Automatic identification of segmentation errors for radiotherapy using geometric learning

06/27/2022
by   Edward G. A. Henderson, et al.
0

Automatic segmentation of organs-at-risk (OARs) in CT scans using convolutional neural networks (CNNs) is being introduced into the radiotherapy workflow. However, these segmentations still require manual editing and approval by clinicians prior to clinical use, which can be time consuming. The aim of this work was to develop a tool to automatically identify errors in 3D OAR segmentations without a ground truth. Our tool uses a novel architecture combining a CNN and graph neural network (GNN) to leverage the segmentation's appearance and shape. The proposed model is trained using self-supervised learning using a synthetically-generated dataset of segmentations of the parotid and with realistic contouring errors. The effectiveness of our model is assessed with ablation tests, evaluating the efficacy of different portions of the architecture as well as the use of transfer learning from an unsupervised pretext task. Our best performing model predicted errors on the parotid gland with a precision of 85.0 respectively, and recall of 66.5 in the clinical pathway, potentially decreasing the time clinicians spend correcting contours by detecting regions which require their attention. All our code is publicly available at https://github.com/rrr-uom-projects/contour_auto_QATool.

READ FULL TEXT

page 3

page 7

research
12/06/2020

Esophageal Tumor Segmentation in CT Images using a 3D Convolutional Neural Network

Manual or automatic delineation of the esophageal tumor in CT images is ...
research
01/14/2021

Self-Supervised Learning for Segmentation

Self-supervised learning is emerging as an effective substitute for tran...
research
08/09/2023

Geometric Learning-Based Transformer Network for Estimation of Segmentation Errors

Many segmentation networks have been proposed for 3D volumetric segmenta...
research
09/30/2021

Automated airway segmentation by learning graphical structure

In this research project, we put forward an advanced method for airway s...
research
08/21/2023

Automated Identification of Failure Cases in Organ at Risk Segmentation Using Distance Metrics: A Study on CT Data

Automated organ at risk (OAR) segmentation is crucial for radiation ther...
research
03/05/2021

Liver Fibrosis and NAS scoring from CT images using self-supervised learning and texture encoding

Non-alcoholic fatty liver disease (NAFLD) is one of the most common caus...
research
06/29/2022

CONVIQT: Contrastive Video Quality Estimator

Perceptual video quality assessment (VQA) is an integral component of ma...

Please sign up or login with your details

Forgot password? Click here to reset