Diabetic Foot Ulcer Segmentation using Color Space Models

Jawahar, Malathy; Anbarasi, L. Jani; Jasmine, S. Graceline; Narendra, Modigari

doi:10.1109/icces48766.2020.9138024

Cited by 20 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…DFU recognition) [2]. Another approach for building the DFU diagnosis system is to use a deep representation for building an end-to-end diagnosis system as in [2], [4], [5], [6], 7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17]. Although the literature showed that the deep-based DFU classification systems achieved better performance than handcrafted-based DFU classification [2], we argue that both deep and handcrafted features are important to distinguish between healthy and unhealthy skin regions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fusion of Hand-crafted and Deep Features for Automatic Diabetic Foot Ulcer Classification

Al-Garaawi¹,

Harbi²,

Morris³

2022

TEM Journal

View full text Add to dashboard Cite

This paper proposes to combine both the texture and deep features to build a robust diabetic foot ulcer recognition system since both features represent valuable information about the disease. The proposed system consists of three stages: feature extraction, feature fusion, and DFU classification. The feature extraction is performed by extracting the handcrafted and deep features. The feature fusion is performed by concatenating both feature vectors into a single vector. The DFU classification is performed by training a random forest classifier on the fusion vectors and the resulting classifier is used then for classification. Experimental results showed that the proposed approach provides satisfactory performance in DFU, ischaemia, and infection classification.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Moreover, deep features are also important as demonstrated in achievements in several medical and non-medical applications (e.g. DFU diagnosis) [6], [7], [8], [9] [13], [14], [15], [16], [17] [21], [22].…”

Section: Introductionmentioning

confidence: 99%

Fusion of Hand-crafted and Deep Features for Automatic Diabetic Foot Ulcer Classification

Al-Garaawi¹,

Harbi²,

Morris³

2022

TEM Journal

View full text Add to dashboard Cite

show abstract

“…Berdasarkan penelitian yang dilakukan Jawahar [24] dengan metode yang sama, belum menunjukan hasil yang baik dalam mendapatkan color space dari nilai HSV dan hanya melakukan satu kali masking sehingga akan mendapatkan hasil segmentasi luka yang kurang maksimal yang dapat dilihat pada Gambar 6.…”

Section: Hasil Dan Pembahasanunclassified

“…Metode Iterasi Gamma error Jawahar [24] HSV 0 0 0.06 Elmogy [25] CAD 0 0 0.06 Li [26] HSV 10 0 0.24 Rother [27] Grabcut 10 5 -…”

Section: Penelitimentioning

confidence: 99%

Segmentasi luka diabetes menggunakan algoritma contour image processing

Roshandri

Utami

Prasetio

2021

JSTIE

View full text Add to dashboard Cite

“…As a result, DFU segmentation has turned out to be an emergent area in the field of image segmentation. Several segmentation algorithms have been developed to perform automated DFU region detection [16,24,32]. State-of-the-art machine and deep learning object detection frameworks are increasingly applied to this problem [19,29,46,49].…”

Section: Introductionmentioning

confidence: 99%

Diabetic foot ulcer segmentation using logistic regression, DBSCAN clustering and mathematical morphology operators

Heras-Tang

Santiago

León-Mecías

et al. 2022

ELCVIA

View full text Add to dashboard Cite

Digital images are used for evaluation and diagnosis of a diabetic foot ulcer. Selecting the wound region (segmentation) in an image is a preliminary step for subsequent analysis. Most of the time, manual segmentation isn't very reliable because specialists could have different opinions over the ulcer border. This fact encourages researchers to find and test different automatic segmentation techniques. This paper presents a computer-aided ulcer region segmentation algorithm for diabetic foot images. The proposed algorithm has two stages: ulcer region segmentation, and post-processing of segmentation results. For the first stage, a trained machine learning model was selected to classify pixels inside the ulcer's region, after a comparison of five learning models. Exhaustive experiments have been performed with our own annotated dataset from images of Cuban patients. The second stage is needed because of the presence of some misclassified pixels. To solve this, we applied the DBSCAN clustering algorithm, together with dilation, and closing morphological operators. The best-trained model after the post-processing stage was the logistic regressor (Jaccard Index $0.81$, accuracy $0.94$, recall $0.86$, precision $0.91$, and F1 score $0.88$). The trained model was sensitive to irrelevant objects in the scene, but the patient foot. Physicians found these results promising to measure the lesion area and to follow-up the ulcer healing process over treatments, reducing errors.

show abstract

Diabetic Foot Ulcer Segmentation using Color Space Models

Cited by 20 publications

References 16 publications

Fusion of Hand-crafted and Deep Features for Automatic Diabetic Foot Ulcer Classification

Fusion of Hand-crafted and Deep Features for Automatic Diabetic Foot Ulcer Classification

Segmentasi luka diabetes menggunakan algoritma contour image processing

Diabetic foot ulcer segmentation using logistic regression, DBSCAN clustering and mathematical morphology operators

Contact Info

Product

Resources

About