Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/8103
Title: | The detection and classification of blast cell in Leukaemia Acute Promyelocytic Leukaemia (AML M3) blood using simulated annealing and neural networks |
Authors: | Ismail, W Hassan, R Payne, A Swift, S |
Keywords: | Heuristic search;Simulated annealing;Classification;Leukaemia cells |
Issue Date: | 2011 |
Citation: | AIME 2011: 13th Conference on Artifical Intelligence in Medicine, 2011 |
Abstract: | This paper presents a method for the detection and classification of blast cells in M3 with others sub-types using simulated annealing and neural networks. In this paper, we increased our test result from 10 images to 20 images. We performed Hill Climbing, Simulated Annealing and Genetic Algorithms for detecting the blast cells. As a result, simulated annealing is the “best” heuristic search for detecting the leukaemia cells. From the detection, we performed features extraction on the blast cells and we classifying based on M3 and other sub-types using neural networks. We received convincing result which has targeting around 97% in classifying of M3 with other sub-types. Our results are based on real world image data from a Haematology Department. |
Description: | This paper was delivered at AIME 2011: 13th Conference on Artifical Intelligence in Medicine. |
URI: | http://bura.brunel.ac.uk/handle/2438/8103 |
Appears in Collections: | Publications Computer Science Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Fulltext.pdf | 473.77 kB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.