Improving Spatial Context in CNNs for Semantic Medical Image Segmentation

Convolutional Neural Networks (CNNs) have been widely used in the semantic segmentation of medical images. Current CNN-based approaches don't fully exploit information about the local neighbourhood of the pixels being classified thus the inferred labels can be affected by the scope of the information included in the sampling frame. Due to the scarcity of the labelled medical images, using the entire image as the encoder-decoder's input frame is practically unattainable. Thus, random sampling using small frames is an indispensable part of the network training. Furthermore, the average pixel-wise accuracy gives the average likelihood of correct classification across all the pixels in the frame where this likelihood is actually not the same for every pixel. We propose a new approach to address these issues by using multiple neighbourhoods around the pixel of interest and aggregating different hypotheses about the pixel's label. The results produced by this method are comparable with the state of the art solutions. In addition, the method is capable of detecting less accurate regions by assessing the consistency of labelling while shifting the sampling frame across these pixels.

[1]  Guosheng Lin,et al.  CRF Learning with CNN Features for Image Segmentation , 2015, Pattern Recognit..

[2]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling , 2015, CVPR 2015.

[3]  Miguel Angel Ferrer-Ballester,et al.  Multi-angle based lively sclera biometrics at a distance , 2014, 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM).

[4]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

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

[6]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[7]  Ronald M. Summers,et al.  Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation , 2015, IEEE Transactions on Medical Imaging.

[8]  Bram van Ginneken,et al.  Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks , 2016, IEEE Transactions on Medical Imaging.

[9]  Bram van Ginneken,et al.  Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images , 2016, IEEE Transactions on Medical Imaging.

[10]  Jan S. Kirschke,et al.  A Localisation-Segmentation Approach for Multi-label Annotation of Lumbar Vertebrae using Deep Nets , 2017, ArXiv.

[11]  Ming Liu,et al.  PCA-aided fully convolutional networks for semantic segmentation of multi-channel fMRI , 2016, 2017 18th International Conference on Advanced Robotics (ICAR).

[12]  Yanchun Zhang,et al.  Accurate vessel segmentation using maximum entropy incorporating line detection and phase-preserving denoising , 2017, Comput. Vis. Image Underst..

[13]  John E. Hall,et al.  Guyton and Hall Textbook of Medical Physiology , 2015 .

[14]  Maged Habib,et al.  REVIEW - A reference data set for retinal vessel profiles , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[16]  Miguel Angel Ferrer-Ballester,et al.  SSRBC 2016: Sclera Segmentation and Recognition Benchmarking Competition , 2016, 2016 International Conference on Biometrics (ICB).

[17]  Andre D. A. Souza,et al.  Indirect measurement of regional axon diameter in excised mouse spinal cord with q-space imaging: Simulation and experimental studies , 2008, NeuroImage.

[18]  G. Mckhann,et al.  Immune attack on the schwann cell surface in acute inflammatory demyelinating polyneuropathy , 1996, Annals of neurology.

[19]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[20]  Lisa Tang,et al.  Deep Convolutional Encoder Networks for Multiple Sclerosis Lesion Segmentation , 2015, MICCAI.

[21]  Vipin Chaudhary,et al.  Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis , 2011, Medical Imaging.

[22]  Brendan McCane,et al.  Deep convolutional encoder-decoder for myelin and axon segmentation , 2016, 2016 International Conference on Image and Vision Computing New Zealand (IVCNZ).

[24]  Mihai Ciuc,et al.  AutoMarkov DNNs for object classification , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[25]  Bulat Ibragimov,et al.  Segmentation of Pathological Structures by Landmark-Assisted Deformable Models , 2017, IEEE Transactions on Medical Imaging.

[26]  Behzad Aliahmad,et al.  Retinal Vessel Diameter Measurement Using Unsupervised Linear Discriminant Analysis , 2012, ISRN ophthalmology.