Skin lesion tracking using structured graphical models

Mirzaalian, Hengameh; Lee, Tim K.; Hamarneh, Ghassan

doi:10.1016/j.media.2015.03.001

Cited by 33 publications

(12 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the time-varying acceleration coefficients [23] are used in this paper. It can be computed by formula (4) and (5).…”

Section: Parameter Optimisation Algorithmmentioning

confidence: 99%

“…In recent years, the machine learning and data mining algorithms employed in medical science have grown rapidly because they are intelligent in analysis and discovering knowledge from datasets [5][6][7][8][9]. Many studies used machine learning methods to treat skin diseases, such as melanoma [4][5][6], which is a type of skin cancer developing from melanocytes. Machine learning has also been used for skin cancer diagnosis [10][11][12][13], skin lesion classification [11,14,15] and skin sensitisation [16,17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Applying particle swarm optimization-based decision tree classifier for wart treatment selection

Liang

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Wart is a disease caused by human papillomavirus with common and plantar warts as general forms. Commonly used methods to treat warts are immunotherapy and cryotherapy. The selection of proper treatment is vital to cure warts. This paper establishes a classification and regression tree (CART) model based on particle swarm optimisation to help patients choose between immunotherapy and cryotherapy. The proposed model can accurately predict the response of patients to the two methods. Using an improved particle swarm algorithm (PSO) to optimise the parameters of the model instead of the traditional pruning algorithm, a more concise and more accurate model is obtained. Two experiments are conducted to verify the feasibility of the proposed model. On the hand, five benchmarks are used to verify the performance of the improved PSO algorithm. On the other hand, the experiment on two wart datasets is conducted. Results show that the proposed model is effective. The proposed method classifies better than k-nearest neighbour, C4.5 and logistic regression. It also performs better than the conventional optimisation method for the CART algorithm. Moreover, the decision tree model established in this study is interpretable and understandable. Therefore, the proposed model can help patients and doctors reduce the medical cost and improve the quality of healing operation.

show abstract

“…Therefore, the time-varying acceleration coefficients [23] are used in this paper. It can be computed by formula (4) and (5).…”

Section: Parameter Optimisation Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Applying particle swarm optimization-based decision tree classifier for wart treatment selection

Liang

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Lesion's thickness is the elevation present between the base and the surface of the lesion. In addition, registration methods may be applied to track skin lesions in images [136], or to detect changes in their structure over time, as the algorithm introduced by Huang and Bergstresser [127]. The authors proposed a new method for the melanoma registration, based on bipartite graph matching, in order to find sufficiently good correspondences between successive images of multiple skin lesions.…”

Section: Other Featuresmentioning

confidence: 99%

Computational methods for pigmented skin lesion classification in images: review and future trends

Oliveira

Papa

Pereira

et al. 2016

Neural Comput & Applic

172

View full text Add to dashboard Cite

Skin cancer is considered as one of the most common types of cancer in several countries, and its incidence rate has increased in recent years. Melanoma cases have caused an increasing number of deaths worldwide, since this type of skin cancer is the most aggressive compared to other types. Computational methods have been developed to assist dermatologists in early diagnosis of skin cancer. An overview of the main and current computational methods that have been proposed for pattern analysis and pigmented skin lesion classification is addressed in this review. In addition, a discussion about the application of such methods, as well as future trends, is also provided. Several methods for feature extraction from both macroscopic and dermoscopic images and models for feature selection are introduced and discussed. Furthermore, classification algorithms and evaluation procedures are described, and performance results for lesion classification and pattern analysis are given.

show abstract

“…Image registration can be done at a full-body level, i.e. full-body images are registered to detect the apparition of new moles or the growth of pre-existing ones [16][17] [18]. Image registration can also be done at the level of individual single skin lesions [19] [20].…”

Section: Introductionmentioning

confidence: 99%

Accurate Segmentation and Registration of Skin Lesion Images to Evaluate Lesion Change

Navarro¹,

Escudero-Viñolo²,

Bescós³

2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Skin cancer is a major health problem. There are several techniques to help diagnose skin lesions from a captured image. Computer-aided diagnosis (CAD) systems operate on single images of skin lesions, extracting lesion features to further classify them and help the specialists. Accurate feature extraction, which further depends on precise lesion segmentation, is key for the performance of these systems. In this paper, we present a skin lesion segmentation algorithm based on a novel adaptation of superpixels techniques and achieving the best reported results for the ISIC 2017 challenge dataset. Additionally, CAD systems have paid little attention to a critical criterion in skin lesion diagnosis: the lesion's evolution. This requires operating on two or more images of the same lesion, captured at different times but with a comparable scale, orientation and point of view; in other words, an image registration process should first be performed. We also propose in this work an image registration approach that outperforms top image registration techniques. Combined with the proposed lesion segmentation algorithm, this allows for the accurate extraction of features to assess the evolution of the lesion. We present a case-study with the lesion-size feature, paving the road for the development of automatic systems to easily evaluate skin lesion evolution.

show abstract

Skin lesion tracking using structured graphical models

Cited by 33 publications

References 38 publications

Applying particle swarm optimization-based decision tree classifier for wart treatment selection

Applying particle swarm optimization-based decision tree classifier for wart treatment selection

Computational methods for pigmented skin lesion classification in images: review and future trends

Accurate Segmentation and Registration of Skin Lesion Images to Evaluate Lesion Change

Contact Info

Product

Resources

About