Giter Site home page Giter Site logo

arunavdey / lstmcaps-adhd Goto Github PK

View Code? Open in Web Editor NEW
2.0 1.0 0.0 6.46 MB

ADHD Classification through MRI scans using an LSTM Capsule Network

Python 92.19% MATLAB 7.69% Dockerfile 0.11%
capsule-network deep-learning keras matlab python tensorflow lstm

lstmcaps-adhd's Introduction

Introduction

Almost all children have behavioral problems. They may run around without caring about their surroundings, be incessantly loud, throw tantrums, refuse to wait for anyone else before their turn, and have problems doing their schoolwork. At other times, they may not pay attention to anyone else, instead choosing to live in their daydreams, and forgetting to complete all other tasks. While this is usually the norm for most children, it is more than just a passing trend for some. Children with attention deficit hyperactivity disorder (ADHD) have frequent and/or severe behavior difficulties that interfere with their capacity to live regular lives. They usually have a lot of difficulty in getting along with other kids, their own family members, and any other passing stranger. This difficulty in paying attention also leads to a difficulty in learning. This can be very dangerous as some people can be quite impulsive. These children are often wrongly branded as just being bad or too impulsive all because they have problems controlling their behaviour. It is normal to be struggling with focusing and behaving from time to time, but children with ADHD are not able to let go of these issues. If left unattended or ignored, these symptoms can carry on and become very severe. This can further lead to interference with education, friendships and familial relationships. If ADHD gets more critical due to being untreated, it can lead to significant, lifetime problems, getting to extremes that can include having run-ins with the law.

The usual pattern observed in people with ADHD are the following:

  • Inattention: This isn't just children usually assumed to be resistant or unintelligible, this is a symptom that manifests in ways such as having difficulty in focusing for long periods of time, working on only one task at a time, or staying coordinated.
  • Hyperactivity: This can mean inability to stay in one place without moving, being noisy without caring about the appropriateness of the situation, unbridled fidgeting, talking constantly without taking a break, etc.
  • Impulsivity: Includes abandoning one task for another, tendency to act without regard for consequences (often at an expense of personal safety). This can also mean wanting to appease everyone or not waiting for anyone’s approval before performing a critical task, and interrupting others without letting them talk when questioned.

The following are three major forms of ADHD:

  • ADHD, combined type: This type includes both impulsiveness and hyperactivity, along with inattention and getting distracted easily
  • ADHD, impulsive/hyperactive type: This type includes only impulsiveness and inattention.
  • ADHD, inattentive and distractible type: This type includes only inattention and getting distracted easily.

The reason for using fMRI scans in the detection of ADHD has proved to be very significant as it allows one to look inside the working of the brain, and find out the differences in the cortisol levels, GM, etc. that lead to behavioral and performance abilities of a person with this disorder. Nevertheless, these abnormalities in normal functioning cannot be directly correlated to ADHD, as these can also be a normal reaction to having a mood swing, a bad day or some other negative occurrence. In spite of these difficulties in narrowing all symptoms down, fMRI scans have shown promising results in helping with the detection of this disorder more accurately. Even if some areas of the brain are linked to ADHD behaviors, how the parts of the brain connect with one another may be crucial in persons who have the disorder. Cognitive, behavioral, and motivational performance may be impaired in someone with ADHD. This suggests that examining not only brain structure but also brain activity during a task could reveal information about the causes of ADHD. This work mainly focuses on using both the fMRI and sMRI scans of patients into ADHD prone and non-adhd prone groups, thus enabling the further diagnosis of the patients whose results have come positive. Results are more reliable when compared to the non-scientific methods used.

Problem Definition

ADHD is a neurodevelopmental disorder that is usually diagnosed in school-going children. Individuals with ADHD have difficulty in concentrating and reining in their impetuous behaviour. They are restless and remain energized constantly. They struggle to learn, are argumentative, and are temperamental. Being a parent to a child with ADHD is hard, frustrating and can be overwhelming. The symptoms of ADHD are often ignored by parents because it may be difficult to tell the difference between a child with ADHD and a "naughty" child. Left untreated, this may result in low self-esteem and the development of anxiety in the future. A number of studies have shown that, even though ADHD isn't linked to significant structural alterations in the brain, MR images can reveal subtle anatomical differences associated with it. For instance, a significant difference in cerebral cortex volume was reported between TDC(typically developing children) and children diagnosed with ADHD. The difference between people diagnosed with ADHD and typically developing individuals indicates that structural MRI could be a useful classification factor for diagnosing ADHD. In order to diagnose diseases by detecting abnormalities in the brain, fMRI can analyze the brain's functional structure. The fMRI uses magnetic resonance imaging (MRI) to detect subtle changes in the blood flow in the active part of the brain. The ability of fMRI data to determine diverse patterns of mental functionality of brain activation has been highlighted. As a result, structural and functional MRI may be useful in detecting brain abnormalities when used together. As a result, in order to elevate classification accuracy, this project is set out to create an ADHD classification approach that integrates both fMRI and sMRI scans. Combining multiple metrics may optimize classification accuracy.

lstmcaps-adhd's People

Contributors

arunavdey avatar roshni-20 avatar

Stargazers

 avatar  avatar

Watchers

 avatar

lstmcaps-adhd's Issues

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.