AI for Healthcare
Artificial intelligence (AI) and related technologies are increasingly prevalent in business and society, and are beginning to be applied to healthcare. These technologies have the potential to transform many aspects of patient care, as well as administrative processes within provider, payer and pharmaceutical organisations.
We work on incorporating the revolution of AI in Healthcare, particularly on medical image analysis, with the goal to transform patient outcomes by enabling enhanced medical decision-making powered by machine learning to build the treatments of the future.
Some of the application areas are
An approach to diagnosis that incorporates multiple sources of data (e.g., pathology, radiology, clinical, molecular and lab operations); uses mathematical models to generate diagnostic inferences; and presents clinically actionable knowledge to customers.
Diagnostic Retinal Image Analysis
Computer aided diagnostic retinal image analysis is the first step in automated screening of retinal, ophthalmic and systemic diseases in large population based studies. Digital retinal images are widely used for early detection of these diseases because they provide a non-invasive window to the human circulatory system and associated pathologies. Glaucoma and diabetic retinopathy (DR) are among the major retinal diseases which are the leading cause of vision loss and blindness in the working population. Early detection of these diseases by screening programs and subsequent treatment can prevent blindness.
Health bots
An intelligent chatbot can guide the concerned parents or patients by understanding and assess the symptoms that they are experiencing and identify the care that they need. With a chatbot as your doctor, patients can receive immediate assistance at the touch of their fingertips. Health bots can also engage and improve the overall patient experience — without the need for a customer support team or a physician on the other end. Additionally, they can also assist with setting up an appointment with the doctor at the right time based on the doctor’s schedule and hours.
Intelligent Visual Surveillance
Person and Vehicle Re-Identification
Understanding of a surveillance scene through computer vision requires the ability to track people across multiple cameras, perform crowd movement analysis and activity detection. Tracking people across multiple cameras is essential for wide area scene analytics and person re-identification is a fundamental aspect of multi-camera tracking. Re-identification (Re-ID) is defined as a process of establishing correspondence between images of a person taken from different cameras. It is used to determine whether instances captured by different cameras belong to the same person, in other words, assign a stable ID to different instances of the person. In an Intelligent traffic monitoring system vehicle re-id plays an import role as vehicle re-id is a process in which we are going to detect a vehicle and then re-identify the vehicle from our database of vehicles. This can play an important role in the field of live monitoring or tracking the vehicles or doing forensic analysis like finding patterns of different vehicles
Abnormal event detection and localization in surveillance videos
Anything deviating from the norm in daily day to day human activity is defined as an anomaly. Surveillance cameras could be automated to detect unusual behavior in Traffic analysis’s, trespassing or in law enforcement. An action that has a very low probability chance to occur is defined as suspicious or an unusual activity. By constructing spatial temporal volumes and grouping videos with a similar criteria, a probabilistic framework could be used to point out the regions that have anomalistic characteristics. Real time response of the system could be used to notify authorities and highlight the anomalous behavior.
Vision Based Violence Detection System
A shot is considered violent if a bared weapon could be seen, if physical violence such as punching or kicking occurred. For the past decade, terrorism has been on the rise, growing at an exponential rate. There have been countless measures that are put in place to stop it or even minimize the effect. We are working on development of an end to end solution to detect and localize unusual objects, suspicious behaviors or irregular events in a scene.
Knowledge Learning and Representation
Knowledge representation and reasoning is the field of artificial intelligence dedicated to representing information about the world in a form that a computer system can utilize to solve complex tasks such as diagnosing a medical condition or having a dialog in a natural language. It enables an intelligent machine to learn from the knowledge and experiences so that it can behave intelligently like a human. A quick glance at an image is sufficient for a human to point out and describe an immense amount of details about the visual scene. However, this remarkable ability has proven to be an elusive task for our visual recognition models.
We are working on the aspects where Computer Vision meets Natural Language Processing-Semantics from Visual Data. Our focus area is Fine-Grained Description of Image Semantics in Natural Language and Visual Question Answering.
3D Computer Vision and Remote Sensing
Remote sensing based on computer vision is the process of detecting and monitoring the physical characteristics of an area based on techniques from the domain of Computer Vision
Machine Vision and Intelligent Systems Lab | NUST-SEECS | © 2024