Automating Antibiotic Sensitivity Testing using Machine Learning Test phase, srs, design phase and source code final deliverable

Get help with
Phd, Masters Thesis & Mcs Final Project
MBA Final Project
Cs619,Fin619,Mgt619,Bnk619,Hrm619,Mkt619
WhatsApp: 0092-3125718857
Skype: trust_aware
Email: projecthelp77@gmail.com
Click here to Join Our Facebook Page
Click here to Join Our YouTube Channel!

Automating Antibiotic Sensitivity Testing using Machine Learning Test phase, srs, design phase and source code final deliverable

/ Category

Machine Learning, Image Processing

Abstract / Introduction

Antibiotics medicines are great discovery in health-care industry due to its efficacy, non-invasive nature and cost-effective treatment. However, inappropriate use antibiotics results in AntiMicrobial Resistance (AMR). Antimicrobial resistance happens when germs like bacteria and fungi develop the ability to defeat the drugs designed to kill them. Consequently, researchers has to produce new antibiotics almost every two year.

Antibiotic Sensitivity Tests are conducted to study the efficacy of new antibiotics. The general steps of antibiotic sensitivity tests includes sample collection, bacterial isolation, incubation, placing the antibiotic disks, evaluation of results and final reporting as illustrated in Figure 1. Brief details can found in this article.

(a) Illustration of the process   (b) Snapshot of actual Petri dish/antibiogram plate

Figure 1: Antibiotic Sensitivity Testing

For evaluation of results, the petri dishes or antibiogram plates are manually examined by human after incubation to observe the zone of inhibition (ZOI) around each antibiotic disk. Considering large-scale scenarios, manual examination is not time consuming but also error-prone. Therefore, this project aim at developing a solution based on machine learning and image processing to automate the evaluation and examination of antibiogram plates.

Functional Requirements:

In this project, students are expected to develop a software application/tool. Through this application, users shall be able to

1. Load/read antibiogram plates images
2. Perform pre-processing to reduce anomalies and noisy data
3. Apply segmentation
4. Recognize the antibiotic labels using OCR.
5. Compute MIC or diameter of the zone of inhibition for each antibiotic 6. Display results accuracy graphically and statistically.

Figure 2 provides the abstract working flow diagram/steps required in the automation process.

Figure 2: Steps to Automate the examination process of Antibiogram Plates

Tools:

You can use any tool related to the project in which you feel comfortable like MATLAB, Weka, C#, Java Python…However, Python is recommended for this project.

Supervisor:

Name: Dr. Israr Ullah