Automatic identification of segmentation errors for radiotherapy using geometric learning

  title={Automatic identification of segmentation errors for radiotherapy using geometric learning},
  author={Edward G. A. Henderson and Andrew Green and Marcel B. van Herk and Eliana Vasquez Osorio},
, Abstract. 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… 

Figures from this paper



Advances in Auto-Segmentation.

Automated Quality Assurance of OAR Contouring for Lung Cancer Based on Segmentation With Deep Active Learning

An automated quality assurance (QA) system for lung cancer based on a segmentation model trained with deep active learning that automatically detected contour errors for QA could provide consistent and objective evaluations with much reduced investigator intervention in multicenter clinical trials.

Automatic segmentation with detection of local segmentation failures in cardiac MRI

The experiments reveal that combining automatic segmentation with manual correction of detected segmentation failures results in improved segmentation and to 10-fold reduction of expert time compared to manual expert segmentation.

Evaluating Segmentation Error without Ground Truth

This paper presents a generic learning approach based on a novel space of segmentation features, which can be trained to predict the overlap error and Dice coefficient of an arbitrary organ segmentation without knowing the ground truth delineation.

Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy

A 3D U-Net architecture that achieves performance similar to experts in delineating a wide range of head and neck OARs is demonstrated that could improve the effectiveness of radiotherapy pathways.

Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy: a general strategy.

A general strategy based on novel geometric attribute distribution (GAD) models to automatically detect radiation therapy OAR contouring errors and facilitate the current clinical workflow holds great potential for improving the radiation therapy workflow.

Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth

The concept of reverse classification accuracy (RCA) is introduced as a framework for predicting the performance of a segmentation method on new data and it is indicated that it is indeed possible to predict the quality of individual segmentations, in the absence of ground truth.

Automatic detection of contouring errors using convolutional neural networks

The results show that CNN‐based algorithms are able to identify ill‐defined contours from a clinically validated and used multiatlas‐based autocontouring tool and can effectively perform automatic verification of MACS contours.

Quality assurance tool for organ at risk delineation in radiation therapy using a parametric statistical approach.

QA tool integration into clinical procedures may reduce the frequency of inaccurate OAR delineation, and potentially improve safety and quality of radiation treatment planning, and the QA tool assists users to detect potential delineation errors.

Contour Generation with Realistic Inter-observer Variation

This work proposes a methodology to generate random contours, based on measured spatial inter-observer variation, IOV, and a single parameter that controls its geometrical dependency: 𝜎, the width of the 3D Gaussian used as point spread function (PSF).