MedIm

Presenter: Nargiz Akhmetova

​

AI algorithm for pneumonia detection

Search

Project's aim

"MedIm" project's goal is to automate the detection of pneumonia using analysis of X-ray images.

Project's importance

• Rapid diagnosis and accelerated treatment.
• Minimization of human factor error

Project work's methodology

Neural Network

Series of algorithms that endeavor to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.

Differences in algorithmic programming and Machine learning

Data interpretation

Spotting the best model by accuracy_score

ML model's types

ML model learning

epochs: full cycle of learning (bigger number of epochs, higher efficiency)

Efficiency calculations

accuracy_score()

Client application

Result of evaluation

Implementations

• Increased quality of diagnostics
• AI concepts' ubiquitous implementation