Meta Ordinal Regression Forest For Learning with Unsure Lung Nodules

Deep learning-based methods have achieved promising performance in early detection and classification of lung nodules, most of which discard unsure nodules and simply deal with a binary classification–malignant vs benign. Recently, an unsure data model (UDM) was proposed to incorporate those unsure nodules by formulating this problem as an ordinal regression, showing better performance over traditional binary classification. To further explore the ordinal relationship for lung nodule classification, this paper proposes a meta ordinal regression forest (MORF), which improves upon the state-of the-art ordinal regression method, deep ordinal regression forest (DORF), in three major ways. First, MORF can alleviate the biases of the predictions by making full use of deep features while DORF needs to fix the composition of decision trees before training. Second, MORF has a novel grouped feature selection (GFS) module to re-sample the split nodes of decision trees. Last, combined with GFS, MORF is equipped with a meta learning based weighting scheme to map the features selected by GFS to tree-wise weights while DORF assigns equal weights for all trees. Experimental results on LIDC-IDRI dataset demonstrate superior performance over existing methods, including the state of-the-art DORF.

[1]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

[2]  Yizhou Wang,et al.  Learning With Unsure Data for Medical Image Diagnosis , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Chao Yang,et al.  Ordinal Regression with Neuron Stick-Breaking for Medical Diagnosis , 2018, ECCV Workshops.

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

[5]  Hongming Shan,et al.  Enhancing Transferability of Features from Pretrained Deep Neural Networks for Lung Nodule Classification , 2017 .

[6]  Bo Wang,et al.  Deep Regression Forests for Age Estimation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Qi Xie,et al.  Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting , 2019, NeurIPS.

[8]  Hao Chen,et al.  Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection , 2017, IEEE Transactions on Biomedical Engineering.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Christopher Joseph Pal,et al.  Unimodal Probability Distributions for Deep Ordinal Classification , 2017, ICML.

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

[12]  Hongming Shan,et al.  Shape and margin-aware lung nodule classification in low-dose CT images via soft activation mapping , 2020, Medical Image Anal..

[13]  Jianbo Shi,et al.  Deep Ordinal Regression Forests , 2020 .

[14]  Pedro Antonio Gutiérrez,et al.  Ordinal Regression Methods: Survey and Experimental Study , 2016, IEEE Transactions on Knowledge and Data Engineering.