Combining Oversampling and Pretrained Feature Extractor For Classification Diabetic Foot Uclear Thermogram Images

I Wayan Jepriana; I Gede Bintang Arya Budaya; Gede Angga Pradipta; Putu Desiana Wulaning Ayu

doi:10.30595/juita.v12i2.23386

Authors

I Wayan Jepriana Institut Teknologi dan Bisnis STIKOM Bali
I Gede Bintang Arya Budaya Institut Teknologi dan Bisnis STIKOM Bali
Gede Angga Pradipta Magister Information System Institut Teknologi dan Bisnis STIKOM Bali
Putu Desiana Wulaning Ayu Institut Teknologi dan Bisnis STIKOM Bali

DOI:

https://doi.org/10.30595/juita.v12i2.23386

Keywords:

diabetic foot uclear, SMOTE, cost sensitive learning, machine learning, imbalanced data.

Abstract

Diabetic Foot Ulcers (DFUs) represent a significant health concern, often leading to severe complications if not diagnosed and treated promptly. Early and accurate classification of DFUs is crucial for effective patient management. However, In the realm of machine learning, the imbalanced data problem is a prevalent issue that arises when the classes in a dataset are not represented equally. This study proposes a novel approach to enhance the classification performance of DFU thermogram images by integrating oversampling techniques with pretrained feature extractors. This study use pretrained model method with InceptionV3 architecture to automatically obtain features in the DFU thermogram datasets. Overall, InceptionV3 as a feature extractor resulted in satisfactory performance, achieving an accuracy of 83.1% on non-diabetic data and 81.1% on diabetic data. Subsequently, the second experiment incorporated the oversampling technique SMOTE, leading to an improvement in performance, with accuracy rising to 98.1% on non-diabetic data and 96.1% on diabetic data. Finally, the SMOTE IPF method achieved accuracy of 98.7%, with a precision of 99.1% for the diabetic class and 98.7% for the non-diabetic class, a recall of 98.2% for the diabetic class and 98.1% for the non-diabetic class, and F-Measure of 98.1% for both the diabetic and non-diabetic classes.

Author Biographies

I Wayan Jepriana, Institut Teknologi dan Bisnis STIKOM Bali

Information System

I Gede Bintang Arya Budaya, Institut Teknologi dan Bisnis STIKOM Bali

Information Technology

Putu Desiana Wulaning Ayu, Institut Teknologi dan Bisnis STIKOM Bali

Magister of Information System

References

[1] J. Saminathan, M. Sasikala, V. B. Narayanamurthy, K. Rajesh, and R. Arvind, “Computer aided detection of diabetic foot ulcer using asymmetry analysis of texture and temperature features,” Infrared Phys Technol, vol. 105, no. January, p. 103219, 2020, doi: 10.1016/j.infrared.2020.103219.

[2] D. Hernandez-Contreras, H. Peregrina-Barreto, J. Rangel-Magdaleno, J. Ramirez-Cortes, and F. Renero-Carrillo, “Automatic classification of thermal patterns in diabetic foot based on morphological pattern spectrum,” Infrared Phys Technol, vol. 73, pp. 149–157, 2015, doi: 10.1016/j.infrared.2015.09.022.

[3] V. Filipe, P. Teixeira, and A. Teixeira, “Automatic Classification of Foot Thermograms Using Machine Learning Techniques,” Algorithms, vol. 15, no. 7, 2022, doi: 10.3390/a15070236.

[4] M. Adam, NG E, Oh S, Heng M, “Automated characterization of diabetic foot using nonlinear features extracted from thermograms,” Infrared Phys Technol, vol. 89, pp. 325–337, 2018, doi: 10.1016/j.infrared.2018.01.022.

[5] C. Evangeline N, S. Srinivasan, and E. Suresh, “Development of AI classification model for angiosome-wise interpretive substantiation of plantar feet thermal asymmetry in type 2 diabetic subjects using infrared thermograms,” J Therm Biol, vol. 110, no. February, p. 103370, 2022, doi: 10.1016/j.jtherbio.2022.103370.

[6] M. H. Alshayeji, S. ChandraBhasi Sindhu, and S. Abed, “Early detection of diabetic foot ulcers from thermal images using the bag of features technique,” Biomed Signal Process Control, vol. 79, no. P2, p. 104143, 2023, doi: 10.1016/j.bspc.2022.104143.

[7] J. J. Van Netten, M. Prijs, J. G. Van Baal, C. Liu, F. Van Der Heijden, and S. A. Bus, “Diagnostic values for skin temperature assessment to detect diabetes-related foot complications,” Diabetes Technol Ther, vol. 16, no. 11, pp. 714–721, 2014, doi: 10.1089/dia.2014.0052.

[8] M. H. Yap, Haciuma R, Alavi A, “Deep learning in diabetic foot ulcers detection: A comprehensive evaluation,” Comput Biol Med, vol. 135, p. 104596, 2021, doi: 10.1016/j.compbiomed.2021.104596.

[9] M. H. Yap, Classidy B, Byra M, “Diabetic foot ulcers segmentation challenge report: Benchmark and analysis,” Med Image Anal, vol. 94, p. 103153, 2024, doi: 10.1016/j.media.2024.103153.

[10] P. N. Thotad, G. R. Bharamagoudar, and B. S. Anami, “Diabetic foot ulcer detection using deep learning approaches,” Sensors International, vol. 4, no. October 2022, p. 100210, 2023, doi: 10.1016/j.sintl.2022.100210.

[11] M. H. Alshayeji, S. ChandraBhasi Sindhu, and S. Abed, “Early detection of diabetic foot ulcers from thermal images using the bag of features technique,” Biomed Signal Process Control, vol. 79, no. P2, p. 104143, 2023, doi: 10.1016/j.bspc.2022.104143.

[12] P. D. W. Ayu, G. A. Pradipta, R. R. Huizen, E. S. W. Kadek, and I. G. E. Artana, “Combining CNN Feature Extractors and Oversampling Safe Level SMOTE to Enhance Amniotic Fluid Ultrasound Image Classification,” International Journal of Intelligent Engineering and Systems, vol. 17, no. 1, pp. 251–262, 2024, doi: 10.22266/ijies2024.0229.24.

[13] G. A. Pradipta, R. Wardoyo, A. Musdholifah, and I. N. H. Sanjaya, “Radius-SMOTE: A New Oversampling Technique of Minority Samples Based on Radius Distance for Learning From Imbalanced Data,” IEEE Access, vol. 9, pp. 74763–74777, 2021, doi: 10.1109/access.2021.3080316.

[14] A. S. Ali Abdullah Yaser Issam Aljanabi, “Developing a convolutional neural network for classifying tumor images using Inception v3.” doi: 10.15587/1729-4061.2023.281227.

[15] N. L. Fitriyani, M. Syafrudin, G. Alfian, C. K. Yang, J. Rhee, and S. M. Ulyah, “Chronic Disease Prediction Model Using Integration of DBSCAN, SMOTE-ENN, and Random Forest,” 2022 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2022, pp. 289–294, 2022, doi: 10.1109/ICETSIS55481.2022.9888806.

[16] J. M. Johnson and T. M. Khoshgoftaar, “Cost-Sensitive Ensemble Learning for Highly Imbalanced Classification,” Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022, pp. 1427–1434, 2022, doi: 10.1109/ICMLA55696.2022.00225.

[17] U. S. Kumar, J. Simon, R. P. Vengaloor, and M. A. Elaveini, “Image Processing Techniques in Thermal and Non-thermal Images,” Lecture Notes in Networks and Systems, vol. 300 LNNS, no. January, pp. 533–544, 2022, doi: 10.1007/978-3-030-84760-9_45.

[18] G. Yadav, S. Maheshwari, and A. Agarwal, “Contrast limited adaptive histogram equalization based enhancement for real time video system,” Proceedings of the 2014 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2014, pp. 2392–2397, 2014, doi: 10.1109/ICACCI.2014.6968381.

[19] A. S. Ali Abdullah Yaser Issam Aljanabi, “Developing a convolutional neural network for classifying tumor images using Inception v3.” doi: 10.15587/1729-4061.2023.281227.

[20] M. Liang and W. Ahmad, “Breast Cancer Intelligent Diagnosis based on Subtractive Clustering Adaptive Neural Fuzzy Inference System and Information Gain,” 2017 International Conference on Computer Systems, Electronics and Control (ICCSEC), no. x, pp. 152–156, 2017.

[21] A. Ibáñez, C. Bielza, and P. Larrañaga, “Cost-sensitive selective naive Bayes classifiers for predicting the increase of the h-index for scientific journals,” Neurocomputing, vol. 135, pp. 42–52, 2014, doi: 10.1016/j.neucom.2013.08.042.

[22] Y. Chen, “Research on Cost-sensitive Classification Methods for Imbalanced Data,” Proceedings - 2021 International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2021, pp. 224–228, 2021, doi: 10.1109/CAIBDA53561.2021.00054.

[23] D. Devi, S. K. Biswas, and B. Purkayastha, “A Cost-sensitive weighted Random Forest Technique for Credit Card Fraud Detection,” 2019 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019, pp. 1–6, 2019, doi: 10.1109/ICCCNT45670.2019.8944885.

[24] P. D. W. Ayu and S. Hartati, “Pixel Classification Based on Local Gray Level Rectangle Window Sampling for Amniotic Fluid Segmentation,” International Journal of Intelligent Engineering and Systems, vol. 14, no. 1, pp. 420–432, 2021, doi: 10.22266/IJIES2021.0228.39.

[25] D. S. N. Ayu, P D W, Sri hartati, Aina Musdholifah, “Amniotic Fluids Classification Using Combination of Rules-Based and Random Forest Algorithm,” in Soft Computing in Data Science, Springer Nature, 2022, p. 15. doi: https://doi.org/10.1007/978-981-16-7334-4_20.