More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation

Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications. With a laparoscopic liver image segmentation application, we investigate the performance impact by altering the quantities of labelled and unlabelled training data, using a semi-supervised segmentation algorithm based on the mean teacher learning paradigm. We first report a significantly higher segmentation accuracy, compared with supervised learning. Interestingly, this comparison reveals that the training strategy adopted in the semi-supervised algorithm is also responsible for this observed improvement, in addition to the added unlabelled data. We then compare different combinations of labelled and unlabelled data set sizes for training semi-supervised segmentation networks, to provide a quantitative example of the practically useful trade-off between the two data planning strategies in this surgical guidance application.

[1]  Naimul Mefraz Khan,et al.  A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation , 2018, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[2]  Sébastien Ourselin,et al.  The NifTK software platform for image-guided interventions: platform overview and NiftyLink messaging , 2014, International Journal of Computer Assisted Radiology and Surgery.

[3]  Dong-Hyun Lee,et al.  Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks , 2013 .

[4]  Josien P. W. Pluim,et al.  Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis , 2018, Medical Image Anal..

[5]  Yiming Li,et al.  Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model , 2019, IPMI.

[6]  C. Perone,et al.  Deep semi-supervised segmentation with weight-averaged consistency targets , 2018, DLMIA/ML-CDS@MICCAI.

[7]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[8]  Sébastien Ourselin,et al.  Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations , 2017, DLMIA/ML-CDS@MICCAI.

[9]  Harri Valpola,et al.  Weight-averaged consistency targets improve semi-supervised deep learning results , 2017, ArXiv.

[10]  Ben Glocker,et al.  Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation , 2017, MICCAI.

[11]  David J. Hawkes,et al.  Deep residual networks for automatic segmentation of laparoscopic videos of the liver , 2017, Medical Imaging.