Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists

TL;DR

This paper introduces a radiologist-inspired method for lung nodule malignancy prediction that combines context parsing and prototype recalling modules, leveraging both nodule features and external case knowledge for improved accuracy.

Contribution

The proposed approach simulates radiologists' diagnostic process by integrating context parsing and prototype recalling, enhancing lung nodule classification performance.

Findings

Achieved state-of-the-art results on multiple datasets.

Effective in both low-dose and noncontrast CT screening scenarios.

Utilized a large-scale dataset with over 16,000 nodules with confirmed labels.

Abstract

Lung cancer is a leading cause of death worldwide and early screening is critical for improving survival outcomes. In clinical practice, the contextual structure of nodules and the accumulated experience of radiologists are the two core elements related to the accuracy of identification of benign and malignant nodules. Contextual information provides comprehensive information about nodules such as location, shape, and peripheral vessels, and experienced radiologists can search for clues from previous cases as a reference to enrich the basis of decision-making. In this paper, we propose a radiologist-inspired method to simulate the diagnostic process of radiologists, which is composed of context parsing and prototype recalling modules. The context parsing module first segments the context structure of nodules and then aggregates contextual information for a more comprehensive understanding of the nodule. The prototype recalling module utilizes prototype-based learning to condense previously learned cases as prototypes for comparative analysis, which is updated online in a momentum way during training. Building on the two modules, our method leverages both the intrinsic characteristics of the nodules and the external knowledge accumulated from other nodules to achieve a sound diagnosis. To meet the needs of both low-dose and noncontrast screening, we collect a large-scale dataset of 12,852 and 4,029 nodules from low-dose and noncontrast CTs respectively, each with pathology- or follow-up-confirmed labels. Experiments on several datasets demonstrate that our method achieves advanced screening performance on both low-dose and noncontrast scenarios.