Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention
<italic>Goal:</italic> Chronic wounds affect 6.5 million Americans. Wound assessment via algorithmic analysis of smartphone images has emerged as a viable option for remote assessment. <italic>Methods:</italic> We comprehensively score wounds based on the clinically-validated...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9464711/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839644534848356352 |
|---|---|
| author | Ziyang Liu Emmanuel Agu Peder Pedersen Clifford Lindsay Bengisu Tulu Diane Strong |
| author_facet | Ziyang Liu Emmanuel Agu Peder Pedersen Clifford Lindsay Bengisu Tulu Diane Strong |
| author_sort | Ziyang Liu |
| collection | DOAJ |
| description | <italic>Goal:</italic> Chronic wounds affect 6.5 million Americans. Wound assessment via algorithmic analysis of smartphone images has emerged as a viable option for remote assessment. <italic>Methods:</italic> We comprehensively score wounds based on the clinically-validated Photographic Wound Assessment Tool (PWAT), which comprehensively assesses clinically important ranges of eight wound attributes: Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability. We proposed a DenseNet Convolutional Neural Network (CNN) framework with patch-based context-preserving attention to assess the 8 PWAT attributes of four wound types: diabetic ulcers, pressure ulcers, vascular ulcers and surgical wounds. <italic>Results:</italic> In an evaluation on our dataset of 1639 wound images, our model estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of over 80%. <italic>Conclusions:</italic> Our work is the first intelligent system that autonomously grades wounds comprehensively based on criteria in the PWAT rubric, alleviating the significant burden that manual wound grading imposes on wound care nurses. |
| format | Article |
| id | doaj-art-128466a0897a4795bd42efbf9f8fb9e7 |
| institution | Matheson Library |
| issn | 2644-1276 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-128466a0897a4795bd42efbf9f8fb9e72025-07-02T00:08:48ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762021-01-01222423410.1109/OJEMB.2021.30922079464711Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving AttentionZiyang Liu0https://orcid.org/0000-0001-5419-1250Emmanuel Agu1https://orcid.org/0000-0002-3361-4952Peder Pedersen2https://orcid.org/0000-0002-7917-7209Clifford Lindsay3Bengisu Tulu4https://orcid.org/0000-0001-7226-1830Diane Strong5https://orcid.org/0000-0002-1756-0464Computer Science Department, Worcester Polytechnic Institute, Worcester, MA, USAComputer Science Department, Worcester Polytechnic Institute, Worcester, MA, USAElectrical and Computer Engineering Department, Worcester Polytechnic Institute, Worcester, MA, USADepartment of Radiology, University of Massachusetts Medical School, Worcester, MA, USAFoisie Business School, Worcester Polytechnic Institute, Worcester, MA, USAFoisie Business School, Worcester Polytechnic Institute, Worcester, MA, USA<italic>Goal:</italic> Chronic wounds affect 6.5 million Americans. Wound assessment via algorithmic analysis of smartphone images has emerged as a viable option for remote assessment. <italic>Methods:</italic> We comprehensively score wounds based on the clinically-validated Photographic Wound Assessment Tool (PWAT), which comprehensively assesses clinically important ranges of eight wound attributes: Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability. We proposed a DenseNet Convolutional Neural Network (CNN) framework with patch-based context-preserving attention to assess the 8 PWAT attributes of four wound types: diabetic ulcers, pressure ulcers, vascular ulcers and surgical wounds. <italic>Results:</italic> In an evaluation on our dataset of 1639 wound images, our model estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of over 80%. <italic>Conclusions:</italic> Our work is the first intelligent system that autonomously grades wounds comprehensively based on criteria in the PWAT rubric, alleviating the significant burden that manual wound grading imposes on wound care nurses.https://ieeexplore.ieee.org/document/9464711/Chronic woundsdeep learningmedical imagingsmartphone assessmenttransfer learning |
| spellingShingle | Ziyang Liu Emmanuel Agu Peder Pedersen Clifford Lindsay Bengisu Tulu Diane Strong Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention IEEE Open Journal of Engineering in Medicine and Biology Chronic wounds deep learning medical imaging smartphone assessment transfer learning |
| title | Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention |
| title_full | Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention |
| title_fullStr | Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention |
| title_full_unstemmed | Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention |
| title_short | Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN With Context-Preserving Attention |
| title_sort | comprehensive assessment of fine grained wound images using a patch based cnn with context preserving attention |
| topic | Chronic wounds deep learning medical imaging smartphone assessment transfer learning |
| url | https://ieeexplore.ieee.org/document/9464711/ |
| work_keys_str_mv | AT ziyangliu comprehensiveassessmentoffinegrainedwoundimagesusingapatchbasedcnnwithcontextpreservingattention AT emmanuelagu comprehensiveassessmentoffinegrainedwoundimagesusingapatchbasedcnnwithcontextpreservingattention AT pederpedersen comprehensiveassessmentoffinegrainedwoundimagesusingapatchbasedcnnwithcontextpreservingattention AT cliffordlindsay comprehensiveassessmentoffinegrainedwoundimagesusingapatchbasedcnnwithcontextpreservingattention AT bengisutulu comprehensiveassessmentoffinegrainedwoundimagesusingapatchbasedcnnwithcontextpreservingattention AT dianestrong comprehensiveassessmentoffinegrainedwoundimagesusingapatchbasedcnnwithcontextpreservingattention |