. PEDIATRICS. 2006 Aug 1;118(2):634-9.
https://doi.org/10.1542/peds.2005-2126
PMid:16882817
[7]. Forriol F, Pascual J. Footprint Analysis Between Three and Seventeen Years of Age. Foot & Ankle. 1990 Oct;11(2):101-4.
https://doi.org/10.1177/107110079001100208
PMid:2265808
[8]. Vijayakumar K, Senthilkumar S, Chandratre S, Bharambe V. An analysis of arches of the foot: Grading the severity of pesplanus and pescavus using a newly designed podoscope and parameters. Journal of the Anatomical Society of India. 2021;70(2):85.
https://doi.org/10.4103/JASI.JASI_61_20
[9]. Barrington NAnn. Foot and ankle radiology. The Foot. 2004 Mar;14(1):58.
https://doi.org/10.1016/j.foot.2003.08.002
[10]. Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, et al. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Transactions on Medical Imaging. 2016 May;35(5):1285-98.
https://doi.org/10.1109/TMI.2016.2528162
PMid:26886976 PMCid:PMC4890616
[11]. Ali Khan H, Jue W, Mushtaq M, Umer Mushtaq M. Brain tumor classification in MRI image using convolutional neural network. Mathematical Biosciences and Engineering. 2020;17(5):6203-16.
https://doi.org/10.3934/mbe.2020328
PMid:33120595
[12]. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A Survey on Deep Learning in Medical Image Analysis. Medical Image Analysis. 2017 Dec;42(1):60-88.
https://doi.org/10.1016/j.media.2017.07.005
PMid:28778026
[13]. Potluri S, Ravuri S, Diedrich C, Schega L. Deep Learning based Gait Abnormality Detection using Wearable Sensor System. Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:3613-3619.
https://doi.org/10.1109/EMBC.2019.8856454
PMid:31946659
[14]. Vijayakumar K, Subramanian R, Senthilkumar S, Dineshkumar D. An Analysis of Arches of Foot: A Comparison between Ink Foot Print Method and Custom Made Podoscope Device Method. Journal of Pharmaceutical Research International. 2021 Jul 3;33(34B):249-56.
https://doi.org/10.9734/jpri/2021/v33i34B31866
[15]. Kim SK, Huh JH. Consistency of Medical Data Using Intelligent Neuron Faster R-CNN Algorithm for Smart Health Care Application. Healthcare. 2020 Jun 25;8(2):185.
https://doi.org/10.3390/healthcare8020185
PMid:32630436 PMCid:PMC7349395
[16]. Cho YS, Hong PC. Applying Machine Learning to Healthcare Operations Management: CNN-Based Model for Malaria Diagnosis. Healthcare [Internet]. 2023 Jan 1 [cited 2023 Aug 20];11(12):1779. Available from: https://www.mdpi.com/2227-9032/11/12/1779
https://doi.org/10.3390/healthcare11121779
PMid:37372897 PMCid:PMC10298712
[17]. Miller KL, Alfaro-Almagro F, Bangerter NK, Thomas DL, Yacoub E, Xu J, et al. Multimodal population brain imaging in the UK Biobank prospective epidemiological study. Nature neuroscience [Internet]. 2016 Nov 1;19(11):1523-36. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5086094/
https://doi.org/10.1038/nn.4393
PMid:27643430 PMCid:PMC5086094
[18]. Zhang H, Waldmann L, Manuel R, Henrik Boije, Tatjana Haitina, Amin Allalou. zOPT: an open source optical projection tomography system and methods for rapid 3D zebrafish imaging. Biomedical Optics Express. 2020 Jun 26;11(8):4290-0.
https://doi.org/10.1364/BOE.393519
PMid:32923043 PMCid:PMC7449731
[19]. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. arXiv (Cornell University). 2015 May 18;8(3).
[20]. Venkata Sushma Chinta et al., VSC et al.,. Investigation of Fracture Toughness of Bidirectional Jute / Epoxy Composite and Analysis by using FEA. International Journal of Mechanical and Production Engineering Research and Development. 2018;8(6):227-38.
https://doi.org/10.24247/ijmperddec201827
[21]. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level Classification of Skin Cancer with Deep Neural Networks. Nature [Internet]. 2017 Jan 25;542(7639):115-8. Available from: https://www.nature.com/articles/nature21056
https://doi.org/10.1038/nature21056
PMid:28117445 PMCid:PMC8382232
[22]. Balakrishnan A, Medikonda J, Namboothiri PK, Natarajan M. Role of Wearable Sensors with Machine Learning Approaches in Gait Analysis for Parkinson’s Disease Assessment: A Review. Engineered Science. 2022;8(1).
