PiaNet: A pyramid input augmented convolutional neural network for GGO detection in 3D lung CT scans

TL;DR

PiaNet is a novel multiscale convolutional neural network designed for accurate detection of ground-glass opacity nodules in 3D lung CT scans, utilizing pyramid connections and a two-stage transfer learning approach.

Contribution

The paper introduces PiaNet, a new multiscale CNN with pyramid connections and a two-stage transfer learning strategy for improved GGO detection in 3D CT images.

Findings

Achieves 91.75% sensitivity with one false positive per scan.

Outperforms state-of-the-art methods like Subsolid CAD and S4ND.

Effective in small datasets through transfer learning.

Abstract

This paper proposes a new convolutional neural network with multiscale processing for detecting ground-glass opacity (GGO) nodules in 3D computed tomography (CT) images, which is referred to as PiaNet for short. PiaNet consists of a feature-extraction module and a prediction module. The former module is constructed by introducing pyramid multiscale source connections into a contracting-expanding structure. The latter module includes a bounding-box regressor and a classifier that are employed to simultaneously recognize GGO nodules and estimate bounding boxes at multiple scales. To train the proposed PiaNet, a two-stage transfer learning strategy is developed. In the first stage, the feature-extraction module is embedded into a classifier network that is trained on a large data set of GGO and non-GGO patches, which are generated by performing data augmentation from a small number of annotated CT scans. In the second stage, the pretrained feature-extraction module is loaded into PiaNet, and then PiaNet is fine-tuned using the annotated CT scans. We evaluate the proposed PiaNet on the LIDC-IDRI data set. The experimental results demonstrate that our method outperforms state-of-the-art counterparts, including the Subsolid CAD and Aidence systems and S4ND and GA-SSD methods. PiaNet achieves a sensitivity of 91.75% with only one false positive per scan