T-Net: A Resource-Constrained Tiny Convolutional Neural Network for Medical Image Segmentation

Tariq M. Khan, Antonio Robles-Kelly, Syed S. Naqvi; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 644-653

Abstract


In this paper, we present T-Net, a fully convolutional net-work particularly well suited for resource constrained andmobile devices, which cannot cater for the computationalresources often required by much larger networks. T-NET's design allows for dual-stream information flow both insideas well as outside of the encoder-decoder pair. Here, weuse group convolutions to increase the width of the networkand, in doing so, learn a larger number of low and inter-mediate level features. We have also employed skip connec-tions in order to keep spatial information loss to a minimum.T-Net uses a dice loss for pixel-wise classification which al-leviates the effect of class imbalance. We have performedexperiments with three different applications, retinal vesselsegmentation, skin lesion segmentation and digestive tractpolyp segmentation. In our experiments, T-Net is quite com-petitive, outperforming alternatives with two or even threeorders of magnitude more trainable parameters.

Related Material


[pdf]
[bibtex]
@InProceedings{Khan_2022_WACV, author = {Khan, Tariq M. and Robles-Kelly, Antonio and Naqvi, Syed S.}, title = {T-Net: A Resource-Constrained Tiny Convolutional Neural Network for Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {644-653} }