Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques
Abstract
:1. Introduction
2. Research Significance
- Extraction and ranking of the relevant features from the temperature pixels for classifying the thermogram images into TCI-based classes.
- Explores the effect of various image enhancement techniques on thermogram images in improving the performance of 2D CNN models in TCI-based classes.
- Investigation of different ML classifiers with feature engineering for enhanced classification performance.
- Proposes a machine-learning framework that outperforms the DFTNet by a significant margin in classifying thermograms into TCI-based classes.
3. Methodology
3.1. Dataset Description
3.2. Image Pre-Processing
D CNN-Based Classification
3.3. Classical Machine Learning Approach
3.3.1. Feature Extraction and Reduction:
3.3.2. Feature Ranking
3.3.3. Classical Machine Learning Models
3.4. Performance Evaluation
4. Experimental Results
4.1. D CNN-Based Classification
4.2. Classical Machine Learning-Based Classification
5. Discussion
6. Conclusions
- The relevant features were extracted and ranked from the temperature pixels to classify the thermogram images into TCI-based classes. This is the best reported performance for a machine learning-based foot thermogram classification into different TCI-based classes.
- We explored the effect of various image enhancement techniques on thermogram images to improve the performance of 2D CNN models in TCI-based classes. It was found that the image enhancement techniques did not help to improve the performance, even for the state-of-the-art DFTNet proposed in [24].
- The classical ML classifier’s performance with carefully selected and refined features was exceptionally good compared to the performance of the 2D CNN models with/without image enhancement.
- The proposed machine-learning framework outperforms the DFTNet by a significant margin in classifying thermograms into TCI-based classes. The trained classical ML models can help in the classification using foot thermograms, which can be captured using infrared cameras.
- The performance reported uses a publicly available dataset, which has to be further validated for robustness with the help of a new dataset. The authors have already applied to the IRB to collect a new dataset.
- The dataset was collected using two different IR cameras (FLIR E60 and FLIR E6) with different resolutions [22]. However, the trained network is still able to find the distinguishing pattern, which confirms the robustness of different IR cameras, but this needs to be further validated with other IR cameras along with low-resolution IR cameras that are usable with mobile phones.
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Cho, N.; Kirigia, J.; Mbanya, J.; Ogurstova, K.; Guariguata, L.; Rathmann, W. IDF Diabetes Atlas-8th. Int. Diabetes Fed. 2015, 160. [Google Scholar]
- Sims, D.S., Jr.; Cavanagh, P.R.; Ulbrecht, J.S. Risk factors in the diabetic foot: Recognition and management. Phys. Ther. 1988, 68, 1887–1902. [Google Scholar] [CrossRef] [PubMed]
- Iversen, M.M.; Tell, G.S.; Riise, T.; Hanestad, B.R.; Østbye, T.; Graue, M.; Midthjell, K. History of foot ulcer increases mortality among individuals with diabetes: Ten-year follow-up of the Nord-Trøndelag Health Study, Norway. Diabetes Care 2009, 32, 2193–2199. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Reyzelman, A.M.; Koelewyn, K.; Murphy, M.; Shen, X.; Yu, E.; Pillai, R.; Fu, J.; Scholten, H.J.; Ma, R. Continuous temperature-monitoring socks for home use in patients with diabetes: Observational study. J. Med. Internet Res. 2018, 20, e12460. [Google Scholar] [CrossRef] [Green Version]
- Frykberg, R.G.; Gordon, I.L.; Reyzelman, A.M.; Cazzell, S.M.; Fitzgerald, R.H.; Rothenberg, G.M.; Bloom, J.D.; Petersen, B.J.; Linders, D.R.; Nouvong, A. Feasibility and efficacy of a smart mat technology to predict development of diabetic plantar ulcers. Diabetes Care 2017, 40, 973–980. [Google Scholar] [CrossRef] [Green Version]
- Inagaki Nagase, F.N. The Impact of Diabetic Foot Problems on Health-Related Quality of Life Of People with Diabetes. Master’s Thesis, University of Alberta, Edmonton, AB, Canada, 2017. [Google Scholar]
- Van Doremalen, R.F.; van Netten, J.J.; van Baal, J.G.; Vollenbroek-Hutten, M.M.; van der Heijden, F. Infrared 3D thermography for inflammation detection in diabetic foot disease: A proof of concept. J. Diabetes Sci. Technol. 2020, 14, 46–54. [Google Scholar] [CrossRef]
- Crisologo, P.A.; Lavery, L.A. Remote home monitoring to identify and prevent diabetic foot ulceration. Ann. Transl. Med. 2017, 5, 430. [Google Scholar] [CrossRef]
- He, Y.; Deng, B.; Wang, H.; Cheng, L.; Zhou, K.; Cai, S.; Ciampa, F. Infrared machine vision and infrared thermography with deep learning: A review. Infrared Phys. Technol. 2021, 116, 103754. [Google Scholar] [CrossRef]
- Hernandez-Contreras, D.; Peregrina-Barreto, H.; Rangel-Magdaleno, J.; Gonzalez-Bernal, J. Narrative review: Diabetic foot and infrared thermography. Infrared Phys. Technol. 2016, 78, 105–117. [Google Scholar] [CrossRef]
- Chan, A.W.; MacFarlane, I.A.; Bowsher, D.R. Contact thermography of painful diabetic neuropathic foot. Diabetes Care 1991, 14, 918–922. [Google Scholar] [CrossRef]
- Jones, B.F. A reappraisal of the use of infrared thermal image analysis in medicine. IEEE Trans. Med. Imaging 1998, 17, 1019–1027. [Google Scholar] [CrossRef]
- Kaabouch, N.; Chen, Y.; Anderson, J.; Ames, F.; Paulson, R. Asymmetry Analysis Based on Genetic Algorithms for the Prediction of Foot Ulcers. In Proceedings of Visualization and Data Analysis, San Jose, CA, USA, 19–20 January 2009; p. 724304. [Google Scholar]
- Kaabouch, N.; Chen, Y.; Hu, W.-C.; Anderson, J.W.; Ames, F.; Paulson, R. Enhancement of the asymmetry-based overlapping analysis through features extraction. J. Electron. Imaging 2011, 20, 013012. [Google Scholar] [CrossRef]
- Liu, C.; van Netten, J.J.; Van Baal, J.G.; Bus, S.A.; van Der Heijden, F. Automatic detection of diabetic foot complications with infrared thermography by asymmetric analysis. J. Biomed. Opt. 2015, 20, 026003. [Google Scholar] [CrossRef] [Green Version]
- Hernandez-Contreras, D.; Peregrina-Barreto, H.; Rangel-Magdaleno, J.; Ramirez-Cortes, J.; Renero-Carrillo, F. Automatic classification of thermal patterns in diabetic foot based on morphological pattern spectrum. Infrared Phys. Technol. 2015, 73, 149–157. [Google Scholar] [CrossRef]
- Hernandez-Contreras, D.; Peregrina-Barreto, H.; Rangel-Magdaleno, J.; Gonzalez-Bernal, J.; Altamirano-Robles, L. A quantitative index for classification of plantar thermal changes in the diabetic foot. Infrared Phys. Technol. 2017, 81, 242–249. [Google Scholar] [CrossRef]
- Hernandez-Contreras, D.A.; Peregrina-Barreto, H.; Rangel-Magdaleno, J.D.J.; Orihuela-Espina, F. Statistical approximation of plantar temperature distribution on diabetic subjects based on beta mixture model. IEEE Access 2019, 7, 28383–28391. [Google Scholar] [CrossRef]
- Kamavisdar, P.; Saluja, S.; Agrawal, S. A survey on image classification approaches and techniques. Int. J. Adv. Res. Comput. Commun. Eng. 2013, 2, 1005–1009. [Google Scholar]
- Ren, J. ANN vs. SVM: Which one performs better in classification of MCCs in mammogram imaging. Knowl. Based Syst. 2012, 26, 144–153. [Google Scholar] [CrossRef] [Green Version]
- Lu, D.; Weng, Q. A survey of image classification methods and techniques for improving classification performance. Int. J. Remote Sens. 2007, 28, 823–870. [Google Scholar] [CrossRef]
- Hernandez-Contreras, D.A.; Peregrina-Barreto, H.; de Jesus Rangel-Magdaleno, J.; Renero-Carrillo, F.J. Plantar thermogram database for the study of diabetic foot complications. IEEE Access 2019, 7, 161296–161307. [Google Scholar] [CrossRef]
- Khandakar, A.; Chowdhury, M.E.; Reaz, M.B.I.; Ali, S.H.M.; Hasan, M.A.; Kiranyaz, S.; Rahman, T.; Alfkey, R.; Bakar, A.A.A.; Malik, R.A. A machine learning model for early detection of diabetic foot using thermogram images. Comput. Biol. Med. 2021, 137, 104838. [Google Scholar] [CrossRef] [PubMed]
- Cruz-Vega, I.; Hernandez-Contreras, D.; Peregrina-Barreto, H.; Rangel-Magdaleno, J.d.J.; Ramirez-Cortes, J.M. Deep Learning Classification for Diabetic Foot Thermograms. Sensors 2020, 20, 1762. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Tawsifur Rahman, A.K.; Qiblawey, Y.; Tahir, A.; Kiranyaz, S.; Saad, M.T.I.; Kashem, B.A.; Al Maadeed, S.; Zughaier, S.M.; Chowdhury, M.E.H.; Khan, M.S. Exploring the Effect of Image Enhancement Techniques on COVID-19 Detection using Chest X-rays Images. arXiv 2020, arXiv:2012.02238. [Google Scholar]
- Taylor, G.I.; Palmer, J.H. Angiosome theory. Br. J. Plast. Surg. 1992, 45, 327–328. [Google Scholar] [CrossRef]
- Cajacuri, L.A.V. Early Diagnostic of Diabetic Foot Using Thermal Images. Ph.D. Thesis, Université D’Orléans, Orléans, France, 2013. [Google Scholar]
- Flir, T. How Does Emissivity Affect Thermal Imaging? Available online: https://www.flir.eu/discover/professional-tools/how-does-emissivity-affect-thermal-imaging/ (accessed on 8 January 2022).
- Zimmerman, J.B.; Pizer, S.M.; Staab, E.V.; Perry, J.R.; McCartney, W.; Brenton, B.C. An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement. IEEE Trans. Med. Imaging 1988, 7, 304–312. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Chowdhury, M.E.; Rahman, T.; Khandakar, A.; Mazhar, R.; Kadir, M.A.; Mahbub, Z.B.; Islam, K.R.; Khan, M.S.; Iqbal, A.; Al-Emadi, N. Can AI help in screening viral and COVID-19 pneumonia? IEEE Access 2020, 8, 132665–132676. [Google Scholar] [CrossRef]
- Tahir, A.; Qiblawey, Y.; Khandakar, A.; Rahman, T.; Khurshid, U.; Musharavati, F.; Kiranyaz, S.; Chowdhury, M.E. Coronavirus: Comparing COVID-19, SARS and MERS in the eyes of AI. arXiv 2020, arXiv:2005.11524. [Google Scholar]
- Rahman, T.; Khandakar, A.; Kadir, M.A.; Islam, K.R.; Islam, K.F.; Mazhar, R.; Hamid, T.; Islam, M.T.; Kashem, S.; Mahbub, Z.B. Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization. IEEE Access 2020, 8, 191586–191601. [Google Scholar] [CrossRef]
- Rahman, T.; Chowdhury, M.E.; Khandakar, A.; Islam, K.R.; Islam, K.F.; Mahbub, Z.B.; Kadir, M.A.; Kashem, S. Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection using Chest X-ray. Appl. Sci. 2020, 10, 3233. [Google Scholar] [CrossRef]
- Anwar, S.M.; Majid, M.; Qayyum, A.; Awais, M.; Alnowami, M.; Khan, M.K. Medical image analysis using convolutional neural networks: A review. J. Med. Syst. 2018, 42, 226. [Google Scholar] [CrossRef] [Green Version]
- Deng, J.; Dong, W.; Socher, R.; Li, L.-J.; Li, K.; Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 20–25 June 2009; pp. 248–255. [Google Scholar]
- Mishra, M.; Menon, H.; Mukherjee, A. Characterization of $ S_1 $ and $ S_2 $ Heart Sounds Using Stacked Autoencoder and Convolutional Neural Network. IEEE Trans. Instrum. Meas. 2018, 68, 3211–3220. [Google Scholar] [CrossRef]
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 2818–2826. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 4510–4520. [Google Scholar]
- Saminathan, J.; Sasikala, M.; Narayanamurthy, V.; Rajesh, K.; Arvind, R. Computer aided detection of diabetic foot ulcer using asymmetry analysis of texture and temperature features. Infrared Phys. Technol. 2020, 105, 103219. [Google Scholar] [CrossRef]
- Chowdhury, M.E.; Alzoubi, K.; Khandakar, A.; Khallifa, R.; Abouhasera, R.; Koubaa, S.; Ahmed, R.; Hasan, A. Wearable real-time heart attack detection and warning system to reduce road accidents. Sensors 2019, 19, 2780. [Google Scholar] [CrossRef] [Green Version]
- Chowdhury, M.E.; Khandakar, A.; Alzoubi, K.; Mansoor, S.; M Tahir, A.; Reaz, M.B.I.; Al-Emadi, N. Real-Time Smart-Digital stethoscope system for heart diseases monitoring. Sensors 2019, 19, 2781. [Google Scholar] [CrossRef] [Green Version]
- Chowdhury, M.H.; Shuzan, M.N.I.; Chowdhury, M.E.; Mahbub, Z.B.; Uddin, M.M.; Khandakar, A.; Reaz, M.B.I. Estimating blood pressure from the photoplethysmogram signal and demographic features using machine learning techniques. Sensors 2020, 20, 3127. [Google Scholar] [CrossRef]
- Hall, M.A. Correlation-based feature selection for machine learning. Ph.D. Thesis, The University of Waikato, Hamilton, New Zealand, 1999. [Google Scholar]
- Haq, A.U.; Zhang, D.; Peng, H.; Rahman, S.U. Combining multiple feature-ranking techniques and clustering of variables for feature selection. IEEE Access 2019, 7, 151482–151492. [Google Scholar] [CrossRef]
- He, S.; Guo, F.; Zou, Q. MRMD2. 0: A python tool for machine learning with feature ranking and reduction. Curr. Bioinform. 2020, 15, 1213–1221. [Google Scholar] [CrossRef]
- Rahman, T.; Al-Ishaq, F.A.; Al-Mohannadi, F.S.; Mubarak, R.S.; Al-Hitmi, M.H.; Islam, K.R.; Khandakar, A.; Hssain, A.A.; Al-Madeed, S.; Zughaier, S.M. Mortality Prediction Utilizing Blood Biomarkers to Predict the Severity of COVID-19 Using Machine Learning Technique. Diagnostics 2021, 11, 1582. [Google Scholar] [CrossRef]
- Rahman, T.; Khandakar, A.; Hoque, M.E.; Ibtehaz, N.; Kashem, S.B.; Masud, R.; Shampa, L.; Hasan, M.M.; Islam, M.T.; Al-Maadeed, S. Development and Validation of an Early Scoring System for Prediction of Disease Severity in COVID-19 using Complete Blood Count Parameters. IEEE Access 2021, 9, 120422–120441. [Google Scholar] [CrossRef]
- Shi, X.; Li, Q.; Qi, Y.; Huang, T.; Li, J. An Accident Prediction Approach Based on XGBoost. In Proceedings of 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), Nanjing, China, 24–26 November 2017; pp. 1–7. [Google Scholar]
- Pal, M. Random forest classifier for remote sensing classification. Int. J. Remote Sens. 2005, 26, 217–222. [Google Scholar] [CrossRef]
- Sharaff, A.; Gupta, H. Extra-tree classifier with metaheuristics approach for email classification. In Advances in Computer Communication and Computational Sciences; Springer: Berlin/Heidelberg, Germany, 2019; pp. 189–197. [Google Scholar]
- Rahman, A.; Chowdhury, M.E.; Khandakar, A.; Kiranyaz, S.; Zaman, K.S.; Reaz, M.B.I.; Islam, M.T.; Ezeddin, M.; Kadir, M.A. Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms. IEEE Access 2021, 9, 94625–94643. [Google Scholar] [CrossRef]
- Shuzan, M.N.I.; Chowdhury, M.H.; Hossain, M.S.; Chowdhury, M.E.; Reaz, M.B.I.; Uddin, M.M.; Khandakar, A.; Mahbub, Z.B.; Ali, S.H.M. A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model. IEEE Access 2021, 9, 96775–96790. [Google Scholar] [CrossRef]
- Chawla, N.V.; Bowyer, K.W.; Hall, L.O.; Kegelmeyer, W.P. SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 2002, 16, 321–357. [Google Scholar] [CrossRef]
- Multilayer Perceptron. Available online: https://en.wikipedia.org/wiki/Multilayer_perceptron (accessed on 2 March 2021).
- Zhang, Y. Support vector machine classification algorithm and its application. In Proceedings of International Conference on Information Computing and Applications, Chengde, China, 14–16 September 2012; pp. 179–186. [Google Scholar]
- Bahad, P.; Saxena, P. Study of Adaboost and Gradient Boosting Algorithms for Predictive Analytics. In Proceedings of International Conference on Intelligent Computing and Smart Communication 2019; Springer: Singapore, 2020; pp. 235–244. [Google Scholar]
- Logistic Regression. Available online: https://en.wikipedia.org/wiki/Logistic_regression (accessed on 2 March 2021).
- Liao, Y.; Vemuri, V.R. Use of k-nearest neighbor classifier for intrusion detection. Comput. Secur. 2002, 21, 439–448. [Google Scholar] [CrossRef]
- Bobkov, V.; Bobkova, A.; Porshnev, S.; Zuzin, V. The Application of Ensemble Learning for Delineation of the Left Ventricle on Echocardiographic Records. In Proceedings of 2016 Dynamics of Systems, Mechanisms and Machines (Dynamics), Omsk, Russia, 15–17 November 2016; pp. 1–5. [Google Scholar]
- Gu, Q.; Li, Z.; Han, J. Linear Discriminant Dimensionality Reduction. In Joint European conference on Machine Learning and Knowledge Discovery in Databases; Springer: Berlin, Heidelberg, 2011; pp. 549–564. [Google Scholar]
- Chen, T.; He, T.; Benesty, M.; Khotilovich, V.; Tang, Y.; Cho, H.; Chen, K. Xgboost: Extreme gradient boosting. R Package Version 0.4–2 2015, 1, 1–4. [Google Scholar]
- Taha, A.A.; Hanbury, A. Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Med. Imaging 2015, 15, 29. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Bénédict, G.; Koops, V.; Odijk, D.; de Rijke, M. sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification. arXiv 2021, arXiv:2108.10566. [Google Scholar]
Dataset | Count of Diabetic Thermograms/Cluster Identified in the Paper | Training Dataset Details | |||
---|---|---|---|---|---|
Training (60% of the Data) Thermogram/Fold | Augmented Train Thermogram/Fold | Validation (20% of the Data) Thermogram/Fold | Test (20% of the Data) Image/Fold | ||
Contreras et al. [22] | Class 1 (TCI < 2) | 34 | 1020 | 11 | 11 |
Class 2 (2 < TCI < 3) | 22 | 1100 | 07 | 07 | |
Class 3 (3 < TCI < 4) | 17 | 1020 | 05 | 06 | |
Class 4 (4 < TCI < 5) | 22 | 1100 | 07 | 08 | |
Class 5 (5 < TCI) | 52 | 1044 | 17 | 18 |
Enhancement | Network | 95% Confidence Interval Results | ||||||
---|---|---|---|---|---|---|---|---|
Class | Accuracy | Precision | Sensitivity | F1-Score | Specificity | Inference Time | ||
Original | ResNet50 | Class 1 | 92.62 ± 06.85 | 81.67 ± 10.13 | 87.50 ± 08.66 | 84.48 ± 09.48 | 94.15 ± 06.15 | 6.247 |
Class 2 | 88.93 ± 10.25 | 60.98 ± 15.93 | 69.44 ± 15.05 | 64.40 ± 15.64 | 92.31 ± 08.70 | |||
Class 3 | 90.98 ± 10.61 | 66.67 ± 17.46 | 42.86 ± 18.33 | 52.18 ± 18.50 | 97.22 ± 06.09 | |||
Class 4 | 86.89 ± 10.88 | 55.56 ± 16.01 | 67.57 ± 15.08 | 60.98 ± 15.72 | 90.34 ± 09.52 | |||
Class 5 | 93.85 ± 05.05 | 95.00 ± 04.58 | 87.36 ± 06.98 | 91.02 ± 06.01 | 97.45 ± 03.31 | |||
Overall | 91.46 ± 03.51 | 77.69 ± 05.22 | 76.64 ± 05.31 | 76.66 ± 05.31 | 94.83 ± 02.78 | |||
AHE | MobileNetv2 | Class 1 | 94.26 ± 6.09 | 88.89 ± 08.23 | 85.71 ± 09.17 | 87.27 ± 08.73 | 96.81 ± 04.60 | 5.412 |
Class 2 | 91.39 ± 09.16 | 70.27 ± 14.93 | 72.22 ± 14.63 | 71.23 ± 14.79 | 94.71 ± 07.31 | |||
Class 3 | 88.11 ± 11.99 | 47.06 ± 18.49 | 28.57 ± 16.73 | 35.55 ± 17.73 | 95.83 ± 07.40 | |||
Class 4 | 84.43 ± 11.68 | 48.94 ± 16.11 | 62.16 ± 15.63 | 54.76 ± 16.04 | 88.41 ± 10.31 | |||
Class 5 | 94.26 ± 04.89 | 91.01 ± 06.01 | 93.10 ± 05.33 | 92.04 ± 05.69 | 94.90 ± 04.62 | |||
Overall | 91.64 ± 03.47 | 76.04 ± 05.36 | 76.23 ± 05.34 | 75.74 ± 05.38 | 94.43 ± 02.88 | |||
Original | ResNet18 | Class 1 | 92.21 ± 07.02 | 83.64 ± 09.69 | 82.14 ± 10.03 | 82.88 ± 09.87 | 95.21 ± 05.59 | 2.536 |
Class 2 | 88.11 ± 10.57 | 58.14 ± 16.12 | 69.44 ± 15.05 | 63.29 ± 15.75 | 91.35 ± 09.18 | |||
Class 3 | 90.98 ± 10.61 | 63.64 ± 17.82 | 50.00 ± 18.52 | 56.00 ± 18.39 | 96.30 ± 06.99 | |||
Class 4 | 86.89 ± 10.88 | 56.10 ± 15.99 | 62.16 ± 15.63 | 58.97 ± 15.85 | 91.30 ± 09.08 | |||
Class 5 | 92.62 ± 05.49 | 91.57 ± 05.84 | 87.36 ± 06.98 | 89.42 ± 06.46 | 95.54 ± 04.34 | |||
Overall | 90.80 ± 03.63 | 76.23 ± 05.34 | 75.41 ± 05.40 | 75.61 ± 05.39 | 94.29 ± 02.91 | |||
Gamma Correction | ResNet18 | Class 1 | 93.03 ± 06.67 | 88.24 ± 08.44 | 80.36 ± 10.41 | 84.12 ± 09.57 | 96.81 ± 04.60 | 3.347 |
Class 2 | 89.75 ± 09.91 | 63.41 ± 15.73 | 72.22 ± 14.63 | 67.53 ± 15.30 | 92.79 ± 08.45 | |||
Class 3 | 90.16 ± 11.03 | 59.09 ± 18.21 | 46.43 ± 18.47 | 52.00 ± 18.51 | 95.83 ± 07.40 | |||
Class 4 | 82.79 ± 12.16 | 44.90 ± 16.03 | 59.46 ± 15.82 | 51.16 ± 16.11 | 86.96 ± 10.85 | |||
Class 5 | 91.80 ± 05.77 | 91.36 ± 05.90 | 85.06 ± 07.49 | 88.10 ± 06.80 | 95.54 ± 04.34 | |||
Overall | 90.23 ± 03.73 | 75.77 ± 05.38 | 73.77 ± 05.52 | 74.41 ± 05.48 | 94.16 ± 02.94 | |||
Gamma Correction | ResNet50 | Class 1 | 92.21 ± 07.02 | 80.33 ± 10.41 | 87.50 ± 08.66 | 83.76 ± 09.66 | 93.62 ± 06.40 | 7.764 |
Class 2 | 88.93 ± 10.25 | 63.64 ± 15.71 | 58.33 ± 16.11 | 60.87 ± 15.94 | 94.23 ± 07.62 | |||
Class 3 | 87.30 ± 12.33 | 44.00 ± 18.39 | 39.29 ± 18.09 | 41.51 ± 18.25 | 93.52 ± 09.12 | |||
Class 4 | 87.70 ± 10.58 | 59.46 ± 15.82 | 59.46 ± 15.82 | 59.46 ± 15.82 | 92.75 ± 08.36 | |||
Class 5 | 93.03 ± 05.35 | 89.77 ± 06.37 | 90.80 ± 06.07 | 90.28 ± 06.22 | 94.27 ± 04.88 | |||
Overall | 90.77 ± 03.63 | 73.90 ± 05.51 | 74.59 ± 05.46 | 74.17 ± 05.49 | 93.80 ± 03.03 |
Classifier | Feature Selection | # of Feature | 95% Confidence Interval Results | Inference Time (ms) | ||||
---|---|---|---|---|---|---|---|---|
Accuracy | Precision | Sensitivity | F1-Score | Specificity | ||||
MLP | XGBoost | 2 | 0.91 ± 01.19 | 0.91 ± 01.19 | 0.91 ± 01.19 | 0.91 ± 01.19 | 0.91 ± 01.19 | 0.592 |
Extra Tree | Random Forest | 5 | 0.88 ± 01.17 | 0.88 ± 01.17 | 0.88 ± 01.17 | 0.88 ± 01.17 | 0.88 ± 01.17 | 0.406 |
Random Forest | XGBoost | 2 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.412 |
KNN | XGBoost | 2 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.87 ± 01.17 | 0.464 |
SVM | XGBoost | 2 | 0.86 ± 01.16 | 0.86 ± 01.16 | 0.86 ± 01.16 | 0.86 ± 01.16 | 0.86 ± 01.16 | 0.456 |
Gradient Boost | XGBoost | 2 | 0.84 ± 01.15 | 0.84 ± 01.15 | 0.84 ± 01.15 | 0.85 ± 01.15 | 0.84 ± 01.15 | 0.492 |
XGBoost | Random Forest | 5 | 0.84 ± 01.15 | 0.84 ± 01.15 | 0.84 ± 01.15 | 0.84 ± 01.15 | 0.84 ± 01.15 | 0.426 |
Logistic Regression | Random Forest | 2 | 0.81 ± 01.13 | 0.81 ± 01.13 | 0.81 ± 01.13 | 0.81 ± 01.13 | 0.81 ± 01.13 | 0.532 |
LDA | Random Forest | 9 | 0.78 ± 01.11 | 0.78 ± 01.11 | 0.78 ± 01.11 | 0.78 ± 01.11 | 0.78 ± 01.11 | 0.406 |
AdaBoost | Random Forest | 3 | 0.68 ± 01.03 | 0.68 ± 01.03 | 0.68 ± 01.03 | 0.70 ± 01.05 | 0.68 ± 01.03 | 0.492 |
Top Combination of Classifier, Feature Selection, # of Feature | Class | Accuracy | Precision | Sensitivity | F1-Score | Specificity | Inference time (ms) |
---|---|---|---|---|---|---|---|
MLP Classifier XGBoost Feature Selection Technique Top 2 Features | Class 1 | 0.91 ± 02.49 | 0.96 ± 02.56 | 0.95 ± 02.54 | 0.95 ± 02.55 | 0.90 ± 02.47 | 0.592 |
Class 2 | 0.91 ± 03.10 | 0.86 ± 03.02 | 0.89 ± 03.07 | 0.88 ± 03.05 | 0.91 ± 03.11 | ||
Class 3 | 0.91 ± 03.52 | 0.83 ± 03.36 | 0.86 ± 03.41 | 0.84 ± 03.38 | 0.92 ± 03.53 | ||
Class 4 | 0.91 ± 03.06 | 0.80 ± 02.87 | 0.86 ± 02.98 | 0.83 ± 02.93 | 0.92 ± 03.07 | ||
Class 5 | 0.91 ± 01.99 | 0.98 ± 02.07 | 0.93 ± 02.02 | 0.95 ± 02.04 | 0.90 ± 01.98 | ||
Overall | 0.91 ± 01.19 | 0.91 ± 01.19 | 0.91 ± 01.19 | 0.91 ± 1.19 | 0.91 ± 01.19 |
Studies | Reported Approach | Approach Results |
---|---|---|
Cruz et al. in [24] | A shallow CNN model named DFTNet was developed to classify using thermogram images | 94.57% F1-score for 10 folds with an unconventional approach of taking 2 different classes in each fold and reporting the average of the 10 folds The authors have computed the 5-fold cross-validation results using DFTNet for the original thermogram (68.96% F1-score), Gamma-enhanced thermogram (68.57% F1-score), AHE-enhanced thermogram (67.69% F1-score) |
Khandakar et al. [23] | Transfer learning using MobileNetV2 and image enhancement to classify thermograms into control and diabetic | A comparatively shallow CNN model, MobilenetV2 achieved an F1 score of ∼95% for a two-feet thermogram image-based classification, and the AdaBoost Classifier used 10 features and achieved an F1 score of 97% |
This study | MLP classifier using 2 features extracted from the thermogram | 91.18% F1-score for 5-fold cross-validation for 5 class-classification |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Khandakar, A.; Chowdhury, M.E.H.; Reaz, M.B.I.; Ali, S.H.M.; Abbas, T.O.; Alam, T.; Ayari, M.A.; Mahbub, Z.B.; Habib, R.; Rahman, T.; et al. Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques. Sensors 2022, 22, 1793. https://doi.org/10.3390/s22051793
Khandakar A, Chowdhury MEH, Reaz MBI, Ali SHM, Abbas TO, Alam T, Ayari MA, Mahbub ZB, Habib R, Rahman T, et al. Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques. Sensors. 2022; 22(5):1793. https://doi.org/10.3390/s22051793
Chicago/Turabian StyleKhandakar, Amith, Muhammad E. H. Chowdhury, Mamun Bin Ibne Reaz, Sawal Hamid Md Ali, Tariq O. Abbas, Tanvir Alam, Mohamed Arselene Ayari, Zaid B. Mahbub, Rumana Habib, Tawsifur Rahman, and et al. 2022. "Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques" Sensors 22, no. 5: 1793. https://doi.org/10.3390/s22051793
APA StyleKhandakar, A., Chowdhury, M. E. H., Reaz, M. B. I., Ali, S. H. M., Abbas, T. O., Alam, T., Ayari, M. A., Mahbub, Z. B., Habib, R., Rahman, T., Tahir, A. M., Bakar, A. A. A., & Malik, R. A. (2022). Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques. Sensors, 22(5), 1793. https://doi.org/10.3390/s22051793