Automated neural foraminal stenosis grading via task-aware structural representation learning

Abstract Neural foraminal stenosis (NFS) is the most common spinal disease in elderly patients, greatly affecting their quality of life. Efficient and accurate grading of NFS is extremely vital for physicians as it offers patients a timely and targeted treatment according to different grading levels. However, current clinical practice relies on physicians’ visual inspection and manual grading of neural foramina (NF), which brings the annoying inefficiency and inconsistency. A fully automated system is highly desirable but faces many technical challenges (e.g., the inefficiency in localizing NF candidates, and the severe ambiguities in grading). In this paper, an automated and accurate localization and grading clinical framework is proposed. By our framework, both localization and grading tasks are handled as multi-class classification problem: two-class classification (NF/non-NF) and four-class classification (normal/slight/marked/severe). To achieved it, a newly proposed saliency-biased Ncuts (SBNcuts) is utilized for efficient localization, and a novel task-aware structural representation learning (TASRL) model is developed for accurate localization and grading. Specifically, SBNcuts creatively incorporates saliency map as a preliminary guess of NF’s locations to refine the generated possible NF candidates with the preserved intact structure of NF. TASRL incorporates task labels (e.g., NF object label and four NFS grade labels) into manifold learning to obtain a discriminative, low-dimensional, and structural image representation, which enables similar appearance sharing among images with the same task label and different appearance among images with different task labels. The superior performance in localization and grading, with very high ( > 0.89) accuracy, specificity, sensitivity, and F-measure, have been demonstrated by experiments on 110 subjects. With our method, physicians could offer an efficient and consistent clinical grading for NFS.

[1]  Dacheng Tao,et al.  Biologically Inspired Feature Manifold for Scene Classification , 2010, IEEE Transactions on Image Processing.

[2]  Thomas Deselaers,et al.  Measuring the Objectness of Image Windows , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Enhua Wu,et al.  Salient region detection via locally smoothed label propagation: With application to attention driven image abstraction , 2017, Neurocomputing.

[5]  S. Baum,et al.  The Effects of Aspirin on Gastric Prostaglandins , 1994, Annals of Internal Medicine.

[6]  Fei-Fei Li,et al.  What Does Classifying More Than 10, 000 Image Categories Tell Us? , 2010, ECCV.

[7]  Hao Su,et al.  Object Bank: An Object-Level Image Representation for High-Level Visual Recognition , 2014, International Journal of Computer Vision.

[8]  Jianhui Chen,et al.  Automated grading of breast cancer histopathology using cascaded ensemble with combination of multi-level image features , 2017, Neurocomputing.

[9]  Pietro Perona,et al.  Self-Tuning Spectral Clustering , 2004, NIPS.

[10]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[11]  Jean Ponce,et al.  Learning mid-level features for recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[14]  H. An,et al.  Spine update. Lumbar foraminal stenosis. , 2000, Spine.

[15]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[16]  David A. McAllester,et al.  Cascade object detection with deformable part models , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  S. Li,et al.  Regression Segmentation for $M^{3}$ Spinal Images , 2015, IEEE Transactions on Medical Imaging.

[18]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[19]  Jing Wang,et al.  Semi-supervised manifold alignment with few correspondences , 2017, Neurocomputing.

[20]  Jun Li,et al.  Simultaneous Sparse Graph Embedding for Hyperspectral Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[21]  David Zhang,et al.  Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification , 2014, International Journal of Computer Vision.

[22]  Heye Zhang,et al.  Unsupervised boundary delineation of spinal neural foramina using a multi‐feature and adaptive spectral segmentation , 2017, Medical Image Anal..

[23]  Ming Yang,et al.  Regionlets for Generic Object Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[24]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[25]  Manohar M. Panjabi,et al.  Dynamic Intervertebral Foramen Narrowing During Simulated Rear Impact , 2006, Spine.

[26]  Tieniu Tan,et al.  Automatic 3D face recognition from depth and intensity Gabor features , 2009, Pattern Recognit..

[27]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Heung Sik Kang,et al.  A practical MRI grading system for lumbar foraminal stenosis. , 2010, AJR. American journal of roentgenology.

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

[30]  Yong Luo,et al.  Multiview matrix completion for multilabel image classification. , 2015, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[31]  Davide Eynard,et al.  Multimodal Manifold Analysis by Simultaneous Diagonalization of Laplacians , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Wotao Yin,et al.  A feasible method for optimization with orthogonality constraints , 2013, Math. Program..