Siamese Encoder-based Spatial-Temporal Mixer for Growth Trend Prediction of Lung Nodules on CT Scans

TL;DR

This paper introduces a novel Siamese encoder and spatial-temporal mixer model to predict lung nodule growth trends from sequential CT scans, improving accuracy by leveraging spatial and temporal features.

Contribution

It proposes a new deep learning framework with a Siamese encoder and spatial-temporal mixer for better growth trend prediction of lung nodules using sequential CT data.

Findings

Outperforms existing methods on the NLSTt dataset

Accurately predicts nodule growth with clinical utility demonstrated

Hierarchical loss improves focus on growing nodules

Abstract

In the management of lung nodules, we are desirable to predict nodule evolution in terms of its diameter variation on Computed Tomography (CT) scans and then provide a follow-up recommendation according to the predicted result of the growing trend of the nodule. In order to improve the performance of growth trend prediction for lung nodules, it is vital to compare the changes of the same nodule in consecutive CT scans. Motivated by this, we screened out 4,666 subjects with more than two consecutive CT scans from the National Lung Screening Trial (NLST) dataset to organize a temporal dataset called NLSTt. In specific, we first detect and pair regions of interest (ROIs) covering the same nodule based on registered CT scans. After that, we predict the texture category and diameter size of the nodules through models. Last, we annotate the evolution class of each nodule according to its changes in diameter. Based on the built NLSTt dataset, we propose a siamese encoder to simultaneously exploit the discriminative features of 3D ROIs detected from consecutive CT scans. Then we novelly design a spatial-temporal mixer (STM) to leverage the interval changes of the same nodule in sequential 3D ROIs and capture spatial dependencies of nodule regions and the current 3D ROI. According to the clinical diagnosis routine, we employ hierarchical loss to pay more attention to growing nodules. The extensive experiments on our organized dataset demonstrate the advantage of our proposed method. We also conduct experiments on an in-house dataset to evaluate the clinical utility of our method by comparing it against skilled clinicians.