Advances in deep learning-based image segmentation, classification and detection of skin burn and scald wounds

doi:10.3877/cma.j.issn.1673-9450.2024.02.014

Abstract

Abstract:

Burns and scalds are common causes of skin damage and injuries, and requiring significant attention. Traditionally, the assessment of burns relied on the clinical experience of burn specialists, making it challenging to accurately evaluate the depth and severity of different wounds. Factors like lighting and wound contamination could lead to assessment biases. In recent years, the importance of deep learning based on machine language in the precise evaluation of burn and scald wounds has gradually increased. This article reviews the progress made by scholars over the past few years in using deep learning for the automated diagnosis of burn and scald wounds, focusing on three key areas: wound image segmentation, classification, and detection. It summarizes and categorizes the application of different deep learning techniques in these areas, further explores the challenges faced in automated diagnosis of burn and scald wounds using deep learning, and looks forward to its future application prospects.

Key words: Burns, Deep learning, Image segmentation, Image classification and detection

Rui Wang, Jiawei Zhang, Kecheng Zhang, Zengding Zhou. Advances in deep learning-based image segmentation, classification and detection of skin burn and scald wounds[J]. Chinese Journal of Injury Repair and Wound Healing(Electronic Edition), 2024, 19(02): 172-175.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhssyxfzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1673-9450.2024.02.014

https://zhssyxfzz.cma-cmc.com.cn/EN/Y2024/V19/I02/172

References 30

[1]	Atiyeh BS, Gunn SW, Hayek SN. Military and civilian burn injuries during armed conflicts[J]. Ann Burns Fire Disasters，2007，20(4)：203-215.
[2]	Klein MB, Hayden D, Elson C, et al. The association between fluid administration and outcome following major burn: a multicenter study[J]. Ann Surg，2007, 245(4): 622-628.
[3]	贲驰，李海航，刘彤，等．人工智能技术辅助烧伤深度诊断的研究进展[J]．中华烧伤杂志，2020，36(3)：244-246.
[4]	Monstrey S, Hoeksema H, Verbelen J, et al. Assessment of burn depth and burn wound healing potential[J]. Burns，2008, 34(6)：761-769.
[5]	Jeschke MG, Chinkes DL, Finnerty CC, et al. Pathophysiologic response to severe burn injury[J]. Ann Surg，2008, 248(3): 387-401.
[6]	Acha B, Serrano C, Acha JI, et al. Segmentation and classification of burn images by color and texture information[J]. J Biomed Opt，2005, 10(3)：34-41.
[7]	Wantanajittikul K, Auephanwiriyakul S, Theera-Umpon N, et al. Automatic segmentation and degree identification in burn color images[C]. The 4th 2011 Biomedical Engineering International Conference. IEEE，2012: 169-173.
[8]	Wolf ES, Rose KJ, Desai HM, et al. Mortality determinants in massive pediatric burns. An analysis of 103 children with > or ＝80% TBSA burns (> or ＝70% full-thickness)[J]. Ann Surg，1997, 225(5): 554.
[9]	Jiao C, Su K, Xie W, et al. Burn image segmentation based on Mask Regions with Convolutional Neural Network deep learning framework: more accurate and more convenient[J]．Burns Trauma，2019, 7：6.
[10]	Chauhan J, Goyal P．Convolution neural network for effective burn region segmentation of color images[J]. Burns，2021, 47(4): 854-862.
[11]	Liu H, Yue K, Cheng S, et al. A framework for automatic burn image segmentation and burn depth diagnosis using deep learning[J]. Comput Math Methods Med, 2021：5514224.
[12]	Liang J, Li R, Wang C, et al. A spiking neural network based on retinal ganglion cells for automatic burn image segmentation[J]. Entropy，2022, 24(11): 1526.
[13]	Abdolahnejad M, Lee J, Chan H, et al. Boundary attention mapping (BAM): fine-grained saliency maps for segmentation of burn injuries[J]. arXiv preprint arXiv，2023.
[14]	Sevik U, Karakullukcu E, Berber T, et al. Automatic classification of skin burn colour images using texture-based feature extraction[J]. IET Image Process，2019, 13(11)：2018-2028.
[15]	Yadav DP, Sharma A, Singh M, et al. Feature extraction based machine learning for human burn diagnosis from burn images[J]．IEEE J Transl Eng Health Med, 2019，7：1800507.
[16]	Boissin C, Laflamme L, Fransén J, et al. Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery[J]. Sci Rep, 2023, 13(1): 1794.
[17]	Chauhan J, Goyal P. Deep learning based fully automatic efficient burn severity estimators for better burn diagnosis[C]. 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020: 1-8.
[18]	Yang CS, Wei CP, Yuan CC, et al. Predicting the length of hospital stay of burn patients: comparisons of prediction accuracy among different clinical stages[J]. Decision Support System, 2010, 50(1)：325-335.
[19]	Acha B, Serrano C, Fondon I, et al. Burn depth analysis using multidimensional scaling applied to psychophysical experiment data[J]. IEEE Trans Med Imaging, 2013, 32(6)：1111-1120.
[20]	Ganapathy P, Tamminedi T, Qin Y, et al. Dual-imaging system for burn depth diagnosis[J]. Burns, 2014, 40(1)：67-81.
[21]	Cirillo MD, Mirdell R, Sjöberg F, et al.Time-independent prediction of burn depth using deep convolutional neural networks[J]．J Burn Care Res, 2019, 40(6): 857-863.
[22]	Rostami B, Anisuzzaman DM, Wang C, et al. Multiclass wound image classification using an ensemble deep CNN-based classifier[J]. Comput Biol Med, 2021, 134: 104536.
[23]	Karthik J, Nath GS, Veena A. Deep learning-based approach for skin burn detection with multi-level classification[J]. Advances in Computing and Network Communications, 2021: 31-40.
[24]	Goyal M, Reeves ND, Rajbhandari S, et al. Robust methods for real-time diabetic foot ulcer detection and localization on mobile devices[J]. IEEE J Biomed Health Inform, 2018, 23(4): 1730-1741.
[25]	Oliveira A, Carvalho AB, Dantas DO. Faster R-CNN approach for diabetic foot ulcer detection[C]. Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2021: 677-684.
[26]	韩旭晖，刘宇，何圭波，等．基于多尺度特征融合的皮肤烧伤创面分级算法[J]．电子测量技术，2022，45(18)：114-118.
[27]	Tan M, Pang R, Le Q. EfficientDet: scalable and efficient object detection[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020：10778-10787.
[28]	Scebba G, Zhang J, Catanzaro S, et al. Detect-and-segment: a deep learning approach to automate wound image segmentation[J]. Informatics in Medicine Unlocked, 2022, 29: 100884.
[29]	Ferdinand J, Chow DV, Prasetyo SY. Automated skin burn detection and severity classification using YOLO Convolutional Neural Network Pretrained Model[C]. E3S Web of Conferences. EDP Sciences, 2023, 426: 01076.
[30]	Pabitha C, Vanathi B. Dense Mesh RCNN: assessment of human skin burn and burn depth severity[J]. The Journal of Supercomputing, 2023: 1-32.

Please choose a citation manager

Content to export