Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT


The detection of useful biomarkers in medical imaging aids in the diagnosis and treatment of patients. An accurate segmentation of diseased areas using supervised Deep Learning relies on prior definitions of these regions, wide-scale annotations, a representative patient cohort in the training set, and a large number of patients with similar characteristics. Although pathology is defined in terms of disease, anomaly detection allows for training on healthy data without any annotation. Biomarker discovery can then take place in these areas. This knowledge provides implicit clues for spotting abnormalities in the body's structure. Bayesian Deep Learning is proposed to take advantage of this trait, assuming that epistemic uncertainty are linked to anatomical deviations from a normal training set. U-Nets trained on a well-defined healthy environment are taught using weak anatomical annotations supplied by previous approaches. We use Monte Carlo dropout to capture our model's epistemic uncertainty estimates at testing time. After that, a new post-processing method is used to take advantage of these estimations and convert their layered look into smooth blob-shaped segments of the anomalies. Using OCT images of retinal layers with weak labelling, we were able to demonstrate the effectiveness of this method. Using an independent anomaly test set of AMD cases, our technique achieved a Dice index of 0.789. Finally, we found that our technique can also detect additional abnormalities in normal scans, such as cut edge artefacts.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Smartphone based Indoor Path Estimation and Localization without Human Intervention ABSTRACT: Many different kinds of indoor positioning systems have been developed as a result of the growing market interest in
PROJECT TITLE : Robust Fuzzy Learning for Partially Overlapping Channels Allocation in UAV Communication Networks ABSTRACT: The emerging cellular-enabled unmanned aerial vehicle (UAV) communication paradigm poses significant challenges
PROJECT TITLE : Prediction of Traffic Flow via Connnected Vehicles ABSTRACT: We propose a framework for short-term traffic flow prediction (STP) so that transportation authorities can take early actions to control flow and prevent
PROJECT TITLE : Passenger Demand Prediction with Cellular Footprints ABSTRACT: An accurate forecast of the demand for passengers across the entire city enables providers of online car-hailing services to more efficiently schedule
PROJECT TITLE : NCF: A Neural Context Fusion Approach to Raw Mobility Annotation ABSTRACT: Improving business intelligence in mobile environments requires a thorough comprehension of human mobility patterns on a point-of-interest

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry