Analysis of various techniques of feature extraction on skin lesion images

Sengupta, Sudhriti; Mittal, Neetu

doi:10.1109/icrito.2017.8342508

Cited by 7 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feature extraction in dermoscopy images using random forest classifier and neural networks was introduced by the year 2016. In 2017, 3D depth analysis and reconstruction algorithm were introduced . The ACO has been used for edge detection of images and the automatic ant colony‐based segmentation was proposed by Dalila et al The ACO combined with adaptive thresholding was applied to derive well‐connected edge map of skin lesion images .…”

Section: Related Workmentioning

confidence: 99%

Improved skin lesion edge detection method using Ant Colony Optimization

2019

Self Cite

View full text Add to dashboard Cite

Background: Skin lesion edge detection is a significant step in developing an automatized diagnostic system. The efficient diagnostic system leads to correct identification and detection of skin lesion diseases. In this paper, ant colony optimization (ACO) technique is used to improve the edge contour of skin lesion images. Material and Method:Firstly, a three-stage preprocessing methodology involving color space conversion, contrast enhancement, and filtering is applied to improve the skin lesion image quality. The edge map is obtained by applying three types of conventional edge detection methods namely Canny, Sobel, and Prewitt. Thereafter, ACO is applied on these images to produce an improved edge contour. Result: The improvement of the proposed methodology is quantitatively verified by analysis of the entropy of the final image obtained by conventional and proposed techniques. Conclusion: From the result analysis, we can conclude that introduction of ACO has increased the efficiency of the conventional edge detection method in skin lesion images. K E Y W O R D S Ant Colony Optimization, Canny, edge detection, Prewitt, skin lesions, Sobel How to cite this article: Sengupta S, Mittal N, Modi M. Improved skin lesion edge detection method using Ant Colony Optimization. Skin Res Technol. 2019;25:846-856.

show abstract

Section: Related Workmentioning

confidence: 99%

Improved skin lesion edge detection method using Ant Colony Optimization

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the CT images are subjected to irregular variations in the human anatomical structures like bony outgrowths, cavitary lesions, vascular areas and soft tissues with varying densities and intensities [3][4]. Such complex medical images with cryptic data and irregular contours are innate in nature and highly tedious to process and interpret [5][6][7]. Further, the quality of CT images is downgraded due to presence of unwanted noise, poor contrast, weak edges and lack of homogeneity.…”

Section: Related Workmentioning

confidence: 99%

Early and Precise Detection of Pancreatic Tumor by Hybrid Approach with Edge Detection and Artificial Intelligence Techniques

Dhruv¹,

Mittal²,

Modi³

2018

EAI Endorsed Transactions on Pervasive Health and Technology

Self Cite

View full text Add to dashboard Cite

INTRODUCTION: Pancreatic cancer is highly lethal as it grows, spreads rapidly and difficult to diagnose at its early stages. It can be identified through scan images. The tumorous images obtained from imaging techniques suffer from the drawback of cryptic data due to presence of unwanted noise and poor contrast. OBJECTIVE: To reduce the risk of pancreatic cancer, its detection and diagnosis at an early stage becomes crucial. METHODS: The proposed work encompasses the processing of CT scans of pancreatic tumor using classical and artificial intelligence based optimized edge detection techniques for optimization and detection of tumor. RESULTS: The simulation results are highly encouraging as evident from the far improved visibility of resultant images with Particle Swarm Optimization. CONCLUSION: The output image with PSO shows the quality enhanced CT images which helps in accurate detection and diagnosis of the pancreatic tumor at an early stage providing an aid in medical imaging.

show abstract

“…The ABCDE rule (Asymmetry, Border, Color, Diameter, Evolve), the 7-point checklist, and the Menzies technique are three clinical diagnosis methods used by dermatologists to distinguish melanoma from nevus [4]. These feature extraction techniques are dependent on lesion color, shape, geometry, texture, and structure [5]. An important screening tool for the detection of melanoma with accurate sensitivity and specificity is ABCD [6]".…”

Section: Introductionmentioning

confidence: 99%

An automatic feature extraction technique from the images of granular parakeratosis disease

Janthakal¹,

Hosalli²

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

The largest and most vital part of the human body is skin and any change in the features of skin is termed as a skin lesion. The paper considers granular parakeratosis lesion that is an epidermal reaction occurring due to the disorder of keratinization, and mainly seen in intertriginous areas. The manual inspection of the lesion features is a bit cumbersome due to which an automated system is proposed in this paper. The main goal is to determine the size and depth of granular parakeratosis lesions using the proposed ensemble algorithm, partition clustering and region properties method. As a flow of the proposed model, segmentation is done using U-net with binary cross entropy, features are extracted using partition clustering and region properties method, and classification is done using SVM 10-fold model. The proposed feature extraction method estimates the depth and absolute size of K lesions in each image by predicting the absolute height and width of the lesion in terms of pixel square. After extracting the features, classification is done, thereby obtaining an accuracy of 95%, sensitivity and specificity of 100%. The proposed model provides better performance compared to state-of-the-art models. The main application of this automated system is in dermatology field where some skin lesions have same features which makes the experts to diagnose the disease incorrectly. If the proposed system is incorporated, diagnosis can be done in an effective manner considering all the relevant features.

show abstract

Analysis of various techniques of feature extraction on skin lesion images

Cited by 7 publications

References 41 publications

Improved skin lesion edge detection method using Ant Colony Optimization

Improved skin lesion edge detection method using Ant Colony Optimization

Early and Precise Detection of Pancreatic Tumor by Hybrid Approach with Edge Detection and Artificial Intelligence Techniques

An automatic feature extraction technique from the images of granular parakeratosis disease

Contact Info

Product

Resources

About