Log In Sign Up

Polyp-artifact relationship analysis using graph inductive learned representations

by   Roger D. Soberanis-Mukul, et al.

The diagnosis process of colorectal cancer mainly focuses on the localization and characterization of abnormal growths in the colon tissue known as polyps. Despite recent advances in deep object localization, the localization of polyps remains challenging due to the similarities between tissues, and the high level of artifacts. Recent studies have shown the negative impact of the presence of artifacts in the polyp detection task, and have started to take them into account within the training process. However, the use of prior knowledge related to the spatial interaction of polyps and artifacts has not yet been considered. In this work, we incorporate artifact knowledge in a post-processing step. Our method models this task as an inductive graph representation learning problem, and is composed of training and inference steps. Detected bounding boxes around polyps and artifacts are considered as nodes connected by a defined criterion. The training step generates a node classifier with ground truth bounding boxes. In inference, we use this classifier to analyze a second graph, generated from artifact and polyp predictions given by region proposal networks. We evaluate how the choices in the connectivity and artifacts affect the performance of our method and show that it has the potential to reduce the false positives in the results of a region proposal network.


page 2

page 3


Self-taught Object Localization with Deep Networks

This paper introduces self-taught object localization, a novel approach ...

A learning without forgetting approach to incorporate artifact knowledge in polyp localization tasks

Colorectal polyps are abnormalities in the colon tissue that can develop...

N-RPN: Hard Example Learning for Region Proposal Networks

The region proposal task is to generate a set of candidate regions that ...

LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

The popular object detection metric 3D Average Precision (3D AP) relies ...

GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation

The inherent ambiguity in ground-truth annotations of 3D bounding boxes ...

Embryo staging with weakly-supervised region selection and dynamically-decoded predictions

To optimize clinical outcomes, fertility clinics must strategically sele...