Automated Detection of Foot Tumor: A Machine Learning Approach Leveraging GLCM Texture Analysis
Abstract
Foot tumors are rare but diagnostically challenging due to overlapping symptoms with benign conditions. Automated image-based detection can aid early identification and reduce misdiagnosis. This study explores the use of GLCM-based feature extraction to classify foot magnetic resonance imaging, focusing on the presence or absence of tumors. The features were classified using logistic regression, decision tree, and random forest. Model performance was evaluated under a five-fold cross-validation framework with scaled features. Experimental results demonstrated strong classification performance, with all models achieving scores between 0.97 and 1.0 across defined metrics. Correlation analysis further revealed that homogeneity, energy, and angular second moment (ASM) had negative associations with the target, while other features showed positive correlations. These findings provide evidence that classical machine learning models, supported by feature engineering, are effective for the detection of foot tumors in absence and presence.
References
V. A. Singh, V. Sandhu, C. T. Yong, and N. F. Yasin, “Tumours of the foot: A 10 years retrospective analysis,” J. Orthop. Surg.,
vol. 32, no. 1, pp. 10225536241248706, 2024.
S. Rammelt, H. Fritzsche, C. Hofbauer, and others, “Malignant tumours of the foot and ankle,” Foot Ankle Surg., vol. 26, pp.
–370, 2020. Conference on electrical engineering, informatics, industrial technology and creative media 2025 102
A. Bhangu, J. A. S. Beard, and R. J. Grimer, “Should soft tissue sarcomas be treated at a specialist centre?,” Sarcoma, vol. 8, pp. 1–6, 2004.
H. Zwipp and S. Rammelt, “Tumoren des Fusses (foot tumours),” in Tscherne Unfallchirurgie Fuss, H. Zwipp and S. Rammelt, Eds. Heidelberg, Germany: Springer, 2014, pp. 755–770.
H. DeGroot III, “Approach to the management of soft tissue tumors of the foot and ankle,” Foot Ankle Spec., vol. 1, no. 3,
pp. 168–176, 2008.
A. K. Walling and S. I. Gasser, “Soft-tissue and bone tumors about the foot and ankle,” Clin. Sports Med., vol. 13, no. 4,
pp. 909–938, 1994.
M. O. Karaca, K. Bas¸arır, A. Merter, E. Acar, E. A. O¨ zbek, M. O¨ zyıldıran, and H. Y. Yıldız, “Malignant tumors of the foot and
ankle,” Foot Ankle Int., vol. 43, no. 9, pp. 1232–1241, 2022.
K. Suzuki, “Overview of deep learning in medical imaging,” Radiol. Phys. Technol., vol. 10, pp. 257–273, 2017.
L. ˇ Sajn and M. Kukar, “Image processing and machine learning for fully automated probabilistic evaluation of medical images,”
Comput. Methods Programs Biomed., vol. 104, no. 3, pp. e75–e86, 2011.
M. Nazir, S. Shakil, and K. Khurshid, “Role of deep learning in brain tumor detection and classification (2015 to 2020): A review,” Comput. Med. Imag. Graph., vol. 91, p. 101940, 2021.
S. Gull and S. Akbar, “Artificial intelligence in brain tumor detection through MRI scans: Advancements and challenges,” Artif. Intell. Internet Things, pp. 241–276, 2021.
S. Hossain, A. Chakrabarty, T. R. Gadekallu, M. Alazab, and M. J. Piran, “Vision transformers, ensemble model, and transfer learning leveraging explainable AI for brain tumor detection and classification,” IEEE J. Biomed. Health Inform., vol. 28, no. 3, pp. 1261–1272, 2023.
G. Kasinathan and S. Jayakumar, “Cloud-based lung tumor detection and stage classification using deep learning techniques,” Biomed. Res. Int., vol. 2022, no. 1, p. 4185835, 2022.
R. Y. Lee, Y. Wu, D. Goh, V. Tan, C. W. Ng, J. C. T. Lim, M. C. Lau, and J. P. S. Yeong, “Application of artificial intelligence to in vitro tumor modeling and characterization of the tumor microenvironment,” Adv. Healthcare Mater., vol. 12, no. 14, p. 2202457, 2023.
A. S. Vironicka and J. G. R. Sathiaseelan, “Texture feature extraction with medical image using GLCM and machine learning techniques,” ICTACT J. Image Video Process., vol. 12, no. 4, 2022.
M. Benco, R. Hudec, P. Kamencay, M. Zachariasova, and S. Matuska, “An advanced approach to extraction of colour texture features based on GLCM,” Int. J. Adv. Robot. Syst., vol. 11, no. 7, p. 104, 2014.
M. R. I. Hossain, I. Ahmed, and M. H. Kabir, “Automatic lung tumor detection based on GLCM features,” in Asian Conf. Comput. Vision, 2014, pp. 109–121.
N. Zulpe and V. Pawar, “GLCM textural features for brain tumor classification,” Int. J. Comput. Sci. Issues, vol. 9, no. 3,
p. 354, 2012.
G. Dheepak, D. Vaishali, and others, “Brain tumor classification: A novel approach integrating GLCM, LBP and composite features,” Front. Oncol., vol. 13, p. 1248452, 2024.
A. Toepfer, N. Harrasser, M. Recker, and others, “Distribution patterns of foot and ankle tumors: A university tumor institute experience,” BMC Cancer, vol. 18, p. 735, 2018.
A. Toepfer, “Tumors of the foot and ankle: A review of the principles of diagnostics and treatment,” Fuss Sprunggelenk, vol. 15, no. 2, pp. 82–96, 2017.
L. H. Wetzel and E. Levine, “Soft-tissue tumors of the foot: Value of MR imaging for specific diagnosis,” AJR Amer. J. Roentgenol., vol. 155, no. 5, pp. 1025–1030, 1990.
S. Waldt, H. Rechl, E. J. Rummeny, and others, “Imaging of benign and malignant soft tissue masses of the foot,” Eur. Radiol., vol. 13, pp. 1125–1136, 2003.
A. Mohseni, E. Ghotbi, F. Kazemi, A. Shababi, S. C. Jahan, A. Mohseni, and N. Shababi, “Artificial intelligence in radiology: What is its true role at present, and where is the evidence?,” Radiol. Clin., vol. 62, no. 6, pp. 935–947, 2024.
J. M. Boone, “Radiological interpretation 2020: Toward quantitative image assessment,” Med. Phys., vol. 34, no. 11, pp. 4173–4179, 2007.
W. Chen, Y. Zhang, X. Wang, and J. Liu, “Comparative analysis of imaging modalities for diagnosing musculoskeletal disorders,” J. Innov. Med. Res., vol. 3, no. 1, pp. 45–53, 2024.
D. S. Sule and R. Ampofo, “Diagnostic imaging techniques: Current trends and challenges,” Diagn. Adv. Precis. Med. Drug Develop., pp. 49–66, 2025.
D. Ballard and J. Sklansky, “Tumor detection in radiographs,” Comput. Biomed. Res., vol. 6, no. 4, pp. 299–321, 1973.
H.-X. Zhao, C.-X. Xia, H.-X. Yin, N. Guo, and Q. Zhu, “The value and limitations of contrast-enhanced transrectal ultrasonography for the detection of prostate cancer,” Eur. J. Radiol., vol. 82, no. 11, pp. e641–e647, 2013.
B. C. Jones and L. M. Fayad, “Musculoskeletal tumor imaging: Focus on emerging techniques,” Sem. Roentgenol., vol. 52, no.
, pp. 269–281, 2017.
V. Narayan, P. K. Mall, S. Awasthi, S. Srivastava, and A. Gupta, “FuzzyNet: Medical image classification based on GLCM texture
feature,” in Proc. Int. Conf. Artif. Intell. Smart Commun. (AISC), 2023, pp. 769–773.
B. Dhruv, N. Mittal, and M. Modi, “Study of Haralick’s and GLCM texture analysis on 3D medical images,” Int. J. Neurosci., vol. 129, no. 4, pp. 350–362, 2019.
P. Filipczuk, T. Fevens, A. Krzy˙zak, and A. Obuchowicz, “GLCM and GLRLM based texture features for computeraided breast cancer diagnosis,” J. Med. Inform. Technol., vol. 19, 2012.
M. Hall-Beyer, “GLCM texture: A tutorial v. 3.0 March 2017,” 2017.
S. S. Shirke, J. A. Kendule, and S. G. Vyawhare, “An approach for PCA and GLCM based MRI image classification,” in Techno-Societal 2016: Int. Conf. Adv. Technol. Soc. Appl., 2016, pp. 265–274.
A. M. Alqudah and A. Alqudah, “Improving machine learning recognition of colorectal cancer using 3D GLCM applied to different color spaces,” Multimed. Tools Appl., vol. 81, pp. 10839–10860, 2022.
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Waltham, MA: Elsevier, 2011. [Online]. Available: https://shop.elsevier.com/books/data-miningconcepts-and-techniques/han/978-0-12-381479-1
A. Reverter, W. Barris, S. McWilliam, K. A. Byrne, Y. H. Wang, S. H. Tan, N. Hudson, and B. P. Dalrymple, “Validation of alternative methods of data normalization in gene co-expression studies,” Bioinformatics, vol. 21, no. 7, pp. 1112–1120, 2004.
D. W. Hosmer, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression, 3rd ed. Hoboken, NJ: Wiley, 2013.
J. R. Quinlan, “Induction of decision trees,” Mach. Learn., vol. 1, no. 1, pp. 81–106, 1986.
L. Breiman, “Random forests,” Machine Learn., vol. 45, no. 1, pp. 5–32, 2001. Conference on electrical engineering, informatics, industrial technology and creative media 2025 103
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016, pp. 785–794.
I. Rish, “An empirical study of the naive Bayes classifier,” in Proc. IJCAI Workshop Empirical Methods AI, 2001.
T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Inf. Theory, vol. 13, no. 1, pp. 21–27, 1967.
C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.
D. M. W. Powers, “Evaluation: From precision, recall and Fmeasure to ROC, informedness, markedness and correlation,” J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011.
T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, 2006.
N. J. Nagelkerke, “A note on a general definition of the coefficient of determination,” Biometrika, vol. 78, no. 3, pp. 691–692, 1991.
F. Utaminingrum, A. M. Alqadri, I. K. Somawirata, C. Karim, A. Septiarini, C.-Y. Lin, and T. K. Shih, “Feature selection of gray-level Cooccurrence matrix using genetic algorithm with Extreme learning machine classification for early detection of Pole roads,” Results in Engineering, vol. 20, p. 101437, 2023.
D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, p. e623, 2021.
