Deep learning approach based on superpixel segmentation assisted labeling for automatic pressure ulcer diagnosis

Che, Chang; Christian, Mesakh; Chang, Dun Hao; Lai, Feipei; Liu, Tom J.; Chen, Yo Shen; Chen, Wei-Jen

doi:10.1371/journal.pone.0264139

Cited by 23 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images taken using a flash were processed to eliminate overexposed pixels [ 36 , 57 ]. Other techniques included grayscale image production [ 58 ], skin detection by using color channel thresholding [ 22 ], and simple linear iterative clustering (SLIC) [ 59 , 60 ].…”

Section: Resultsmentioning

confidence: 99%

“…Images taken using a flash were processed to eliminate overexposed pixels [36,57]. Other techniques included grayscale image production [58], skin detection by using color channel thresholding [22], and simple linear iterative clustering (SLIC) [59,60]. The most commonly used techniques were cropping (mentioned in 17 articles) and resizing (mentioned in 15 articles).…”

Section: Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Towards Home-Based Diabetic Foot Ulcer Monitoring: A Systematic Review

Kairys

Pauliukiene

Raudonis

et al. 2023

Sensors

View full text Add to dashboard Cite

It is considered that 1 in 10 adults worldwide have diabetes. Diabetic foot ulcers are some of the most common complications of diabetes, and they are associated with a high risk of lower-limb amputation and, as a result, reduced life expectancy. Timely detection and periodic ulcer monitoring can considerably decrease amputation rates. Recent research has demonstrated that computer vision can be used to identify foot ulcers and perform non-contact telemetry by using ulcer and tissue area segmentation. However, the applications are limited to controlled lighting conditions, and expert knowledge is required for dataset annotation. This paper reviews the latest publications on the use of artificial intelligence for ulcer area detection and segmentation. The PRISMA methodology was used to search for and select articles, and the selected articles were reviewed to collect quantitative and qualitative data. Qualitative data were used to describe the methodologies used in individual studies, while quantitative data were used for generalization in terms of dataset preparation and feature extraction. Publicly available datasets were accounted for, and methods for preprocessing, augmentation, and feature extraction were evaluated. It was concluded that public datasets can be used to form a bigger, more diverse datasets, and the prospects of wider image preprocessing and the adoption of augmentation require further research.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Images taken using a flash were processed to eliminate overexposed pixels [36,57]. Other techniques included grayscale image production [58], skin detection by using color channel thresholding [22], and simple linear iterative clustering (SLIC) [59,60]. The most commonly used techniques were cropping (mentioned in 17 articles) and resizing (mentioned in 15 articles).…”

Section: Preprocessingmentioning

confidence: 99%

Towards Home-Based Diabetic Foot Ulcer Monitoring: A Systematic Review

Kairys

Pauliukiene

Raudonis

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…There are some previously published studies proposing different deep learning algorithms to do the wound segmentation as we mentioned before [10][11][12][13][14][32][33][34] . The types of deep learning, their performance, and other details are listed in Table 3.…”

Section: Discussionmentioning

confidence: 99%

Automatic segmentation and measurement of pressure injuries using deep learning models and a LiDAR camera

Liu

Wang

Christian

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Pressure injuries are a common problem resulting in poor prognosis, long-term hospitalization, and increased medical costs in an aging society. This study developed a method to do automatic segmentation and area measurement of pressure injuries using deep learning models and a light detection and ranging (LiDAR) camera. We selected the finest photos of patients with pressure injuries, 528 in total, at National Taiwan University Hospital from 2016 to 2020. The margins of the pressure injuries were labeled by three board-certified plastic surgeons. The labeled photos were trained by Mask R-CNN and U-Net for segmentation. After the segmentation model was constructed, we made an automatic wound area measurement via a LiDAR camera. We conducted a prospective clinical study to test the accuracy of this system. For automatic wound segmentation, the performance of the U-Net (Dice coefficient (DC): 0.8448) was better than Mask R-CNN (DC: 0.5006) in the external validation. In the prospective clinical study, we incorporated the U-Net in our automatic wound area measurement system and got 26.2% mean relative error compared with the traditional manual method. Our segmentation model, U-Net, and area measurement system achieved acceptable accuracy, making them applicable in clinical circumstances.

show abstract

“…The research on music automatic labeling has high value in both theoretical research and practical application. The deep CNN (Convolutional Neural Network) model in the field of deep learning has achieved good results in the fields of image and voice [8][9] . In this paper, the word vector of lyrics is used as input information, and a multimodal music automatic annotation model based on CNN and SAM(Self-attention mechanism) is proposed.…”

Section: Introductionmentioning

confidence: 99%