End-to-end learning of convolutional neural net and dynamic programming for left ventricle segmentation

Nhat M. Nguyen, Nilanjan Ray
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:555-569, 2020.

Abstract

Differentiable programming is able to combine different functions or modules in a data processing pipeline with the goal of applying gradient descent-based end-to-end learning or optimization. A significant impediment to differentiable programming is the non-differentiable nature of some functions. We propose to overcome this difficulty by using neural networks to approximate such modules. An approximating neural network provides synthetic gradients (SG) for backpropagation across a non-differentiable module. Our design is grounded on a well-known theory that gradient of an approximating neural network can approximate a sub-gradient of a weakly differentiable function. We apply SG to combine convolutional neural network (CNN) with dynamic programming (DP) in end-to-end learning for segmenting left ventricle from short axis view of heart MRI. Our experiments show that end-to-end combination of CNN and DP requires fewer labeled images to achieve a significantly better segmentation accuracy than using only CNN.

Cite this Paper

BibTeX
@InProceedings{pmlr-v121-nguyen20a, title = {End-to-end learning of convolutional neural net and dynamic programming for left ventricle segmentation}, author = {Nguyen, Nhat M. and Ray, Nilanjan}, booktitle = {Proceedings of the Third Conference on Medical Imaging with Deep Learning}, pages = {555--569}, year = {2020}, editor = {Arbel, Tal and Ben Ayed, Ismail and de Bruijne, Marleen and Descoteaux, Maxime and Lombaert, Herve and Pal, Christopher}, volume = {121}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/nguyen20a/nguyen20a.pdf}, url = {https://proceedings.mlr.press/v121/nguyen20a.html}, abstract = {Differentiable programming is able to combine different functions or modules in a data processing pipeline with the goal of applying gradient descent-based end-to-end learning or optimization. A significant impediment to differentiable programming is the non-differentiable nature of some functions. We propose to overcome this difficulty by using neural networks to approximate such modules. An approximating neural network provides synthetic gradients (SG) for backpropagation across a non-differentiable module. Our design is grounded on a well-known theory that gradient of an approximating neural network can approximate a sub-gradient of a weakly differentiable function. We apply SG to combine convolutional neural network (CNN) with dynamic programming (DP) in end-to-end learning for segmenting left ventricle from short axis view of heart MRI. Our experiments show that end-to-end combination of CNN and DP requires fewer labeled images to achieve a significantly better segmentation accuracy than using only CNN.} }
Endnote
%0 Conference Paper %T End-to-end learning of convolutional neural net and dynamic programming for left ventricle segmentation %A Nhat M. Nguyen %A Nilanjan Ray %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-nguyen20a %I PMLR %P 555--569 %U https://proceedings.mlr.press/v121/nguyen20a.html %V 121 %X Differentiable programming is able to combine different functions or modules in a data processing pipeline with the goal of applying gradient descent-based end-to-end learning or optimization. A significant impediment to differentiable programming is the non-differentiable nature of some functions. We propose to overcome this difficulty by using neural networks to approximate such modules. An approximating neural network provides synthetic gradients (SG) for backpropagation across a non-differentiable module. Our design is grounded on a well-known theory that gradient of an approximating neural network can approximate a sub-gradient of a weakly differentiable function. We apply SG to combine convolutional neural network (CNN) with dynamic programming (DP) in end-to-end learning for segmenting left ventricle from short axis view of heart MRI. Our experiments show that end-to-end combination of CNN and DP requires fewer labeled images to achieve a significantly better segmentation accuracy than using only CNN.
APA
Nguyen, N.M. & Ray, N.. (2020). End-to-end learning of convolutional neural net and dynamic programming for left ventricle segmentation. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 121:555-569 Available from https://proceedings.mlr.press/v121/nguyen20a.html.

Related Material