SIGA 

This research proposes an interactive GA system to enhance brain MRI images referred to as SIGA. SIGA aims at aiding neurologists and radiologists to detect abnormalities in brain images. Unlike standard IGA systems where its learning is completely dependant on the user, SIGA enhances the MRI based on a joint decision between user and computer. Also, it uses RBFN as a surrogate to model the user’s preferences and reduces the number of user interaction with the system.

 

There are many practical applications of SIGA. Here, some scenarios where SIGA can be useful.

Scenario 1: Globally, there is a high demand for highly experienced neurologists and radiologists. Thus, hiring such doctors is costly while there is not enough labour to cover all hospitals. In fact, in some countries hiring senior neurologists is not affordable. Here, the SIGA can be used to aid less experienced specialists' decisions arguably as effectively as senior specialists when analysing brains MRIs.

Scenario 2: When a brain tumor is too small, usually it is not clear on a standard T1 MRI. Even an experienced doctor can easily confuse cancerous tissue with fluid from edema in the brain. Here, SIGA can play a key role in enhancing the MRI and clarifying tumor areas. This can reduce the number of cases where the doctor decides to inject the patient with IV contrast.

Datasets:

Here you can download SIGA program and test it to enhance MRI images and compare it with other methods.

 

· SIGA Demo. (Require Windows OS and latest .Net framework).

· SIGA MRI test images (Brain tumour cases).

SIGA—Surrogate Interactive Genetic Algorithm

Brain

Computing and Electronic Engineering

Ahmed Kattan