Quality-aware semi-supervised learning for CMR segmentation

TY - CHAP

T1 - Quality-aware semi-supervised learning for CMR segmentation

AU - Ruijsink, Bram

AU - Puyol Anton, Esther

AU - Li, Ye

AU - Bai, Wenjia

AU - Kerfoot, Eric

AU - Razavi, Reza

AU - King, Andrew

PY - 2020/8/26

Y1 - 2020/8/26

N2 - One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing dataset only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the nal product of medical image analysis - they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account awealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis. In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics. SemiQCSeg can be an effcient approach for training segmentation networks for medical image data when labelled datasets are scarce.

AB - One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing dataset only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the nal product of medical image analysis - they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account awealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis. In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics. SemiQCSeg can be an effcient approach for training segmentation networks for medical image data when labelled datasets are scarce.

KW - CMR

KW - segmentation network

KW - Quality Control

KW - data augmentation

M3 - Conference paper

BT - 2020 Conference on Medical Image Computing and Computer Assisted Interventions

PB - Springer

ER -