Meta Ordinal Regression Forest For Learning with Unsure Lung Nodules

TL;DR

This paper introduces MORF, a novel meta ordinal regression forest that enhances lung nodule classification by effectively utilizing unsure data and improving upon existing ordinal regression methods.

Contribution

MORF advances lung nodule classification by incorporating a grouped feature selection and meta learning-based weighting, outperforming previous methods like DORF.

Findings

MORF achieves higher accuracy on the LIDC-IDRI dataset.

MORF outperforms DORF and other existing methods.

The proposed GFS and meta learning schemes improve model robustness.

Abstract

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 the LIDC-IDRI dataset demonstrate superior performance over existing methods, including the state-of-the-art DORF.