Automatic Lesion Detection System (ALDS) for Skin Cancer Classification Using SVM and Neural Classifiers

Abstract

Technology aided platforms provide reliable tools in almost every field these days. These tools being supported by computational power are significant for applications that need sensitive and precise data analysis. One such important application in the medical field is Automatic Lesion Detection System (ALDS) for skin cancer classification. Computer aided diagnosis helps physicians and dermatologists to obtain a "second opinion" for proper analysis and treatment of skin cancer. Precise segmentation of the cancerous mole along with surrounding area is essential for proper analysis and diagnosis. This paper is focused towards the development of improved ALDS framework based on probabilistic approach that initially utilizes active contours and watershed merged mask for segmenting out the mole and later SVM and Neural Classifier are applied for the classification of the segmented mole. After lesion segmentation, the selected features are classified to ascertain that whether the case under consideration is melanoma or non-melanoma. The approach is tested for varying datasets and comparative analysis is performed that reflects the effectiveness of the proposed system.

Melanoma Skin Cancer Detection by Segmentation and Feature Extraction using combination of OTSU and STOLZ Algorithm Technique

“…After lesion segmentation, the selected features are classified to ascertain that whether the case under consideration is melanoma or non-melanoma. [2] The Melanoma Skin Cancer Detection and Feature Extraction through Image Processing Techniques by et al Dr. S.Gopinathan, S. Nancy Arokia Rani suggested a method for an approach to detect the melanoma skin cancer and feature extraction through various image processing techniques .The input for the system is the skin lesion which is uncertain to be melanoma cancer. The image is pre-processed to ejection of hair and noise etc.…”

“…The TDS Index is computed using the following equation: TDS = 1.3A + 0.1B + O.5C +0.5D…………........... (2) If the TDS Index is less than 4.75, it is benign (noncancerous) skin lesion. If the TDS Index is greater than 4.75, and less than 5.45, it is suspicious case of skin lesion.…”

Surveys on Detection of Melanoma through Image Processing Techniques

“…Output is in the form of TDS score and Classification result. G. Muhammad Ali Farooq et al [7] described ALDS framework based on probabilistic approach that at starts it utilizes active contours and watershed merged mask for segmenting out the mole and later SVM and Neural Classifier are applied for the classification of the segmented mole. After lesion segmentation, the selected features are classified to ascertain that whether the case under consideration is melanoma or non-melanoma.…”

Study of Techniques Used For Segmentation and Classification of Skin Lesion

“…V demonstrates the vector instatement amid bolster vector machine operation. As proposed by [9],In the underlying perception results were not predictable, subsequently closeness file was watched, utilizing the accompanying condition Equation 2:Similarity Index U x and U y demonstrates the participation capacities whose esteem lies in the vicinity of 0 and 1. After this progression include extraction and correlation is performed utilizing SVM and ANN systems.…”

“…Bolster vector machine is one of the viable pictures preparing division instrument used to recognize recognized part from the first part. [9]proposed exact division procedure. Exact division of the contaminated territory alongside encompassing region is basic for precise examination and analysis of lesion.…”