When introducing advanced image computing algorithms, e.g., whole-heart segmentation, into clinical practice, a common suspicion is how reliable the automatically computed results are. In fact, it is important to find out the failure cases and identify the misclassified pixels so that they can be excluded or corrected for the subsequent analysis or diagnosis. However, it is not a trivial problem to predict the errors in a segmentation mask when ground truth (usually annotated by experts) is absent. In this work, we attempt to address the pixel-wise error map prediction problem and the per-case mask quality assessment problem using a unified deep learning (DL) framework. Specifically, we first formalize an error map prediction problem, then we convert it to a segmentation problem and build a DL network to tackle it. We also derive a quality indicator (QI) from a predicted error map to measure the overall quality of a segmentation mask. To evaluate the proposed framework, we perform extensive experiments on a public whole-heart segmentation dataset, i.e., MICCAI 2017 MMWHS. By 5-fold cross validation, we obtain an overall Dice score of 0.626 for the error map prediction task, and observe a high Pearson correlation coefficient (PCC) of 0.972 between QI and the actual segmentation accuracy (Acc), as well as a low mean absolute error (MAE) of 0.0048 between them, which evidences the efficacy of our method in both error map prediction and quality assessment.
[1]
Hao Chen,et al.
VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images
,
2017,
NeuroImage.
[2]
Hui Zhang,et al.
Image segmentation evaluation: A survey of unsupervised methods
,
2008,
Comput. Vis. Image Underst..
[3]
Qiang Yang,et al.
Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning
,
2010,
ECML/PKDD.
[4]
Ben Glocker,et al.
Automatic Quality Control of Cardiac MRI Segmentation in Large-Scale Population Imaging
,
2017,
MICCAI.
[5]
Xiahai Zhuang,et al.
Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI
,
2016,
Medical Image Anal..
[6]
Jian Sun,et al.
Deep Residual Learning for Image Recognition
,
2015,
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[7]
Zhuowen Tu,et al.
Deeply-Supervised Nets
,
2014,
AISTATS.
[8]
Horst Bischof,et al.
Multi-label Whole Heart Segmentation Using CNNs and Anatomical Label Configurations
,
2017,
STACOM@MICCAI.
[9]
Konstantinos Kamnitsas,et al.
Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth
,
2017,
IEEE Transactions on Medical Imaging.