ICARUS: Retrieving Skin Ulcer Images through Bag-of-Signatures

Chino, Daniel Yoshinobu Takada; Scabora, Lucas C.; Cazzolato, Mirela T.; Jorge, Ana Elisa Serafim; Traina, Caetano; Traina, Agma J. M.

doi:10.1109/cbms.2018.00022

Cited by 11 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Images were picked by specialists at random, aiming at maximizing diversity, e.g., tissue dominance, skin color, age, and treatment. The size of superpixels was set to 550 pixels according to the recommendations in [4,12]. As a result, 44,893 superpixels were detached and labeled as follows: (i) 37,187 superpixels with predominant healthy skin area, (ii) 3,974 fibrin superpixels, (iii) 3,284 superpixels with predominant granulation tissue, and (iv) 448 superpixels of necrosed tissue.…”

Section: Methodsmentioning

confidence: 99%

“…Regions of interest within images are detached either by parameter-specific methods, e.g., FCN-Net [29] and SegNet [27], or generic methods, e.g., uniform grids [5]. Superpixels are an alternative to both parameter-specific and generic methods, as they split an image I into k p regions with well-defined borders [12]. Such regions are automatically selected according to a construction algorithm.…”

Section: Preliminariesmentioning

confidence: 99%

“…where L is a discrete and disjoint set of labels and T is a training set that conditions the behavior of c. In the context of wounds, T summarizes the set of labeled superpixels S ⊆ S, i.e., T = { ε(s i ), l j | ∀ s i ∈ S ; L = ∪ j l j } for a feature extractor ε. The classifier's learning algorithm is a biased method that induces c from T to predict a label l ∈ L for any superpixel s j ∈ S. Examples of classifiers applied to tissue classification include Naïve-Bayes, Multi-Layer Perceptron (MLP), Support Vector Machines (SVM), Instance-based Learning (IbL), and RandomForest [8,9,10,12].…”

Section: Preliminariesmentioning

confidence: 99%

“…Their approaches are based on a divide-andconquer strategy, in which an ulcer is segmented with the support of superpixel construction methods [13]. Such methods are employed for splitting an image into several pieces of ulcered tissues with well-defined borders to be described by feature engineering methods, as MPEG-7 descriptors [4] and Bag-of-Signatures [12]. The features are labeled by the RandomForest classifier, which segments dermatological wounds with 89.87% accuracy [12].…”

mentioning

confidence: 99%

“…Such methods are employed for splitting an image into several pieces of ulcered tissues with well-defined borders to be described by feature engineering methods, as MPEG-7 descriptors [4] and Bag-of-Signatures [12]. The features are labeled by the RandomForest classifier, which segments dermatological wounds with 89.87% accuracy [12]. Those classifier-driven segmentation approaches also provide the basis for measurements of the size and stage of the wound [4,8,9,10,11,14,15].Recently, deep-learning (DL) models have been successfully applied to specific tissue segmentation problems, such as skin cancer and melanoma characterization [16,17,18].…”

mentioning

confidence: 99%

See 4 more Smart Citations

A superpixel-driven deep learning approach for the analysis of dermatological wounds

Blanco¹,

Traina²,

Traina³

et al. 2020

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Background. The image-based identification of distinct tissues within dermatological wounds enhances patients' care since it requires no intrusive evaluations. This manuscript presents an approach, we named QTDU , that combines deep learning models with superpixel-driven segmentation methods for assessing the quality of tissues from dermatological ulcers. Method. QTDU consists of a three-stage pipeline for the obtaining of ulcer segmentation, tissues' labeling, and wounded area quantification. We set up our approach by using a real and annotated set of dermatological ulcers for training several deep learning models to the identification of ulcered superpixels. Results. Empirical evaluations on 179,572 superpixels divided into four classes showed QTDU accurately spot wounded tissues (AUC = 0.986, sensitivity = 0.97, and specificity = 0.974) and outperformed machinelearning approaches in up to 8.2% regarding F1-Score through fine-tuning of a ResNet-based model. Last, but not least, experimental evaluations also showed QTDU correctly quantified wounded tissue areas within a 0.089 Mean Absolute Error ratio. Conclusions. Results indicate QTDU effectiveness for both tissue segmentation and wounded area quantification tasks. When compared to existing machine-learning approaches, the combination of superpixels and deep learning models outperformed the competitors within strong significant levels. can be automatically evaluated by Computer-Aided Diagnosis (CAD) tools, or even used for the searching of massive databases through content-only queries, as in Content-Based Image Retrieval (CBIR) applications. In both CAD and CBIR cases, the detection of abnormalities requires the extraction of patterns from images, while a decision-making strategy is necessary for juxtaposing new images to those in the database [4,5].Since dermatological lesions are routinely diagnosed by biopsies and surrounding skin aspects, ulcers can be computationally characterized by particular types of tissues (and their areas) within the wounded region [6,7]. For instance, Mukherjee et al.[8] proposed a five-color classification model and applied a color-based low-level extractor further labeled by a Support-Vector Machine (SVM) strategy at an 87.61% hit ratio. Such idea of concatenating feature extraction and classification is found at the core of most wound segmentation strategies, as in the study of Kavitha et al.[9] that evaluated leg ulcerations by extracting patterns based on local spectral histograms to be labeled by a Multi-Layer Perceptron (MLP) classifier with 87.05% accuracy. Analogously, Pereyra et al.[10] discussed the use of color descriptors and an Instancebased Learning (IbL) classifier with a 61.7% hit ratio, whereas Veredas et al. [11] suggested the use of texture descriptors and an MLP classifier with 84.84% accuracy.Blanco et al.[4] and Chino et al.[12] followed a slightly different premise for finding proper similarity measures and comparison criteria for dermatological wounds. Their approaches are based on a divide-andconquer stra...

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Preliminariesmentioning

confidence: 99%

Section: Preliminariesmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

A superpixel-driven deep learning approach for the analysis of dermatological wounds

Blanco¹,

Traina²,

Traina³

et al. 2020

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

The UTrack framework for segmenting and measuring dermatological ulcers through telemedicine

Cazzolato

Ramos

Rodrigues

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

A multi-task convolutional neural network for classification and segmentation of chronic venous disorders

Oliveira

Torres

Morais

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Chronic Venous Disorders (CVD) of the lower limbs are one of the most prevalent medical conditions, affecting 35% of adults in Europe and North America. Due to the exponential growth of the aging population and the worsening of CVD with age, it is expected that the healthcare costs and the resources needed for the treatment of CVD will increase in the coming years. The early diagnosis of CVD is fundamental in treatment planning, while the monitoring of its treatment is fundamental to assess a patient’s condition and quantify the evolution of CVD. However, correct diagnosis relies on a qualitative approach through visual recognition of the various venous disorders, being time-consuming and highly dependent on the physician’s expertise. In this paper, we propose a novel automatic strategy for the joint segmentation and classification of CVDs. The strategy relies on a multi-task deep learning network, denominated VENet, that simultaneously solves segmentation and classification tasks, exploiting the information of both tasks to increase learning efficiency, ultimately improving their performance. The proposed method was compared against state-of-the-art strategies in a dataset of 1376 CVD images. Experiments showed that the VENet achieved a classification performance of 96.4%, 96.4%, and 97.2% for accuracy, precision, and recall, respectively, and a segmentation performance of 75.4%, 76.7.0%, 76.7% for the Dice coefficient, precision, and recall, respectively. The joint formulation increased the robustness of both tasks when compared to the conventional classification or segmentation strategies, proving its added value, mainly for the segmentation of small lesions.

show abstract

ICARUS: Retrieving Skin Ulcer Images through Bag-of-Signatures

Cited by 11 publications

References 18 publications

A superpixel-driven deep learning approach for the analysis of dermatological wounds

A superpixel-driven deep learning approach for the analysis of dermatological wounds

The UTrack framework for segmenting and measuring dermatological ulcers through telemedicine

A multi-task convolutional neural network for classification and segmentation of chronic venous disorders

Contact Info

Product

Resources

About