Segmentation and Classification of Skin Lesions for Disease Diagnosis

Sumithra, R.; Suhil, Mahamad; Guru, D. S.

doi:10.1016/j.procs.2015.03.090

Cited by 176 publications

(76 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to its outstanding generalization capability and reputation of being a highly accurate paradigm, an SVM classier [40] is employed in the current detection framework. As a very effective method for universal purpose pattern recognition, SVM has been proposed by Vapnik [41,42], which is characterized by a substantial resistance to overfitting, a long-standing and inherent problem for several supervised learning algorithms (e.g., neural networks and decision trees).…”

Section: Skin Lesion Classificationmentioning

confidence: 99%

An SVM Framework for Malignant Melanoma Detection Based on Optimized HOG Features

Bakheet

2017

Computation

View full text Add to dashboard Cite

Early detection of skin cancer through improved techniques and innovative technologies has the greatest potential for significantly reducing both morbidity and mortality associated with this disease. In this paper, an effective framework of a CAD (Computer-Aided Diagnosis) system for melanoma skin cancer is developed mainly by application of an SVM (Support Vector Machine) model on an optimized set of HOG (Histogram of Oriented Gradient) based descriptors of skin lesions. Experimental results obtained by applying the presented methodology on a large, publicly accessible dataset of dermoscopy images demonstrate that the proposed framework is a strong contender for the state-of-the-art alternatives by achieving high levels of sensitivity, specificity, and accuracy (98.21%, 96.43% and 97.32%, respectively), without sacrificing computational soundness.

show abstract

Section: Skin Lesion Classificationmentioning

confidence: 99%

An SVM Framework for Malignant Melanoma Detection Based on Optimized HOG Features

Bakheet

2017

Computation

View full text Add to dashboard Cite

show abstract

“…The texture descriptors, on the other hand, for this work will make use the approach described by Arifin et al [1] and Sumithra et al [10]. The proposed approach uses a Gray level Co-Occurrence Matrix (GLCM) for their automated system that detects different skin anomalies.…”

Section: Texture-based Attribute For the Multi-model Multi-levelmentioning

confidence: 99%

“…A study done by Sumithra et al [10] proposed a system that focuses on segmentation and classification of skin lesions for disease diagnosis. Their system used color, texture, and color histogram to represent the images.…”

Section: Introductionmentioning

confidence: 99%

Design and Evaluation of a Multi-model, Multi-level Artificial Neural Network for Eczema Skin Lesion Detection

Guzman

Maglaque

Torres

et al. 2015

2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)

View full text Add to dashboard Cite

There are several current systems developed to identify common skin lesions such as eczema that utilize image processing and most of these apply feature extraction techniques and machine learning algorithms. These systems extract the features from pre-processed images and use them for identifying the skin lesions through machine learning as the core. This paper presents the design and evaluation of a system that implements a multi-model, multi-level system using the Artificial Neural Network (ANN) architecture for eczema detection. In this work, multi-model system is defined as architecture with different models depending on the input characteristic. The outputs of these models are integrated by a decision layer, thus multi-level, which computes the probability of an eczema case. The resulting system has 68.37% average confidence level as opposed to the 63.01% of the single level, i.e. single model, system in the actual testing of eczema versus non-eczema cases. Furthermore, the multi-model, multi-level design produces more stable models in the training phase wherein overfitting was reduced.

show abstract

“…However, these methods use hand-crafted features, and therefore rely on an accurate segmentation of the lesion [2]. Moreover, lesion segmentations have been used to assist melanoma diagnosis [10,21,24]. This motivates the use of deep learning based computer-aided diagnosis systems to improve the accuracy and sensitivity of melanoma detection methods.…”

Section: Introductionmentioning

confidence: 99%

Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis

Abhishek

Hamarneh

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Skin lesion segmentation is a vital task in skin cancer diagnosis and further treatment. Although deep learning based approaches have significantly improved the segmentation accuracy, these algorithms are still reliant on having a large enough dataset in order to achieve adequate results. Inspired by the immense success of generative adversarial networks (GANs), we propose a GAN-based augmentation of the original dataset in order to improve the segmentation performance. In particular, we use the segmentation masks available in the training dataset to train the Mask2Lesion model, and use the model to generate new lesion images given any arbitrary mask, which are then used to augment the original training dataset. We test Mask2Lesion augmentation on the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset and achieve an improvement of 5.17% in the mean Dice score as compared to a model trained with only classical data augmentation techniques.

show abstract

Segmentation and Classification of Skin Lesions for Disease Diagnosis

Cited by 176 publications

References 10 publications

An SVM Framework for Malignant Melanoma Detection Based on Optimized HOG Features

An SVM Framework for Malignant Melanoma Detection Based on Optimized HOG Features

Design and Evaluation of a Multi-model, Multi-level Artificial Neural Network for Eczema Skin Lesion Detection

Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis

Contact Info

Product

Resources

About