Coarse-to-Fine Classification via Parametric and Nonparametric Models for Computer-Aided Diagnosis

TL;DR

This paper introduces a two-tiered coarse-to-fine classification framework combining parametric and nonparametric models to improve early cancer detection accuracy in 3D medical imaging, validated on large clinical datasets.

Contribution

It proposes a novel two-step classification cascade that enhances detection sensitivity and reduces false positives in CAD systems for cancer diagnosis.

Findings

Achieves better detection performance than existing single-layer classifiers.

Validated on large, multi-site clinical datasets for colorectal and lung cancer.

Improves early cancer detection accuracy in 3D medical imaging.

Abstract

Classification is one of the core problems in Computer-Aided Diagnosis (CAD), targeting for early cancer detection using 3D medical imaging interpretation. High detection sensitivity with desirably low false positive (FP) rate is critical for a CAD system to be accepted as a valuable or even indispensable tool in radiologists' workflow. Given various spurious imagery noises which cause observation uncertainties, this remains a very challenging task. In this paper, we propose a novel, two-tiered coarse-to-fine (CTF) classification cascade framework to tackle this problem. We first obtain classification-critical data samples (e.g., samples on the decision boundary) extracted from the holistic data distributions using a robust parametric model (e.g., \cite{Raykar08}); then we build a graph-embedding based nonparametric classifier on sampled data, which can more accurately preserve or formulate the complex classification boundary. These two steps can also be considered as effective "sample pruning" and "feature pursuing + $k$NN/template matching", respectively. Our approach is validated comprehensively in colorectal polyp detection and lung nodule detection CAD systems, as the top two deadly cancers, using hospital scale, multi-site clinical datasets. The results show that our method achieves overall better classification/detection performance than existing state-of-the-art algorithms using single-layer classifiers, such as the support vector machine variants \cite{Wang08}, boosting \cite{Slabaugh10}, logistic regression \cite{Ravesteijn10}, relevance vector machine \cite{Raykar08}, $k$-nearest neighbor \cite{Murphy09} or spectral projections on graph \cite{Cai08}.