Addressing Artefact-Related Image Challenges In Automated Polyp Detection

Supervision: Prof. Dr. Nassir Navab, Dr. Shadi Albarqouni, Roger Soberanis

Abstract

Deep learning techniques are becoming the state-of-the-art in automated polyp detection and the performance of these algorithms relies heavily on the size and quality of the training datasets. Specifically, endoscopic videoframes tend to be corrupted by various artefacts that impair their visibility and affect polyp detection rate. This thesis aims to tackle the issue of artefacts in endoscopic images by extracting knowledge from an artefact dataset that contains over 2,000 images with more than 17,000 annotated artefacts. Our first step was to participate in the ISBI 2019 Endoscopic Artefact Detection Challenge, where we implemented a RetinaNet^? architecture and finished 3rd in the challenge. This object detection framework is then trained on polyp images while we explore different knowledge combination methods, such as Learning without Forgetting, to address the artefacts in these images. We hope that this improves polyp detection performance as well as further expands our comprehension of the effects of artefacts in automated detection in endoscopy.

Requirements:

Good understanding of statistics and machine learning methods.
Very good programming skills in Python & TensorFlow^? / PyTorch^?

Location:

Garching

Literature

Resultant Paper

ProjectForm
Title:	Addressing Artefact-Related Image Challenges In Automated Polyp Detection
Abstract:	Deep learning techniques are becoming the state-of-the-art in automated polyp detection and the performance of these algorithms relies heavily on the size and quality of the training datasets. Specifically, endoscopic videoframes tend to be corrupted by various artefacts that impair their visibility and affect polyp detection rate. This thesis aims to tackle the issue of artefacts in endoscopic images by extracting knowledge from an artefact dataset that contains over 2,000 images with more than 17,000 annotated artefacts. Our first step was to participate in the ISBI 2019 Endoscopic Artefact Detection Challenge, where we implemented a RetinaNet^? architecture and finished 3rd in the challenge. This object detection framework is then trained on polyp images while we explore different knowledge combination methods, such as Learning without Forgetting, to address the artefacts in these images. We hope that this improves polyp detection performance as well as further expands our comprehension of the effects of artefacts in automated detection in endoscopy.
Student:	Maxime Kayser
Director:	Prof. Dr. Nassir Navab
Supervisor:	Dr. Shadi Albarqouni, Roger Soberanis
Type:	Bachelor Thesis
Area:	Machine Learning, Medical Imaging
Status:	finished
Start:
Finish:
Thesis (optional):
Picture:

		Chair for Computer Aided Medical Procedures & Augmented Reality Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality
THIS WEBPAGE IS DEPRECATED - please visit our new website