Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization

<p dir="ltr">Diabetes mellitus (DM) can cause chronic foot issues and severe infections, including Diabetic Foot Ulcers (DFUs) that heal slowly due to insufficient blood flow. A recurrence of these ulcers can lead to 84% of lower limb amputations and even cause death. High-risk diabe...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Rusab Sarmun (17632269) (author)
مؤلفون آخرون: Muhammad E. H. Chowdhury (14150526) (author), M. Murugappan (18842221) (author), Ahmed Aqel (21767678) (author), Maymouna Ezzuddin (21767681) (author), Syed Mahfuzur Rahman (21767684) (author), Amith Khandakar (14151981) (author), Sanzida Akter (21767687) (author), Rashad Alfkey (17093008) (author), Anwarul Hasan (1332066) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513543705985024
author Rusab Sarmun (17632269)
author2 Muhammad E. H. Chowdhury (14150526)
M. Murugappan (18842221)
Ahmed Aqel (21767678)
Maymouna Ezzuddin (21767681)
Syed Mahfuzur Rahman (21767684)
Amith Khandakar (14151981)
Sanzida Akter (21767687)
Rashad Alfkey (17093008)
Anwarul Hasan (1332066)
author2_role author
author
author
author
author
author
author
author
author
author_facet Rusab Sarmun (17632269)
Muhammad E. H. Chowdhury (14150526)
M. Murugappan (18842221)
Ahmed Aqel (21767678)
Maymouna Ezzuddin (21767681)
Syed Mahfuzur Rahman (21767684)
Amith Khandakar (14151981)
Sanzida Akter (21767687)
Rashad Alfkey (17093008)
Anwarul Hasan (1332066)
author_role author
dc.creator.none.fl_str_mv Rusab Sarmun (17632269)
Muhammad E. H. Chowdhury (14150526)
M. Murugappan (18842221)
Ahmed Aqel (21767678)
Maymouna Ezzuddin (21767681)
Syed Mahfuzur Rahman (21767684)
Amith Khandakar (14151981)
Sanzida Akter (21767687)
Rashad Alfkey (17093008)
Anwarul Hasan (1332066)
dc.date.none.fl_str_mv 2024-04-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s12559-024-10267-3
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Diabetic_Foot_Ulcer_Detection_Combining_Deep_Learning_Models_for_Improved_Localization/29625089
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Clinical sciences
Medical biochemistry and metabolomics
Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Diabetic foot ulcer (DFU)
Weighted bounding box fusion (WBF)
Machine learning
Deep learning
Diabetic Foot Ulcer Challenge 2020 (DFUC2020)
dc.title.none.fl_str_mv Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Diabetes mellitus (DM) can cause chronic foot issues and severe infections, including Diabetic Foot Ulcers (DFUs) that heal slowly due to insufficient blood flow. A recurrence of these ulcers can lead to 84% of lower limb amputations and even cause death. High-risk diabetes patients require expensive medications, regular check-ups, and proper personal hygiene to prevent DFUs, which affect 15–25% of diabetics. Accurate diagnosis, appropriate care, and prompt response can prevent amputations and fatalities through early and reliable DFU detection from image analysis. We propose a comprehensive deep learning-based system for detecting DFUs from patients’ feet images by reliably localizing ulcer points. Our method utilizes innovative model ensemble techniques—non-maximum suppression (NMS), Soft-NMS, and weighted bounding box fusion (WBF)—to combine predictions from state-of-the-art object detection models. The performances of diverse cutting-edge model architectures used in this study complement each other, leading to more generalized and improved results when combined in an ensemble. Our WBF-based approach combining YOLOv8m and FRCNN-ResNet101 achieves a mean average precision (mAP) score of 86.4% at the IoU threshold of 0.5 on the DFUC2020 dataset, significantly outperforming the former benchmark by 12.4%. We also perform external validation on the IEEE DataPort Diabetic Foot dataset which has demonstrated robust and reliable model performance on the qualitative analysis. In conclusion, our study effectively developed an innovative diabetic foot ulcer (DFU) detection system using an ensemble model of deep neural networks (DNNs). This AI-driven tool serves as an initial screening aid for medical professionals, augmenting the diagnostic process by enhancing sensitivity to potential DFU cases. While recognizing the presence of false positives, our research contributes to improving patient care through the integration of human medical expertise with AI-based solutions in DFU management.</p><h2>Other Information</h2><p dir="ltr">Published in: Cognitive Computation<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s12559-024-10267-3" target="_blank">https://dx.doi.org/10.1007/s12559-024-10267-3</a></p>
eu_rights_str_mv openAccess
id Manara2_c135f92cf31fcb12e7d6837ea5cc8cdf
identifier_str_mv 10.1007/s12559-024-10267-3
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29625089
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved LocalizationRusab Sarmun (17632269)Muhammad E. H. Chowdhury (14150526)M. Murugappan (18842221)Ahmed Aqel (21767678)Maymouna Ezzuddin (21767681)Syed Mahfuzur Rahman (21767684)Amith Khandakar (14151981)Sanzida Akter (21767687)Rashad Alfkey (17093008)Anwarul Hasan (1332066)Biomedical and clinical sciencesClinical sciencesMedical biochemistry and metabolomicsEngineeringBiomedical engineeringHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceMachine learningDiabetic foot ulcer (DFU)Weighted bounding box fusion (WBF)Machine learningDeep learningDiabetic Foot Ulcer Challenge 2020 (DFUC2020)<p dir="ltr">Diabetes mellitus (DM) can cause chronic foot issues and severe infections, including Diabetic Foot Ulcers (DFUs) that heal slowly due to insufficient blood flow. A recurrence of these ulcers can lead to 84% of lower limb amputations and even cause death. High-risk diabetes patients require expensive medications, regular check-ups, and proper personal hygiene to prevent DFUs, which affect 15–25% of diabetics. Accurate diagnosis, appropriate care, and prompt response can prevent amputations and fatalities through early and reliable DFU detection from image analysis. We propose a comprehensive deep learning-based system for detecting DFUs from patients’ feet images by reliably localizing ulcer points. Our method utilizes innovative model ensemble techniques—non-maximum suppression (NMS), Soft-NMS, and weighted bounding box fusion (WBF)—to combine predictions from state-of-the-art object detection models. The performances of diverse cutting-edge model architectures used in this study complement each other, leading to more generalized and improved results when combined in an ensemble. Our WBF-based approach combining YOLOv8m and FRCNN-ResNet101 achieves a mean average precision (mAP) score of 86.4% at the IoU threshold of 0.5 on the DFUC2020 dataset, significantly outperforming the former benchmark by 12.4%. We also perform external validation on the IEEE DataPort Diabetic Foot dataset which has demonstrated robust and reliable model performance on the qualitative analysis. In conclusion, our study effectively developed an innovative diabetic foot ulcer (DFU) detection system using an ensemble model of deep neural networks (DNNs). This AI-driven tool serves as an initial screening aid for medical professionals, augmenting the diagnostic process by enhancing sensitivity to potential DFU cases. While recognizing the presence of false positives, our research contributes to improving patient care through the integration of human medical expertise with AI-based solutions in DFU management.</p><h2>Other Information</h2><p dir="ltr">Published in: Cognitive Computation<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s12559-024-10267-3" target="_blank">https://dx.doi.org/10.1007/s12559-024-10267-3</a></p>2024-04-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s12559-024-10267-3https://figshare.com/articles/journal_contribution/Diabetic_Foot_Ulcer_Detection_Combining_Deep_Learning_Models_for_Improved_Localization/29625089CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/296250892024-04-01T00:00:00Z
spellingShingle Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
Rusab Sarmun (17632269)
Biomedical and clinical sciences
Clinical sciences
Medical biochemistry and metabolomics
Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Diabetic foot ulcer (DFU)
Weighted bounding box fusion (WBF)
Machine learning
Deep learning
Diabetic Foot Ulcer Challenge 2020 (DFUC2020)
status_str publishedVersion
title Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
title_full Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
title_fullStr Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
title_full_unstemmed Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
title_short Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
title_sort Diabetic Foot Ulcer Detection: Combining Deep Learning Models for Improved Localization
topic Biomedical and clinical sciences
Clinical sciences
Medical biochemistry and metabolomics
Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Diabetic foot ulcer (DFU)
Weighted bounding box fusion (WBF)
Machine learning
Deep learning
Diabetic Foot Ulcer Challenge 2020 (DFUC2020)