Automatic Segmentation and classification of Skin Lesion Images

Taouil, Khaled; Romdhane, Nadra Ben

doi:10.1109/dfma.2006.296918

Cited by 17 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This experiment used the same data sets with the experiment 2, and took the group A as the sample of the classification learning as well as the group B & C as the test samples. This experiment used k-Nearest Neighbor (KNN) [11] to classify cell images, and took irregularity extraction methods in the reference [4] & reference [12] as our comparison algorithm whose results were shown in the Table 3. Seen from the Table 3, the metrics values of irregularity about classification accuracy in this paper was better than those in the reference [4] & reference [12].…”

Section: Experiments 3: To Analyze the Ability Of Classificationmentioning

confidence: 99%

“…This experiment used k-Nearest Neighbor (KNN) [11] to classify cell images, and took irregularity extraction methods in the reference [4] & reference [12] as our comparison algorithm whose results were shown in the Table 3. Seen from the Table 3, the metrics values of irregularity about classification accuracy in this paper was better than those in the reference [4] & reference [12]. The classification ability of anol r was slightly stronger than that of snol r , which was because the larger concavo convex region of the cell outline would influence the regularity of cell contour and the index anol r excludes effects of small convex region to show better classification ability.…”

Section: Experiments 3: To Analyze the Ability Of Classificationmentioning

confidence: 99%

“…The literature [3] used Gauss filtering method to smooth curves and determined the appropriate scale to measure irregularity with multiscale contour curvature model, which had computational complexity and large amount of calculation because there needed to track the extreme point of the curve in the smoothing process. The literature [4] measured the irregularity of profile by adding up the distance distribution of the focus of the closed contour curve to each point on the contour curve, which paid attention to the local change curve but still tend to similar circular contour. The literature [5,12] brought forward using local fractal dimension to measure the irregularity of profile curve, which obtained the multi-scale contour curve by using Gauss smoothing curve and computing the local fractal dimension of the smoothed curve.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cell Contour Irregularity Feature Extraction Methods based on Linear Geometric Heat Flow Curve Evolution

Xu¹,

Zhang²

2014

IJSIP

View full text Add to dashboard Cite

When the cytological smear method is used to check cervical lesions, the irregularity of the cells contour is essential for smear image interpretation and has the vital significance for research on computer aided diagnosis of cervical lesions. Aimed at measuring the regularity of cells outlines, based on the characteristic that the normal cell smears is generally circular, oval, convex polygon, we put forward a cell contour irregularity feature extraction and measurement method based on linear geometric heat flow curve evolution, in which the curve of cells outline is dealt with linear geometric heat flow curve evolution to totally convex (i.e. no curvature zero crossing) and compared with the original contour to extract indexes which can describe irregularity features of cell contour. Experimental results show that the method proposed in this paper can better describe the irregularity of cell contour and distinguish cells of different lesions.

show abstract

Section: Experiments 3: To Analyze the Ability Of Classificationmentioning

confidence: 99%

Section: Experiments 3: To Analyze the Ability Of Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cell Contour Irregularity Feature Extraction Methods based on Linear Geometric Heat Flow Curve Evolution

Xu¹,

Zhang²

2014

IJSIP

View full text Add to dashboard Cite

show abstract

“…Thresholding [6][7][8][9][10] and region growing are two simple yet widely used algorithms in the literature. They produce a satisfactory segmentation when skin lesions have clear boundaries.…”

Section: Introductionmentioning

confidence: 99%

A narrow band graph partitioning method for skin lesion segmentation

Yuan

Situ

Zouridakis

2009

Pattern Recognition

View full text Add to dashboard Cite

“…The adopted classifier was the artificial neural network (RUBEGNI et al, 2002). Taouil and Romdhane (2006) aimed at an automatic system for segmentation and diagnosis of melanomas. 62 images were analyzed between benign and malignant, in which obtained a hit rate between 89.5% to 95.8% using artificial neural network (TAOUIL; ROMDHANE, 2006).…”

Section: Automatic Sorting Using Artificial Neural Networkmentioning

confidence: 99%

Software for automatic diagnostic prediction of skin clinical images based on ABCD rule

Oselame¹,

Sanches²,

Kuntze³

et al. 2017

Biosci. J.

View full text Add to dashboard Cite

ABSTRACT:Cancer is responsible for about 7 million annual deaths worldwide. Among them, the melanoma type, responsible for 4% of the skin cancers, whose incidence has doubled in the last ten years. The processing of digital images has shown good potential for assistance in the early detection of melanomas. In this sense, the objective of the current study was to develop a software for clinical images processing and reach a score of accuracy higher than 95%. The ABCD rule was used as a guide for the development of computational analysis methods. MATLAB was used as programming environment for the development of the processing of digital images software. The images used were acquired from two banks of free images. They included images of melanomas (n=15) and nevi images (not cancer) (n=15). Images in RGB color channel were used, which were converted to grayscale, 8x8 median filter applications and 3x3 neighborhood approach technique. After, we proceeded to the binarization and inversion of black and white for later extraction of contour characteristics of the lesion. The classifier used was an artificial neural network of radial basis, getting accuracy for diagnosis of melanomas images of 100% and of 90.9% for not cancer images. Thus, global correction for diagnostic prediction was 95.5%. An area under the ROC graph 0.967 was achieved, suggesting a great diagnostic predictive ability. Besides, the software presents low cost use, since it can be run on most operating systems used nowadays.

show abstract

Automatic Segmentation and classification of Skin Lesion Images

Cited by 17 publications

References 28 publications

Cell Contour Irregularity Feature Extraction Methods based on Linear Geometric Heat Flow Curve Evolution

Cell Contour Irregularity Feature Extraction Methods based on Linear Geometric Heat Flow Curve Evolution

A narrow band graph partitioning method for skin lesion segmentation

Software for automatic diagnostic prediction of skin clinical images based on ABCD rule

Contact Info

Product

Resources

About