|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Deep learning is gaining popularity as a superior method for various applications, including medical imaging analysis where large amounts of data need to be processed. This paper focuses on the difficult job of blood cell classification, and a deep learning model based on Convolutional Neural Networks (CNN) is developed to categorise blood cell pictures into subtypes. The suggested model outperformed conventional assessment factors when tested against a dataset including 13,000 pictures of blood cells and their subtypes. Blood and its constituents are vital for human existence and serve as markers for a variety of biological illnesses. Pathologists traditionally used optical microscopic blood images to diagnose disorders like AIDS, leukaemia, and others. Recently, computer-aided diagnosis systems have been developed to diagnose blood disorders from microscopic images By using a CNN as a feature extractor without the need for human feature engineering, the model can learn and extract valuable characteristics from photos. The model may then use the capabilities of both deep learning and standard machine learning by integrating the retrieved features with classic machine learning algorithms such as SVM, KNN, and Random Forest. It's also worth mentioning that analysing classifier performance based on five features extracted directly from photos is a fantastic approach to understand the value of each feature and decide which characteristics are more informative in order to categorise the task.
Keyword
Nearest Neighbours (KNN), , Support vector machine , Random Forest, CNN, White Blood Cells
PDF Download (click here)
|
|
|
|
|