Exploiting Clinically Available Delineations for CNN-based Segmentation in Radiotherapy Treatment Planning

11/12/2019
by   Louis D. van Harten, et al.
31

Convolutional neural networks (CNNs) have been widely and successfully used for medical image segmentation. However, CNNs are typically considered to require large numbers of dedicated expert-segmented training volumes, which may be limiting in practice. This work investigates whether clinically obtained segmentations which are readily available in picture archiving and communication systems (PACS) could provide a possible source of data to train a CNN for segmentation of organs-at-risk (OARs) in radiotherapy treatment planning. In such data, delineations of structures deemed irrelevant to the target clinical use may be lacking. To overcome this issue, we use multi-label instead of multi-class segmentation. We empirically assess how many clinical delineations would be sufficient to train a CNN for the segmentation of OARs and find that increasing the training set size beyond a limited number of images leads to sharply diminishing returns. Moreover, we find that by using multi-label segmentation, missing structures in the reference standard do not have a negative effect on overall segmentation accuracy. These results indicate that segmentations obtained in a clinical workflow can be used to train an accurate OAR segmentation model.

READ FULL TEXT
research
03/17/2020

3D medical image segmentation with labeled and unlabeled data using autoencoders at the example of liver segmentation in CT images

Automatic segmentation of anatomical structures with convolutional neura...
research
04/12/2020

Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are powerful medical image segmenta...
research
06/09/2018

Autoencoders for Multi-Label Prostate MR Segmentation

Organ image segmentation can be improved by implementing prior knowledge...
research
08/17/2022

Data-Efficient Vision Transformers for Multi-Label Disease Classification on Chest Radiographs

Radiographs are a versatile diagnostic tool for the detection and assess...
research
06/06/2023

LegoNet: Alternating Model Blocks for Medical Image Segmentation

Since the emergence of convolutional neural networks (CNNs), and later v...
research
04/02/2022

Progressive Minimal Path Method with Embedded CNN

We propose Path-CNN, a method for the segmentation of centerlines of tub...
research
04/07/2018

Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper Confident Bound

Deep convolutional neural networks (CNNs), especially fully convolutiona...

Please sign up or login with your details

Forgot password? Click here to reset