Conv-MCD: A Plug-and-Play Multi-task Module for Medical Image Segmentation

For the task of medical image segmentation, fully convolutional network (FCN) based architectures have been extensively used with various modifications. A rising trend in these architectures is to employ joint-learning of the target region with an auxiliary task, a method commonly known as multi-task learning. These approaches help impose smoothness and shape priors, which vanilla FCN approaches do not necessarily incorporate. In this paper, we propose a novel plug-and-play module, which we term as Conv-MCD, which exploits structural information in two ways - i) using the contour map and ii) using the distance map, both of which can be obtained from ground truth segmentation maps with no additional annotation costs. The key benefit of our module is the ease of its addition to any state-of-the-art architecture, resulting in a significant improvement in performance with a minimal increase in parameters. To substantiate the above claim, we conduct extensive experiments using 4 state-of-the-art architectures across various evaluation metrics, and report a significant increase in performance in relation to the base networks. In addition to the aforementioned experiments, we also perform ablative studies and visualization of feature maps to further elucidate our approach.

[1]  Gabriela Csurka,et al.  What is a good evaluation measure for semantic segmentation? , 2013, BMVC.

[2]  Rich Caruana,et al.  Multitask Learning: A Knowledge-Based Source of Inductive Bias , 1993, ICML.

[3]  Eugenio Culurciello,et al.  LinkNet: Exploiting encoder representations for efficient semantic segmentation , 2017, 2017 IEEE Visual Communications and Image Processing (VCIP).

[4]  Hao Chen,et al.  DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[6]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Antonio M. López,et al.  A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images , 2016, Journal of healthcare engineering.

[9]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Dimitris N. Metaxas,et al.  Deep multi-task and task-specific feature learning network for robust shape preserved organ segmentation , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[11]  Ghulam Muhammad,et al.  Development of the Arabic Voice Pathology Database and Its Evaluation by Using Speech Features and Machine Learning Algorithms , 2017, Journal of healthcare engineering.