Scribd
Upload
113 views

Title: Medical Image Classification Using Artificial Neural Networks

This document describes a project to classify medical images using artificial neural networks. The objective is to create an automated machine learning algorithm to classify images such as CT, MRI, and PET scans with and without transformations. The proposal involves applying feature transforms to medical images, extracting features, using a classifier to measure performance, and comparing the results. The work plan is to apply transforms from September to December, extract features from December to January, use a classifier from January to February, measure performance from February to March, and report the results in March.

Uploaded by

Nnabimanyu Abi
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
113 views

Title: Medical Image Classification Using Artificial Neural Networks

This document describes a project to classify medical images using artificial neural networks. The objective is to create an automated machine learning algorithm to classify images such as CT, MRI, and PET scans with and without transformations. The proposal involves applying feature transforms to medical images, extracting features, using a classifier to measure performance, and comparing the results. The work plan is to apply transforms from September to December, extract features from December to January, use a classifier from January to February, measure performance from February to March, and report the results in March.

Uploaded by

Nnabimanyu Abi
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 12

TITLE

MEDICAL IMAGE CLASSIFICATION


USING ARTIFICIAL NEURAL
NETWORKS
PROJECT MEMBERS

S.GUGAPRIYA (26EC29)
D.LALITHA (26EC47)
N.N.ABIMANYU (26EC01)

Project Guidance:

Mr.S.RAJA,M.E.,
Lecturer,
Department of ECE.
OBJECTIVE OF OUR
PROJECT

To create an automated machine learning


algorithm for classifying medical images
such as CT,MRI,PET,etc… with and without
applying transformations and comparing
their performances
EXISTING METHOD
 COMPARATIVE STUDY ON MEDICAL
IMAGE CLASSIFICATION BASED ON
WAVELET AND RIDGELET
TRANSFORMATIONS (Ridgelet
transform provided efficient results than
wavelet in case of denoising and
approximation of images with straight
edges)
PROPOSAL OF OUR PROJECT
MEDICAL
IMAGES
FEATURE PERFORMANCE
TRANSFORMS CLASSIFIER
EXTRACTION MEASUREMENT

FEATURE PERFORMANCE
CLASSIFIER
EXTRACTION MEASUREMENT

COMPARISION

RESULT
WORKPLAN

Month Module
September Applying Transform
December Feature Extraction
January Classifier
February Performance Measurement
& Comparison

March Results
Transform Of Normal Image
Transform Of Abnormal Image
Pixel Values

Type Maximum value of Minimum value of


pixel pixel
Normal 255 1
Abnormal 255 1
REFERENCES
 “A Comparison of Wavelet-Based and Ridgelet-Based
Texture Classification of Tissues in Computed Tomography “
Lindsay Semler and Lucia Dettori, Intelligent Multimedia
Processing Laboratory School of Computer Science,
Telecommunications & Information Systems,
DePaul University, Chicago, USA.

 “A New Adaptive Ridgelet Neural Network” Shuyuan Yang,


Min Wang and Licheng Jiao, Institute of Intelligence
Information Processing, Xidian University, China.
REFERENCES(contd.)
 “The finite Ridgelet transformation for Image
Representation”
Minh N. Do, Member, IEEE, and Martin Vetterli, Fellow,
IEEE Signal Processing Society

 “Wavelets in Medical Image Processing: Denoising,


Segmentation, and Registration”
Yinpeng Jin, Elsa Angelini and Andrew Laine
Department of Biomedical Engineering, Columbia
University, New York, NY, USA
THANK YOU

You might also like