Abstract:
Our project Automated Multiclass liver disease diagnosis is used to diagnose normal,
fatty and Cirrhosis liver diseases. The methodology that we are intending to implement,
for detecting liver abnormalities in an automated manner is based on the ultrasound
images. We deal with cases that are on boundaries and train such Machine learning
algorithm to predict correct labels. To achieve this, created a website to predict liver
disease in which we only need a liver ultrasound image and our website predict liver
disease. Our trained model is Support Vector Classifier that helps us predicting Liver
diseases. Our model trained on features that are extracted from relevant liver ultrasound
images dataset. We extract features from each ultrasound image using Wavelet Packet
Transformation techniques this feature extraction techniques help us to get high end
results.
Fatty and Cirrhosis liver diseases are among the most serious disorder which can’t be
diagnosed at initial stages. Moreover, if these disorders are not captured initially, they
may eventually lead to serious and critical circumstances. As of now, the most accurate
method for the detection of most disorders of liver is Biopsy. A biopsy is a very
expensive and painful method [1]. Therefore, considering all these problems, we have
decided to jump into this problem and automate this complete process with the use of
Machine Learning Classifier.
Our proposed methodology for Automated Liver Disease Diagnosis will be a great help
for poor people as it will be less expensive and ultimately providing relief from pain to
the patients because they only need ultrasound images for predicting disease.
