CIRDataset: A large-scale Dataset for Clinically-Interpretable lung nodule Radiomics and malignancy prediction

TL;DR

This paper introduces CIRDataset, a large-scale, clinically-annotated lung nodule dataset, and presents a deep learning model for nodule segmentation, spike classification, and malignancy prediction, aiming to improve interpretability and clinical relevance.

Contribution

The paper provides the first large-scale dataset with detailed radiologist annotations for lung nodule features and offers an end-to-end deep learning baseline for integrated segmentation, feature classification, and malignancy prediction.

Findings

CIRDataset contains 956 annotated lung nodules with spike/lobulation labels.

The deep learning model effectively segments nodules and classifies spike types.

Benchmark results facilitate validation of model explanations and clinical insights.

Abstract

Spiculations/lobulations, sharp/curved spikes on the surface of lung nodules, are good predictors of lung cancer malignancy and hence, are routinely assessed and reported by radiologists as part of the standardized Lung-RADS clinical scoring criteria. Given the 3D geometry of the nodule and 2D slice-by-slice assessment by radiologists, manual spiculation/lobulation annotation is a tedious task and thus no public datasets exist to date for probing the importance of these clinically-reported features in the SOTA malignancy prediction algorithms. As part of this paper, we release a large-scale Clinically-Interpretable Radiomics Dataset, CIRDataset, containing 956 radiologist QA/QC'ed spiculation/lobulation annotations on segmented lung nodules from two public datasets, LIDC-IDRI (N=883) and LUNGx (N=73). We also present an end-to-end deep learning model based on multi-class Voxel2Mesh extension to segment nodules (while preserving spikes), classify spikes (sharp/spiculation and curved/lobulation), and perform malignancy prediction. Previous methods have performed malignancy prediction for LIDC and LUNGx datasets but without robust attribution to any clinically reported/actionable features (due to known hyperparameter sensitivity issues with general attribution schemes). With the release of this comprehensively-annotated CIRDataset and end-to-end deep learning baseline, we hope that malignancy prediction methods can validate their explanations, benchmark against our baseline, and provide clinically-actionable insights. Dataset, code, pretrained models, and docker containers are available at https://github.com/nadeemlab/CIR.