Developing an Automatic Cooperating Neural Networks and Image Standardization Approach for Segmentation of X-Ray Computed Tomography Images

Medical image segmentation is a common image analysis task that can impact diagnostic accuracy. Image quality varies depending on application, acquisition parameters and patient preparation. This requires developers’ data preparation efforts prior training. Training on an explicit data nature imposes limitations on generalization. This requires further data pre/post processing efforts for each dataset of different nature. Hence, it’s essential to embed a core component in the segmentation algorithm to automatically handle data processing tasks. In this work, we developed a fully-automated system that transforms computed tomography (CT) images into a standard format prior to segmentation learning and then inverse-transform segments to the original image format to preserve co-registration. Furthermore, we have developed a multi neural network segmentation module that incorporates three convolutional task-specific neural networks that utilize global (two networks) and local (one network) information, while making the segmentation based on agreement of contextual information using probability heatmaps. For baseline non-standard training and testing on a diverse liver dataset, there was no learning convergence and testing results performed relatively poorly. In contrast, after standardized training on the same dataset, all networks converged and yielded dice of +90%. Using the same standardized training, standard and non-standard testing were compared after applying single variable variation. Standardization consistently improved performance by 2.5%, 34.7% and 1.5% for field-of-view, slice-thickness and anatomy, respectively. We also found that global-based segmentation outperformed local-based, and network cooperation significantly outperformed individual networks with dice 95.20%. This offers a segmentation system with better generalization capabilities to serve variable clinical environments.

[1]  Ronald M. Summers,et al.  Anatomy-specific classification of medical images using deep convolutional nets , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[2]  Rongrong Guo,et al.  Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion , 2017, Medical Imaging.

[3]  Hervé Delingette,et al.  A Patch-Based Approach for the Segmentation of Pathologies: Application to Glioma Labelling , 2016, IEEE Transactions on Medical Imaging.

[4]  Shu Liao,et al.  Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition , 2016, IEEE Transactions on Medical Imaging.

[5]  Min Tang,et al.  Segmentation-by-detection: A cascade network for volumetric medical image segmentation , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[6]  Xiangrong Zhou,et al.  Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method , 2017, Medical physics.

[7]  Vijaya K. Shandilya,et al.  USE OF HISTOGRAM EQUALIZATION IN IMAGE PROCESSING FOR IMAGE ENHANCEMENT , 2011 .

[8]  Xiangzhi Bai,et al.  Efficient Multiple Organ Localization in CT Image Using 3D Region Proposal Network , 2019, IEEE Transactions on Medical Imaging.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[11]  Daniel Rueckert,et al.  Automated Abdominal Multi-Organ Segmentation With Subject-Specific Atlas Generation , 2013, IEEE Transactions on Medical Imaging.

[12]  Juha Koikkalainen,et al.  Fast and robust multi-atlas segmentation of brain magnetic resonance images , 2010, NeuroImage.

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

[14]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[15]  Sébastien Ourselin,et al.  Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations , 2017, DLMIA/ML-CDS@MICCAI.

[16]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[17]  Paul A. Yushkevich,et al.  Multi-Atlas Segmentation with Joint Label Fusion , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Boqiang Liu,et al.  DRRNet: Dense Residual Refine Networks for Automatic Brain Tumor Segmentation , 2019, Journal of Medical Systems.

[19]  Ran Klein,et al.  Anatomical region identification in medical X-ray computed tomography (CT) scans: development and comparison of alternative data analysis and vision-based methods , 2020, Neural Computing and Applications.

[20]  Yuichiro Hayashi,et al.  Deep learning and its application to medical image segmentation , 2018, ArXiv.

[21]  Ümit Budak,et al.  Cascaded deep convolutional encoder-decoder neural networks for efficient liver tumor segmentation. , 2019, Medical hypotheses.

[22]  Deukhee Lee,et al.  Automatic spine segmentation from CT images using Convolutional Neural Network via redundant generation of class labels , 2019, J. Comput. Des. Eng..