Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets

Nicolas Roulet, Diego Fernandez Slezak, Enzo Ferrante
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:401-413, 2019.

Abstract

Brain lesion and anatomy segmentation in magnetic resonance images are fundamental tasks in neuroimaging research and clinical practice. Given enough training data, convolutional neuronal networks (CNN) proved to outperform all existent techniques in both tasks independently. However, to date, little work has been done regarding simultaneous learning of brain lesion and anatomy segmentation from disjoint datasets. In this work we focus on training a single CNN model to predict brain tissue and lesion segmentations using heterogeneous datasets labeled independently, according to only one of these tasks (a common scenario when using publicly available datasets). We show that label contradiction issues can arise in this case, and propose a novel \textit{adaptive cross entropy} (ACE) loss function that makes such training possible. We provide quantitative evaluation in two different scenarios, benchmarking the proposed method in comparison with a multi-network approach. Our experiments suggest ACE loss enables training of single models when standard cross entropy and Dice loss functions tend to fail. Moreover, we show that it is possible to achieve competitive results when comparing with multiple networks trained for independent tasks.

Cite this Paper


BibTeX
@InProceedings{pmlr-v102-roulet19a, title = {Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets}, author = {Roulet, Nicolas and Slezak, Diego Fernandez and Ferrante, Enzo}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {401--413}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/roulet19a/roulet19a.pdf}, url = { http://proceedings.mlr.press/v102/roulet19a.html }, abstract = {Brain lesion and anatomy segmentation in magnetic resonance images are fundamental tasks in neuroimaging research and clinical practice. Given enough training data, convolutional neuronal networks (CNN) proved to outperform all existent techniques in both tasks independently. However, to date, little work has been done regarding simultaneous learning of brain lesion and anatomy segmentation from disjoint datasets. In this work we focus on training a single CNN model to predict brain tissue and lesion segmentations using heterogeneous datasets labeled independently, according to only one of these tasks (a common scenario when using publicly available datasets). We show that label contradiction issues can arise in this case, and propose a novel \textit{adaptive cross entropy} (ACE) loss function that makes such training possible. We provide quantitative evaluation in two different scenarios, benchmarking the proposed method in comparison with a multi-network approach. Our experiments suggest ACE loss enables training of single models when standard cross entropy and Dice loss functions tend to fail. Moreover, we show that it is possible to achieve competitive results when comparing with multiple networks trained for independent tasks.} }
Endnote
%0 Conference Paper %T Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets %A Nicolas Roulet %A Diego Fernandez Slezak %A Enzo Ferrante %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-roulet19a %I PMLR %P 401--413 %U http://proceedings.mlr.press/v102/roulet19a.html %V 102 %X Brain lesion and anatomy segmentation in magnetic resonance images are fundamental tasks in neuroimaging research and clinical practice. Given enough training data, convolutional neuronal networks (CNN) proved to outperform all existent techniques in both tasks independently. However, to date, little work has been done regarding simultaneous learning of brain lesion and anatomy segmentation from disjoint datasets. In this work we focus on training a single CNN model to predict brain tissue and lesion segmentations using heterogeneous datasets labeled independently, according to only one of these tasks (a common scenario when using publicly available datasets). We show that label contradiction issues can arise in this case, and propose a novel \textit{adaptive cross entropy} (ACE) loss function that makes such training possible. We provide quantitative evaluation in two different scenarios, benchmarking the proposed method in comparison with a multi-network approach. Our experiments suggest ACE loss enables training of single models when standard cross entropy and Dice loss functions tend to fail. Moreover, we show that it is possible to achieve competitive results when comparing with multiple networks trained for independent tasks.
APA
Roulet, N., Slezak, D.F. & Ferrante, E.. (2019). Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:401-413 Available from http://proceedings.mlr.press/v102/roulet19a.html .

Related Material