CNN-Based Wound Segmentation: A Review of Models and Performance Evaluation


Year : 2025 | Volume :15 | Issue : 01 | Page : 33-46
    By

    Saumitra Gurav,

  • Crysline Correa,

  • Soham Mokashi,

  • Larissa Martis,

  • Joshua Michael,

  1. Student, Department of Computer Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra West, Mumbai, Maharashtra, India
  2. Student, Department of Computer Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra West, Mumbai, Maharashtra, India
  3. Student, Department of Computer Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra West, Mumbai, Maharashtra, India
  4. Student, Department of Computer Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra West, Mumbai, Maharashtra, India
  5. Assistant Professor, Department of Computer Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra West, Mumbai, Maharashtra, India

Abstract

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_160572’);});Edit Abstract & Keyword

Deep learning, particularly convolutional neural networks (CNNs), has altered medical image processing by automating and precisely segmenting complex medical pictures. Wound segmentation, a critical application in automated wound assessment, is essential for wound size estimation, classification, and healing progress monitoring. This study presents a comprehensive review of CNN-based wound segmentation models, focusing on their architectures, methodologies, and performance on diverse datasets. Four deep learning models, including two U-Net variants (5-layer and 4-layer), SegNet, and MobileNetV2, were evaluated on three datasets: AZH Woundcare Dataset, WoundSeg Dataset, and Medetec Wound Dataset. The models were analyzed using standard metrics such as Dice coefficient and loss values. By comparing the strengths and limitations of these models, this review highlights the impact of dataset size and architectural variations on segmentation performance. The findings shed light on the status of wound segmentation research and suggest directions for
future advancements.

Keywords: Wound segmentation, convolutional neural networks, U-net, Segnet, Mobilenetv2, deep learning, medical image analysis, segmentation

[This article belongs to Current Trends in Signal Processing (ctsp)]

How to cite this article:
Saumitra Gurav, Crysline Correa, Soham Mokashi, Larissa Martis, Joshua Michael. CNN-Based Wound Segmentation: A Review of Models and Performance Evaluation. Current Trends in Signal Processing. 2025; 15(01):33-46.
How to cite this URL:
Saumitra Gurav, Crysline Correa, Soham Mokashi, Larissa Martis, Joshua Michael. CNN-Based Wound Segmentation: A Review of Models and Performance Evaluation. Current Trends in Signal Processing. 2025; 15(01):33-46. Available from: https://journals.stmjournals.com/ctsp/article=2025/view=0

—



Full Text PDF


Full Text PDF


window.onload = function () {
let slideIndex = 0;
const slides = document.querySelectorAll(“.Slide img”);
const prevBtn = document.querySelector(“.prevBtn”);
const nextBtn = document.querySelector(“.nextBtn”);
function showSlide(index) {
slides.forEach((slide, i) => {
slide.style.display = i === index ? “block” : “none”;
});
}
showSlide(slideIndex);
prevBtn.addEventListener(“click”, () => {
slideIndex = (slideIndex > 0) ? slideIndex – 1 : slides.length – 1;
showSlide(slideIndex);
});
nextBtn.addEventListener(“click”, () => {
slideIndex = (slideIndex < slides.length – 1) ? slideIndex + 1 : 0;
showSlide(slideIndex);
});
};

Browse Figures

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_160572’);});Edit

References

  1. Wang C, Anisuzzaman DM, Williamson V, Dhar MK, Rostami B, Niezgoda J, Gopalakrishnan S, Yu Z. Fully automatic wound segmentation with deep convolutional neural networks. Sci Rep. 2020 Dec 14; 10(1): 21897. https://doi.org/10.1038/s41598-020-78799-w
  2. Müller D, Kramer F. MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning. BMC Med 2021 Dec; 21(1): 12. https://doi.org/10.1186/s12880-020-00543-7
  3. Xu Y, He X, Xu G, Qi G, Yu K, Yin L, Yang P, Yin Y, Chen H. A medical image segmentation method based on multi-dimensional statistical features. Front Neurosci. 2022 Sep 15; 16: 1009581. https://doi.org/10.3389/fnins.2022.1009581
  4. Huang Z, Wang L, Xu L. DRA-Net: Medical image segmentation based on adaptive feature extraction and region-level information fusion. Sci Rep. 2024 Apr 27; 14(1): 9714. https://doi.org/10.1038/s41598-024-60475-y
  5. Wang C, Anisuzzaman DM, Williamson V, Dhar MK, Rostami B, Niezgoda J, Gopalakrishnan S, Yu Z. Fully automatic wound segmentation with deep convolutional neural networks. Sci Rep. 2020 Dec 14; 10(1): 21897.
  6. Daimary D, Bora MB, Amitab K, Kandar D. Brain tumor segmentation from MRI images using hybrid convolutional neural networks. Procedia Comput Sci. 2020 Jan 1; 167: 2419–28. https://doi.org/10.1016/j.procs.2020.03.295
  7. Daniel J, Rose JA, Vinnarasi FS, Rajinikanth V. VGG‐UNet/VGG‐SegNet Supported Automatic Segmentation of Endoplasmic Reticulum Network in Fluorescence Microscopy Images. Scanning. 2022; 2022(1): 7733860. https://doi.org/10.1155/2022/7733860
  8. Huang A, Jiang L, Zhang J, Wang Q. Attention-VGG16-UNet: a novel deep learning approach for automatic segmentation of the median nerve in ultrasound images. Quant Imaging Med Surg. 2022 Jun; 12(6): 3138–3150.
  9. Zhang R, Tian D, Xu D, Qian W, Yao Y. A survey of wound image analysis using deep learning: Classification, detection, and segmentation. IEEE Access. 2022 Jul 28; 10: 79502–15.
  10. Baccouch W, Oueslati S, Solaiman B, Labidi S. A comparative study of CNN and U-Net performance for automatic segmentation of medical images: application to cardiac MRI. Procedia Comput Sci. 2023 Jan 1; 219: 1089–96. https://doi.org/10.1016/j.procs.2023.01.388.
  11. Siddique N, Paheding S, Elkin CP, Devabhaktuni V. U-net and its variants for medical image segmentation: A review of theory and applications. IEEE Access. 2021 Jun 3; 9: 82031–57.
  12. Malhotra R, Saini BS, Gupta S. CB-D2RNet–An efficient context bridge network for glioma segmentation. J Vis Commun Image Represent. 2023 Jun 1; 94: 103836.
  13. Wang C, Anisuzzaman DM, Williamson V, Dhar MK, Rostami B, Niezgoda J, Gopalakrishnan S, Yu Z. Fully automatic wound segmentation with deep convolutional neural networks. Sci Rep. 2020 Dec 14; 10(1):21897.
  14. Oota SR, Rowtula V, Mohammed S, Liu M, Gupta M. WSNet: towards an effective method for wound image segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2023; 3234–3243.
  15. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18; Springer International Publishing. 2015; 234–241.
  16. Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell. 2017 Jan 2; 39(12): 2481–95.
  17. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2018; 4510-4520.
  18. Yuan H, Cheng J, Wu Y, Zeng Z. Low-res MobileNet: An efficient lightweight network for low-resolution image classification in resource-constrained scenarios. Multimed Tools Appl. 2022 Nov; 81(27): 38513–30.
Regular Issue Subscription Review Article
Volume 15
Issue 01
Received 10/01/2025
Accepted 14/01/2025
Published 08/02/2025
78