Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques
ABSTRACT Wounds contribute to 30%–42% of hospital visits and 9% of deaths but remain underreported in Africa. Diseases and surgeries increase wound prevalence, especially in rural areas where 27%–82% of people live, and health facilities are poor or non‐existent. This research aims to design a disea...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.70001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576619896635392 |
|---|---|
| author | Prince Odame Maxwell Mawube Ahiamadzor Nana Kwaku Baah Derkyi Kofi Agyekum Boateng Kelvin Sarfo‐Acheampong Eric Tutu Tchao Andrew Selasi Agbemenu Henry Nunoo‐Mensah Dorothy Araba Yakoba Agyapong Jerry John Kponyo |
| author_facet | Prince Odame Maxwell Mawube Ahiamadzor Nana Kwaku Baah Derkyi Kofi Agyekum Boateng Kelvin Sarfo‐Acheampong Eric Tutu Tchao Andrew Selasi Agbemenu Henry Nunoo‐Mensah Dorothy Araba Yakoba Agyapong Jerry John Kponyo |
| author_sort | Prince Odame |
| collection | DOAJ |
| description | ABSTRACT Wounds contribute to 30%–42% of hospital visits and 9% of deaths but remain underreported in Africa. Diseases and surgeries increase wound prevalence, especially in rural areas where 27%–82% of people live, and health facilities are poor or non‐existent. This research aims to design a disease‐related wound classification model for online diagnosis and telemedicine support for traditional health practitioners and village health workers. This paper focuses on wounds from diabetic ulcers, pressure ulcers, surgery, and venous ulcers. The approaches used included Contrast Limited Adaptive Histogram Equalization (CLAHE) with machine and deep learning models, Discrete Wavelet Transformations (DWT) with a novel Gated Wavelet Convolutional Neural Network (CNN) model, and FixCaps, an improved version of Capsule Networks utilizing Convolutional Block Attention Module (CBAM) to reduce spatial information loss. The performance metrics showed similar results for the first two approaches, but FixCaps was the most proficient, with accuracy, precision, recall, and F‐score of 93.83%, 95.41%, 88.63%, and 90.93% respectively. FixCaps had trainable parameters of about 8.28 MB compared with the 195.64 MB of the Gated Wavelet CNN Model. |
| format | Article |
| id | doaj-art-6950e309fcc84baca40a83890e014f45 |
| institution | Kabale University |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-6950e309fcc84baca40a83890e014f452025-01-31T00:22:49ZengWileyEngineering Reports2577-81962025-01-0171n/an/a10.1002/eng2.70001Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning TechniquesPrince Odame0Maxwell Mawube Ahiamadzor1Nana Kwaku Baah Derkyi2Kofi Agyekum Boateng3Kelvin Sarfo‐Acheampong4Eric Tutu Tchao5Andrew Selasi Agbemenu6Henry Nunoo‐Mensah7Dorothy Araba Yakoba Agyapong8Jerry John Kponyo9Department of Computer Engineering Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaResponsible Artificial Intelligence Lab Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaResponsible Artificial Intelligence Lab Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaResponsible Artificial Intelligence Lab Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaResponsible Artificial Intelligence Lab Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaDepartment of Computer Engineering Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaDepartment of Computer Engineering Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaDepartment of Computer Engineering Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaDepartment of Computer Engineering Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaResponsible Artificial Intelligence Lab Kwame Nkrumah University of Science and Technology Kumasi Ashanti Region GhanaABSTRACT Wounds contribute to 30%–42% of hospital visits and 9% of deaths but remain underreported in Africa. Diseases and surgeries increase wound prevalence, especially in rural areas where 27%–82% of people live, and health facilities are poor or non‐existent. This research aims to design a disease‐related wound classification model for online diagnosis and telemedicine support for traditional health practitioners and village health workers. This paper focuses on wounds from diabetic ulcers, pressure ulcers, surgery, and venous ulcers. The approaches used included Contrast Limited Adaptive Histogram Equalization (CLAHE) with machine and deep learning models, Discrete Wavelet Transformations (DWT) with a novel Gated Wavelet Convolutional Neural Network (CNN) model, and FixCaps, an improved version of Capsule Networks utilizing Convolutional Block Attention Module (CBAM) to reduce spatial information loss. The performance metrics showed similar results for the first two approaches, but FixCaps was the most proficient, with accuracy, precision, recall, and F‐score of 93.83%, 95.41%, 88.63%, and 90.93% respectively. FixCaps had trainable parameters of about 8.28 MB compared with the 195.64 MB of the Gated Wavelet CNN Model.https://doi.org/10.1002/eng2.70001capsule networksdeep learningtelemedicinewound classification |
| spellingShingle | Prince Odame Maxwell Mawube Ahiamadzor Nana Kwaku Baah Derkyi Kofi Agyekum Boateng Kelvin Sarfo‐Acheampong Eric Tutu Tchao Andrew Selasi Agbemenu Henry Nunoo‐Mensah Dorothy Araba Yakoba Agyapong Jerry John Kponyo Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques Engineering Reports capsule networks deep learning telemedicine wound classification |
| title | Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques |
| title_full | Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques |
| title_fullStr | Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques |
| title_full_unstemmed | Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques |
| title_short | Multi‐Wound Classification: Exploring Image Enhancement and Deep Learning Techniques |
| title_sort | multi wound classification exploring image enhancement and deep learning techniques |
| topic | capsule networks deep learning telemedicine wound classification |
| url | https://doi.org/10.1002/eng2.70001 |
| work_keys_str_mv | AT princeodame multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT maxwellmawubeahiamadzor multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT nanakwakubaahderkyi multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT kofiagyekumboateng multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT kelvinsarfoacheampong multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT erictututchao multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT andrewselasiagbemenu multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT henrynunoomensah multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT dorothyarabayakobaagyapong multiwoundclassificationexploringimageenhancementanddeeplearningtechniques AT jerryjohnkponyo multiwoundclassificationexploringimageenhancementanddeeplearningtechniques |