References

Beeckman D, Schoonhoven L, Fletcher J EPUAP classification system for pressure ulcers: European reliability study. J Adv Nurs. 2007; 60:(6)682-691 https://doi.org/10.1111/j.1365-2648.2007.04474.x

Yazdanpanah L, Nasiri M, Adarvishi S. Literature review on the management of diabetic foot ulcer. World J Diabetes. 2015; 6:(1)37-53 https://doi.org/10.4239/wjd.v6.i1.37

Brownrigg JR, Apelqvist J, Bakker K Evidence-based management of PAD & the diabetic foot. Eur J Vasc Endovasc Surg. 2013; 45:(6)673-681 https://doi.org/10.1016/j.ejvs.2013.02.014

Chronic leg ulcers: epidemiology, aetiopathogenesis, and management. 2013. https://tinyurl.com/yygk5hkm

Serra R, Butrico L, Ruggiero M Epidemiology, diagnosis and treatment of chronic leg ulcers: a systematic review. Acta Phlebol. 2015; 16:(1)9-18

Totty JP, Harwood AE, Wallace T Use of photograph-based telemedicine in postoperative wound assessment to diagnose or exclude surgical site infection. J Wound Care. 2018; 27:(3)128-135 https://doi.org/10.12968/jowc.2018.27.3.128

Kidholm K, Ekeland AG, Jensen LK A model for assessment of telemedicine applications: mast. Int J Technol Assess Health Care. 2012; 28:(1)44-51 https://doi.org/10.1017/S0266462311000638

Moor Z, Angel D, Bjerregaard J eHealth in Wound Care from conception to implementation. J Wound Care. 2015; 24:S1-S44 https://doi.org/10.12968/jowc.2015.24.Sup5.S1

Ardila D, Kiraly AP, Bharadwaj S End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature Medicine. 2019; 25:954-961

Anwar SM, Majid M, Qayyum A Medical image analysis using convolutional neural networks: a review. J Med Syst. 2018; 42:(11) https://doi.org/10.1007/s10916-018-1088-1

Goyal M, Yap MH, Reeves ND Fully convolutional networks for diabetic foot ulcer segmentation.: IEEE; 2017 https://doi.org/10.1109/SMC.2017.8122675

Goodfellow I, Bengio Y, Courville A. Deep Learning Book.: MIT; 2016

Bengio Y. Learning deep architectures for AI. J Foundations and Trends in Machine Learning. 2009; 2:(1)1-127

Fukushima K. Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw. 1988; 1:(2)119-130 https://doi.org/10.1016/0893-6080(88)90014-7

Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998; 86:(11)2278-2324 https://doi.org/10.1109/5.726791

Mask R-CNN. https://arxiv.org/abs/1703.06870 (accessed 26 September 2019)

Li F, Wang C, Liu X A composite model of wound segmentation based on traditional methods and deep neural networks. Comput Intell Neurosci. 2018; 4149103 https://doi.org/10.1155/2018/4149103

Zahia S, Sierra-Sosa D, Garcia-Zapirain B, Elmaghraby A. Tissue classification and segmentation of pressure injuries using convolutional neural networks. Comput Methods Programs Biomed. 2018; 159:(6)51-58 https://doi.org/10.1016/j.cmpb.2018.02.018

Goyal M, Reeves DN, Davison AK DFUNet: convolutional neural networks for diabetic foot ulcer classification. IEEE. 2018; 1 https://doi.org/10.1109/tetci.2018.2866254

SegNet: a deep convolutional encoder-decoder architecture for image segmentation. 2016. https://arxiv.org/abs/1511.00561

LinkNet: exploiting encoder representations for efficient semantic segmentation. 2017. https://arxiv.org/abs/1707.03718

U-Net: convolutional networks for biomedical image segmentation. 2015. https://arxiv.org/abs/1505.04597

TernausNet: U-Net with VGG11 encoder pre-trained on ImageNet for segmentation. 2018. https://arxiv.org/abs/1801.05746

Ahmad Fauzi MF, Khansa I, Catignani K Computerized segmentation and measurement of chronic wound images. Comput Biol Med. 2015; 60:74-85 https://doi.org/10.1016/j.compbiomed.2015.02.015

Chang AC, Dearman BI, Greenwood JE A comparison of wound area measurement techniques: Visitrak versus photography. Eplasty. 2011; 11

Sheehan P, Jones P, Giurini JM Percent change in wound area of diabetic foot ulcers over a 4-week period is a robust predictor of complete healing in a 12-week prospective trial. Plast Reconstr Surg. 2006; 117:239S-244S https://doi.org/10.1097/01.prs.0000222891.74489.33

Sheehan P, Jones P, Caselli A Percent change in wound area of diabetic foot ulcers over a 4-week period is a robust predictor of complete healing in a 12-week prospective trial. Diabetes Care. 2003; 26:(6)1879-1882 https://doi.org/10.2337/diacare.26.6.1879

Iizaka S, Kaitani T, Sugama J Predictive validity of granulation tissue color measured by digital image analysis for deep pressure ulcer healing: a multicenter prospective cohort study. Wound Repair Regen. 2013; 21:(1)25-34 https://doi.org/10.1111/j.1524-475X.2012.00841.x

Prevention and treatment of pressure ulcers: clinical practice guideline. In: Haesler E (ed). : Cambridge Media; 2014

Sanada H, Iizaka S, Matsui Y Clinical wound assessment using DESIGN-R total score can predict pressure ulcer healing: pooled analysis from two multicenter cohort studies. Wound Repair Regen. 2011; 19:(5)559-67 https://doi.org/10.1111/j.1524-475X.2011.00719.x

Yokoi H, Ho M, Iwamoto S Design strategies for global clinical trials of endovascular devices for critical limb ischemia (cli) ― a joint USA-Japanese Perspective. Circ J. 2018; 82:(9)2233-2239 https://doi.org/10.1253/circj.CJ-18-0014

Wound healing

Convolutional neural networks for wound detection: the role of artificial intelligence in wound care

01 October 2019
Research

Abstract

Objective:

Telemedicine is an essential support system for clinical settings outside the hospital. Recently, the importance of the model for assessment of telemedicine (MAST) has been emphasised. The development of an eHealth-supported wound assessment system using artificial intelligence is awaited. This study explored whether or not wound segmentation of a diabetic foot ulcer (DFU) and a venous leg ulcer (VLU) by a convolutional neural network (CNN) was possible after being educated using sacral pressure ulcer (PU) data sets, and which CNN architecture was superior at segmentation.

Methods:

CNNs with different algorithms and architectures were prepared. The four architectures were SegNet, LinkNet, U-Net and U-Net with the VGG16 Encoder Pre-Trained on ImageNet (Unet_VGG16). Each CNN learned the supervised data of sacral pressure ulcers (PUs).

Results:

Among the four architectures, the best results were obtained with U-Net. U-Net demonstrated the second-highest accuracy in terms of the area under the curve (0.997) and a high specificity (0.943) and sensitivity (0.993), with the highest values obtained with Unet_VGG16. U-Net was also considered to be the most practical architecture and superior to the others in that the segmentation speed was faster than that of Unet_VGG16.

Conclusion:

The U-Net CNN constructed using appropriately supervised data was capable of segmentation with high accuracy. These findings suggest that eHealth wound assessment using CNNs will be of practical use in the future.

Hard-to-heal wounds include pressure ulcers (PU),1 diabetic foot ulcers (DFU)2,3 and venous leg ulcers (VLU).4,5 The increase in the prevalence of hard-to-heal wounds is an urgent issue that must be resolved in order to relieve pressure on the health-care economy. These wounds are increasingly treated by a range of health professionals in outpatient clinics or in the community, under which circumstances, the use of computer technology and cloud applications using mobile devices, such as smartphones and tablets is becoming more important.

Telemedicine is an essential part of the support system for clinical settings outside the hospital.6 Recently, the importance of the model for assessment of telemedicine (MAST) has been emphasised.7,8 Telecare and telehealth are under a state of rapid development. Of these a fundamental technology is an eHealth-supported wound assessment system using artificial intelligence (AI). However, at present, no device capable of automatically evaluating wounds has been developed, although the segmentation of wounds with considerable accuracy is possible.

Register now to continue reading

Thank you for visiting Journal of Wound Care's Silk Road Supplement and reading some of our peer-reviewed resources for healthcare professionals across Asia. To read more, please register today.

Register
Or continue by

Signing in with your registered email address

artificial intelligence
chronic wounds
convolutional neural networks
eHealth
wound assessment