Journal Article2026

Accurate Diabetic Foot Ulcer Segmentation: A Human-Machine Collaborative Approach with EfficientNet and Self-ONN FPN

Md Shaheenur Islam Sumon, Muhammad EH Chowdhury, Saadia Binte Alam, Rashedur Rahman, Hadil Aldhubiea, Serkan Kiranyaz, Shahjada Selim, Raihan Anwar, Rashad Alfkey, Samir Fazal Manam, Md Mezbah Ahmed Mahedi, Tahmid Zaman Raad

Cognitive Computation

Springer, Vol. 18, Issue 1, pp. 90, ISBN: 1866-9956

  • Good Health and Well-being — Relevance: 61%
DOI: 10.1007/s12559-026-10636-0URL

Abstract

Abstract Diabetes mellitus is a chronic metabolic disease that affects millions of people worldwide and often leads to diabetic foot ulcers (DFUs). DFUs, which are a major source of morbidity and mortality and are brought on by neuropathy, ischemia, and poor wound healing, significantly raise the risk of lower limb amputations. Effective treatment of DFUs depends on their timely and accurate identification. However, the visual inspection-based clinical procedures used today are subjective and prone to mistakes. Using computer-aided approaches is a possible alternative. In this study, we introduced CFUD-3010, a new and extensive DFU segmentation dataset. 3,010 tagged photos were produced by merging two publicly accessible datasets, the Chronic Wound Dataset and DFU 2020. Because the DFU 2020 dataset lacked segmentation annotations, we used a joint human-machine method to create ground truth masks. In addition, we provide a new Self-Organized Operational Neural Network (Self-ONN)-based decoder and a pre-trained EfficientNetB3-based encoder for the DFU segmentation tasks. By improving heterogeneity and network variety while maintaining computational efficiency, self-ONNs get around the drawbacks of conventional convolution-based models. Using a STAPLE-based methodology, our model achieved precision of 87.918% and a Dice Similarity Coefficient (DSC) of 86.379%. The suggested model was tested on 200 more photos for external validation in order to assess its generalizability. It surpassed current standards with precision of 92.298% and a DSC of 91.217%. Our method demonstrates the ability of sophisticated deep learning models to deliver precise, automated DFU segmentation, which can significantly enhance clinical evaluations and patient outcomes.

Keywords

  • Diabetic foot ulcer
  • EfficientNetB3
  • computer-aided diagnosis
  • ground truth annotation
  • human-machine collaboration
  • staples

CCDS Authors

Saadia Binte Alam, PhD
Saadia Binte Alam, PhD

Saadia Binte Alam, PhD

  • Director, MIRA & WiSE Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

Md. Rashedur Rahman, D. Eng.
Md. Rashedur Rahman, D. Eng.

Md. Rashedur Rahman, D. Eng.

  • Co-Director, MIRA & NEST Wings

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

CHI, HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

References

  1. 1.Yann LeCun, Yoshua Bengio, Geoffrey Hinton. (2015). Deep learning. Nature, 521(7553), 436–444[10.1038/nature14539]
  2. 2.Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie. (2017). Feature Pyramid Networks for Object Detection. , 936–944[10.1109/cvpr.2017.106]
  3. 3.Bryan C. Russell, Antonio Torralba, Kevin P. Murphy, William T. Freeman. (2007). LabelMe: A Database and Web-Based Tool for Image Annotation. International Journal of Computer Vision, 77(1-3), 157–173[10.1007/s11263-007-0090-8]
  4. 4.Huimin Huang, Lanfen Lin, Ruofeng Tong, Hongjie Hu, Qiaowei Zhang, Yutaro Iwamoto, Xianhua Han, Yen-Wei Chen, Jian Wu. (2020). UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation. , 1055–1059[10.1109/icassp40776.2020.9053405]
  5. 5.Andrew JM Boulton, Loretta Vileikyte, Gunnel Ragnarson-Tennvall, Jan Apelqvist. (2005). The global burden of diabetic foot disease. The Lancet, 366(9498), 1719–1724[10.1016/s0140-6736(05)67698-2]
  6. 6.Foivos I. Diakogiannis, François Waldner, Peter Caccetta, Chen Wu. (2020). ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing, 162, 94–114[10.1016/j.isprsjprs.2020.01.013]
  7. 7.S.K. Warfield, K.H. Zou, W.M. Wells. (2004). Simultaneous Truth and Performance Level Estimation (STAPLE): An Algorithm for the Validation of Image Segmentation. IEEE Transactions on Medical Imaging, 23(7), 903–921[10.1109/tmi.2004.828354]
  8. 8.Nuha A. ElSayed, Grazia Aleppo, Raveendhara R. Bannuru, Dennis Bruemmer, Billy S. Collins, Laya Ekhlaspour, Jason L. Gaglia, Marisa E. Hilliard, Eric L. Johnson, Kamlesh Khunti, Ildiko Lingvay, Glenn Matfin, Rozalina G. McCoy, Mary Lou Perry, Scott J. Pilla, Sarit Polsky, Priya Prahalad, Richard E. Pratley, Alissa R. Segal, Jane Jeffrie Seley, Elizabeth Selvin, Robert C. Stanton, Robert A. Gabbay. (2023). 2. Diagnosis and Classification of Diabetes: Standards of Care in Diabetes—2024. Diabetes Care, 47(Supplement_1), S20–S42[10.2337/dc24-s002]
  9. 9.Dominik Müller, Iñaki Soto-Rey, Frank Kramer. (2022). Towards a guideline for evaluation metrics in medical image segmentation. BMC Research Notes, 15(1), 210[10.1186/s13104-022-06096-y]
  10. 10.Ziv Yaniv, Bradley C. Lowekamp, Hans J. Johnson, Richard Beare. (2017). SimpleITK Image-Analysis Notebooks: a Collaborative Environment for Education and Reproducible Research. Journal of Imaging Informatics in Medicine, 31(3), 290–303[10.1007/s10278-017-0037-8]
  11. 11.Chuanbo Wang, D. M. Anisuzzaman, Victor Williamson, Mrinal Kanti Dhar, Behrouz Rostami, Jeffrey Niezgoda, Sandeep Gopalakrishnan, Zeyun Yu. (2020). Fully automatic wound segmentation with deep convolutional neural networks. Scientific Reports, 10(1), 21897[10.1038/s41598-020-78799-w]
  12. 12.Line Bisgaard Jørgensen, Jens A Sørensen, Gregor BE Jemec, Knud B Yderstræde. (2015). Methods to assess area and volume of wounds – a systematic review. International Wound Journal, 13(4), 540–553[10.1111/iwj.12472]
  13. 13.Xianfeng Ou, Pengcheng Yan, Yiming Zhang, Bing Tu, Guoyun Zhang, Jianhui Wu, Wujing Li. (2019). Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes. IEEE Access, 7, 108152–108160[10.1109/access.2019.2931922]
  14. 14.Kiranyaz, Mustafa Serkan, Ince T., Iosifidis A., Gabbouj M.. (2020). Operational neural networks. Qatar University QSpace (Qatar University)[10.1007/s00521-020-04780-3]
  15. 15.Puneeth N. Thotad, Geeta R. Bharamagoudar, Basavaraj S. Anami. (2022). Diabetic foot ulcer detection using deep learning approaches. Sensors International, 4, 100210[10.1016/j.sintl.2022.100210]
  16. 16.Kiranyaz, Mustafa Serkan, Malik J., Abdallah H.B., Ince T., Iosifidis A., Gabbouj M.. (2021). Self-organized Operational Neural Networks with Generative Neurons. Qatar University QSpace (Qatar University)[10.1016/j.neunet.2021.02.028]
  17. 17.Gaetano Scebba, Jia Zhang, Sabrina Catanzaro, Carina Mihai, Oliver Distler, Martin Berli, Walter Karlen. (2022). Detect-and-segment: A deep learning approach to automate wound image segmentation. Informatics in Medicine Unlocked, 29, 100884[10.1016/j.imu.2022.100884]
  18. 18.Moi Hoon Yap, Katie E. Chatwin, Choon-Ching Ng, Caroline A. Abbott, Frank L. Bowling, Satyan Rajbhandari, Andrew J. M. Boulton, Neil D. Reeves. (2017). A New Mobile Application for Standardizing Diabetic Foot Images. Journal of Diabetes Science and Technology, 12(1), 169–173[10.1177/1932296817713761]
  19. 19.Dhanesh Ramachandram, Jose Luis Ramirez-GarciaLuna, Robert D J Fraser, Mario Aurelio Martínez-Jiménez, Jesus E Arriaga-Caballero, Justin Allport. (2022). Fully Automated Wound Tissue Segmentation Using Deep Learning on Mobile Devices: Cohort Study. JMIR mhealth and uhealth, 10(4), e36977[10.2196/36977]
  20. 20.Saleh A. Albelwi. (2022). Deep Architecture based on DenseNet-121 Model for Weather Image Recognition. International Journal of Advanced Computer Science and Applications, 13(10)[10.14569/ijacsa.2022.0131065]
  21. 21.Bingyu Chen, Min Xia, Ming Qian, Junqing Huang. (2022). MANet: a multi-level aggregation network for semantic segmentation of high-resolution remote sensing images. International Journal of Remote Sensing, 43(15-16), 5874–5894[10.1080/01431161.2022.2073795]
  22. 22.Burak Taşcı. (2023). Attention Deep Feature Extraction from Brain MRIs in Explainable Mode: DGXAINet. Diagnostics, 13(5), 859[10.3390/diagnostics13050859]
  23. 23.Amirreza Mahbod, Gerald Schaefer, Rupert Ecker, Isabella Ellinger. (2022). Automatic Foot Ulcer Segmentation Using an Ensemble of Convolutional Neural Networks. 2022 26th International Conference on Pattern Recognition (ICPR), 4358–4364[10.1109/icpr56361.2022.9956253]
  24. 24.Mehmet Emre Sertkaya, Burhan Ergen, Mesut Togacar. (2019). Diagnosis of Eye Retinal Diseases Based on Convolutional Neural Networks Using Optical Coherence Images. , 1–5[10.1109/electronics.2019.8765579]
  25. 25.Chuanbo Wang, Amirreza Mahbod, Isabella Ellinger, Adrian Galdran, Sandeep Gopalakrishnan, Jeffrey Niezgoda, Zeyun Yu. (2024). FUSeg: The Foot Ulcer Segmentation Challenge. Information, 15(3), 140[10.3390/info15030140]
  26. 26.Moi Hoon Yap, Bill Cassidy, Michal Byra, Ting-yu Liao, Huahui Yi, Adrian Galdran, Yung-Han Chen, Raphael Brüngel, Sven Koitka, Christoph M. Friedrich, Yu-wen Lo, Ching-hui Yang, Kang Li, Qicheng Lao, Miguel A. González Ballester, Gustavo Carneiro, Yi-Jen Ju, Juinn-Dar Huang, Joseph M. Pappachan, Neil D. Reeves, Vishnu Chandrabalan, Darren Dancey, Connah Kendrick. (2024). Diabetic foot ulcers segmentation challenge report: Benchmark and analysis. Medical Image Analysis, 94, 103153[10.1016/j.media.2024.103153]
  27. 27.Erdal Basaran, Zafer Comert, Abdulkadir Sengur, Umit Budak, Yuksel Celik, Mesut Togacar. (2019). Chronic Tympanic Membrane Diagnosis based on Deep Convolutional Neural Network. 2019 4th International Conference on Computer Science and Engineering (UBMK), 1–4[10.1109/ubmk.2019.8907070]
  28. 28.Mengying Xiao, Liyuan Zhang, Weili Shi, Jianhua Liu, Wei He, Zhengang Jiang. (2021). A visualization method based on the Grad-CAM for medical image segmentation model. 2021 International Conference on Electronic Information Engineering and Computer Science (EIECS), 242–247[10.1109/eiecs53707.2021.9587953]
  29. 29.Mrinal Kanti Dhar, Taiyu Zhang, Yash Patel, Sandeep Gopalakrishnan, Zeyun Yu. (2024). FUSegNet: A deep convolutional neural network for foot ulcer segmentation. Biomedical Signal Processing and Control, 92, 106057[10.1016/j.bspc.2024.106057]
  30. 30.Khalil Ur Rehman, Li Jianqiang, Anaa Yasin, Anas Bilal, Shakila Basheer, Inam Ullah, Muhammad Kashif Jabbar, Yibin Tian. (2025). A Feature Fusion Attention-Based Deep Learning Algorithm for Mammographic Architectural Distortion Classification. IEEE Journal of Biomedical and Health Informatics, 30(4), 2793–2804[10.1109/jbhi.2025.3547263]
  31. 31.Bo Song, Ahmet Sacan. (2012). Automated wound identification system based on image segmentation and Artificial Neural Networks. , 1–4[10.1109/bibm.2012.6392633]
  32. 32.Nina Petrova, Michael Edmonds. (2006). Emerging drugs for diabetic foot ulcers. Expert Opinion on Emerging Drugs, 11(4), 709–724[10.1517/14728214.11.4.709]
  33. 33.Malathy Jawahar, L. Jani Anbarasi, S. Graceline Jasmine, Modigari Narendra. (2020). Diabetic Foot Ulcer Segmentation using Color Space Models. , 742–747[10.1109/icces48766.2020.9138024]
  34. 34.Jin-Young Kim, Sung-Bae Cho. (2019). Evolutionary Optimization of Hyperparameters in Deep Learning Models. , 831–837[10.1109/cec.2019.8790354]
  35. 35.Cong Cao, Yue Qiu, Zheng Wang, Jiarui Ou, Jiaoju Wang, Alphonse Houssou Hounye, Muzhou Hou, Qiuhong Zhou, Jianglin Zhang. (2022). Nested segmentation and multi-level classification of diabetic foot ulcer based on mask R-CNN. Multimedia Tools and Applications, 82(12), 18887–18906[10.1007/s11042-022-14101-6]
  36. 36.Md. Sakib Abrar Hossain, Sidra Gul, Muhammad E. H. Chowdhury, Muhammad Salman Khan, Md. Shaheenur Islam Sumon, Enamul Haque Bhuiyan, Amith Khandakar, Maqsud Hossain, Abdus Sadique, Israa Al-Hashimi, Mohamed Arselene Ayari, Sakib Mahmud, Abdulrahman Alqahtani. (2023). Deep Learning Framework for Liver Segmentation from T1-Weighted MRI Images. Sensors, 23(21), 8890[10.3390/s23218890]
  37. 37.Asaad Ahmed, Guangmin Sun, Anas Bilal, Yu Li, Shouki A. Ebad. (2025). A Hybrid Deep Learning Approach for Skin Lesion Segmentation With Dual Encoders and Channel-Wise Attention. IEEE Access, 13, 42608–42621[10.1109/access.2025.3548135]
  38. 38.Huahui Yi, Wei Xu, Zekun Jiang, Jun Gao, Qingbo Kang, Qicheng Lao, Kang Li. (2023). OCRNet for Diabetic Foot Ulcer Segmentation Combined with Edge Loss. Lecture notes in computer science, 31–39[10.1007/978-3-031-26354-5_3]
  39. 39.Rusab Sarmun, Saidul Kabir, Johayra Prithula, Abdulrahman Alqahtani, Sohaib Bassam Zoghoul, Israa Al-Hashimi, Adam Mushtak, MuhammadE.H. Chowdhury. (2024). Enhancing intima-media complex segmentation with a multi-stage feature fusion-based novel deep learning framework. Engineering Applications of Artificial Intelligence, 133, 108050[10.1016/j.engappai.2024.108050]
  40. 40.Armando Heras-Tang, Damian Valdes-Santiago, Ángela Mireya León-Mecías, Marta Lourdes Baguer Díaz-Romañach, José Alejandro Mesejo-Chiong, Carlos Cabal-Mirabal. (2022). Diabetic foot ulcer segmentation using logistic regression, DBSCAN clustering and mathematical morphology operators. ELCVIA Electronic Letters on Computer Vision and Image Analysis, 21(2), 22–39[10.5565/rev/elcvia.1413]
← All publications