Skin lesion images classification using new color pigmented boundary descriptors

Mahdiraji, Saeid Amouzad; Baleghi, Yasser; Sakhaei, Sayed Mahmoud

doi:10.1109/pria.2017.7983026

Cited by 16 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Reference [ 13 ], a novel boundary descriptor based on the color variation of the skin lesion input images, achieved with standard cameras, is introduced. Furthermore, in order to reach higher performance, a set of textural and morphological features is added.…”

Section: Related Workmentioning

confidence: 99%

Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection

Manzo

Pellino²

2020

J. Imaging

View full text Add to dashboard Cite

Malignant melanoma is the deadliest form of skin cancer and, in recent years, is rapidly growing in terms of the incidence worldwide rate. The most effective approach to targeted treatment is early diagnosis. Deep learning algorithms, specifically convolutional neural networks, represent a methodology for the image analysis and representation. They optimize the features design task, essential for an automatic approach on different types of images, including medical. In this paper, we adopted pretrained deep convolutional neural networks architectures for the image representation with purpose to predict skin lesion melanoma. Firstly, we applied a transfer learning approach to extract image features. Secondly, we adopted the transferred learning features inside an ensemble classification context. Specifically, the framework trains individual classifiers on balanced subspaces and combines the provided predictions through statistical measures. Experimental phase on datasets of skin lesion images is performed and results obtained show the effectiveness of the proposed approach with respect to state-of-the-art competitors.

show abstract

Section: Related Workmentioning

confidence: 99%

Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection

Manzo

Pellino²

2020

J. Imaging

View full text Add to dashboard Cite

show abstract

“…we used 'disc' as the structural element with 9 X 9 value for all images used in our study . Figure 4 compares the performance of segmentation with other existing approaches [16][17]. it was ensured that the proposed work produces best segmentation than the existing approaches also it compares the accuracy measures with state of art…”

Section: Resultsmentioning

confidence: 97%

Automated Framework for Segmenting Skin Lesions using Artificial Bee Colony Optimization with Morphological Reconstruction

Sumathi¹,

Venkatesulu²

2019

IJEAT

View full text Add to dashboard Cite

Nowadays, Many people are affected by skin cancers. Our proposed work designed a framework to extract the skin cancer using artificial bee colony with morphological reconstruction filters, which helps the demonologist to prevent the severity in early stage, Melanoma is the now become a harmful form of skin cancer which leads the skin cells to grow rapidly and form cancerous tumors. We collected various melanoma images from having used samples from public dataset like ISIC archive and a few from clinical datasets. To remove the noise, median filtering is used for preprocessing in the first step, to segment the tumor boundary Artificial bee colony is used and to remove the unwanted pixels using morphological reconstruction filters. Segmentation metrics like precision, recall, accuracy, Mean Square Error, Peak signal to noise ratio and computational time were calculated. Our proposed method yield 97.7% segmentation accuracy when compared with the level set method and Fuzzy C Means clustering techniques

show abstract

“…Currently visual examination is considered as the standard clinical procedure for detection and identification of skin lesions [6]. One of the most popular protocols for medical assessment of the lesions on the skin is the 'ABCD' protocol, according to which the dermatologist examines the asymmetry (A), the border (B), the colour (C) and the diameter (D) of the spot on the skin.…”

Section: Introductionmentioning

confidence: 99%

“…Mahdiraji et al in [6] calculated boundary features which were processed by neural networks to perform classification of skin lesions using sets of images acquired from conventional cameras. Mishra et al [18] and Jafari et al [19] presented segmentation approaches which can isolate the skin spot (i.e.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Cancer Diagnosis

Naronglerdrit¹,

Mporas²

2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

This chapter presents a methodology for diagnosis of pigmented skin lesions using convolutional neural networks. The architecture is based on convolutional neural networks and it is evaluated using new CNN models as well as retrained modification of pre-existing CNN models were used. The experimental results showed that CNN models pre-trained on big datasets for general purpose image classification when re-trained in order to identify skin lesion types offer more accurate results when compared to convolutional neural network models trained explicitly from the dermatoscopic images. The best performance was achieved by retraining a modified version of ResNet-50 convolutional neural network with accuracy equal to 93.89%. Analysis on skin lesion pathology type was also performed with classification accuracy for melanoma and basal cell carcinoma being equal to 79.13% and 82.88%, respectively.

show abstract

Skin lesion images classification using new color pigmented boundary descriptors

Cited by 16 publications

References 17 publications

Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection

Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection

Automated Framework for Segmenting Skin Lesions using Artificial Bee Colony Optimization with Morphological Reconstruction

Deep Learning for Cancer Diagnosis

Contact Info

Product

Resources

About