Melanomand Benign Skin Lesion Classification using Back propagation Neural Network

Description

Melanomand Benign Skin Lesion Classification

Abstract:

Classification of skin lesions plays a crucial role in diagnosing various, local and gene-related, medical conditions in the field of dermoscopy. Estimation of these biomarkers are used to provide some insight while detecting cancerous cells and classifying the lesion as either benign or malignant. This paper presents groundwork for detection of skin lesions with cancerous inclination by segmentation and subsequent application of Neural Network on dermoscopy images, Images with skin lesions were segmented based on individual channel intensity Thresholding. The resultant images were fed into NN for feature extraction. The extracted features were then used for classification by an NN classifier. Previously, several approaches have been used for subject diagnostic with varying degree of success. However, room is still available for exploring other techniques for improving proportion of successfully detected malignant lesions. Melanomand Benign Skin Lesion Classification


Melanomand Benign Skin Lesion Classification

Introduction:

  • Skin cancers are cancers that arise from the skin. They are due to the development of abnormal cells that have the ability to invade or spread to other parts of the body.
  • There are three main types of skin cancers: basal-cell skin cancer (BCC), squamous cell skin cancer (SCC), and melanoma. The first two, along with a number of less common skin cancers, are known as nonmelanoma skin cancer (NMSC).
  • Basal-cell cancer grows slowly and can damage the tissue around it but is unlikely to spread to distant areas or result in death. It often appears as a painless raised area of skin that may be shiny with small blood vessels running over it or may present as a raised area with an ulcer.
  • Squamous-cell skin cancer is more likely to spread. It usually presents as a hard lump with a scaly top but may also form an ulcer. Melanomas are the most aggressive.
  • Signs include a mole that has changed in size, shape, color, irregular edges, has more than one color, is itchy, or bleeds. A skin that has inadequate melanin is exposed to the risk of sunburn as well as harmful ultraviolet rays from the sun. Clinical analysis and biopsy tests are commonly used.

System Analysis

 Existing Systems

  • Principal Component Analysis
  • Local binary pattern and shape features
  • KNN and FNN classifier

Drawbacks of Existing method

  • High Computational load and poor discriminatory power.
  • LBP doesn’t differentiate the local texture region.
  • FNN is slow training for a large feature set.
  • Less accuracy in classification

Proposed Method

  • Skin lesion classification for Computer-Aided Diagnosis (CAD) system based on,
  • Hybrid features involve color features and texture descriptors
  • Neural Network classifier

Advantages

  • Fast and better compatible in classification.
  • Low computational complexity
  • Better efficiency and less sensitive to noise
  • High accuracy
  • Take less time to process

Requirement Specifications

Hardware Requirements

  • system
  • 4 GB of RAM
  • 500 GB of Hard disk

SOFTWARE REQUIREMENTS:


Block Diagram

Melanomand Benign Skin Lesion Classification using Back propagation Neural Network


Colour Space Conversion

Color space conversion happens when a Color Management Module (CMM) translates color from one device’s space to another. Conversion may require approximations in order to preserve the image’s most important color qualities.

  • The use of color in image processing is prompted by the useful resource of the number one factor. First, shade is a powerful descriptor that frequently simplifies object identity and extraction from a scene. Second, human beings can determine plenty of shade solar shades and intensities, in comparison to approximately only two dozen sun sunglasses of gray. This 2d aspect is especially important in manual photo assessment.

GLCM feature extraction

  • In statistical texture analysis, texture features are computed from the statistical distribution of observed combinations of intensities at specified positions relative to each other in the image. According to the number of intensity points (pixels) in each combination, statistics are classified into first-order, second-order, and higher-order statistics.
  • The Gray Level Concurrence Matrix (GLCM) method is a way of extracting second-order statistical texture features. The approach has been used in a number of applications, Third and higher-order textures consider the relationships among three or more pixels.

ABCD Parameters

The ABCDE Rule of skin cancer is an easy-to-remember system for determining whether a mole or growth may be cancerous. They describe the physical condition and/or progression of any skin abnormality that would suggest the development of a malignancy.

  • A for Asymmetry
  • B for Border
  • C for Color
  • D for Diameter
  • E for Elevation

BPN Training and Classification

           As is clear from the diagram, the working of BPN is in two phases. One phase sends the signal from the input layer to the output layer, and the other phase back propagates the error from the output layer to the input layer. For training, BPN will use binary sigmoid activation function Back-propagation is the essence of neural net training. It is the method of fine-tuning the weights of a neural net based on the error rate obtained in the previous epoch (i.e., iteration). Proper tuning of the weights allows you to reduce error rates and to make the model reliable by increasing its generalization


REFERENCES

[1]Adherence Santy and Adheena Santy, Segmentation Methods For Computer-Aided Melanoma Detection, IEEE Conference,2015.

?[2] Omar Abuzaghleh, Miad Faezipour, and Buket D.Barkana, A Comparison of Feature Sets for an automated Skin Lesion Analysis System for Melanoma Early Detection and Prevention, IEEE journal,2015.?

[3] M. Rademaker and A. Oakley, Digital monitoring by whole-body photography and sequential digital dermoscopy detect thinner melanomas, IEEE journal,2010.

?[4] Xiaojing Yuan, Zhenyu Yang, George Zouridakis, and Nizar Mullani >?

[5] Abder-Rahman Ali, Micael S. Couceiro, and Aboul Ella Hassenian, Melanoma Detection Using Fuzzy CMeans Clustering Coupled With Mathematical Morphology, IEEE Conference,2014

?[6] Rebecca Moussa, Firas Gerges, Christian Salem, Romario Akiki, Omar Falou, and Danielle Azar, Computer-aided Detection of Melanoma Using Geometric Features, IEEE Conference,2012?

[7] M. Moncrieff, S. Cotton, P. Hall, R. Schiffner, U. Lipski, and E. Claridge, Siascopy assists in the diagnosis of melanoma by utilizing computer vision techniques to visualize the internal structure of the skin,2001.

?[8] Supriya Joseph and Janu R Panicker, Skin Lesion Analysis System for Melanoma Detection with an Effective Hair Segmentation Method, IEEE Conference,2016

?[9] Omar Abuzaghleh, Buket D. Barkana, And Miad Faezipour, Noninvasive Real-Time Automated Skin Lesion Analysis System For Melanoma Early Detection And Prevention, IEEE Journal,2015 [10]Reda Kasmi and Karim Mokrani, Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule, IEEE Journal,2015?

[10] G. L. Marcialis, A. Lewicke, B. Tan, P. Coli, D. Grimberg, A. Congiu, et al., ?First international fingerprint liveness detection competition? Livet 2009,? in Proc. IAPR ICIAP, Springer LNCS-5716. 2009, pp. 12? 23.


 

Customer Reviews

There are no reviews yet.

Be the first to review “Melanomand Benign Skin Lesion Classification using Back propagation Neural Network”

This site uses Akismet to reduce spam. Learn how your comment data is processed.