Delta radiomic features improve prediction for lung cancer incidence: A nested case–control analysis of the National Lung Screening Trial

Abstract

BackgroundCurrent guidelines for lung cancer screening increased a positive scan threshold to a 6 mm longest diameter. We extracted radiomic features from baseline and follow‐up screens and performed size‐specific analyses to predict lung cancer incidence using three nodule size classes (<6 mm [small], 6‐16 mm [intermediate], and ≥16 mm [large]).MethodsWe extracted 219 features from baseline (T0) nodules and 219 delta features which are the change from T0 to first follow‐up (T1). Nodules were identified for 160 incidence cases diagnosed with lung cancer at T1 or second follow‐up screen (T2) and for 307 nodule‐positive controls that had three consecutive positive screens not diagnosed as lung cancer. The cases and controls were split into training and test cohorts; classifier models were used to identify the most predictive features.ResultsThe final models revealed modest improvements for baseline and delta features when compared to only baseline features. The AUROCs for small‐ and intermediate‐sized nodules were 0.83 (95% CI 0.76‐0.90) and 0.76 (95% CI 0.71‐0.81) for baseline‐only radiomic features, respectively, and 0.84 (95% CI 0.77‐0.90) and 0.84 (95% CI 0.80‐0.88) for baseline and delta features, respectively. When intermediate and large nodules were combined, the AUROC for baseline‐only features was 0.80 (95% CI 0.76‐0.84) compared with 0.86 (95% CI 0.83‐0.89) for baseline and delta features.ConclusionsWe found modest improvements in predicting lung cancer incidence by combining baseline and delta radiomics. Radiomics could be used to improve current size‐based screening guidelines.

Prediction of lung cancer risk at follow-up screening with low-dose CT: a training and validation study of a deep learning method

“…Our study was designed to avoid some common pitfalls in previous studies of both machine learning and deep learning. Although a case-control design is helpful to show the added value of machine learning or deep learning, 12,20,21 the study sample from such a design would not be representative of the general screening population and, therefore, its predictor could not be directly applied to clinical practice. Most studies of machine learning and deep learning did not mask the validation sample's cancer outcomes.…”

“…Many published studies of machine learning and deep learning did not differentiate cancers diagnosed at different timepoints in both prediction algorithm development and its AUC assessment. 18,20,21 Our study outcomes were derived from survival analysis that takes an individual's length of follow-up into consideration. This approach not only reduces bias from different durations of follow-up for participants but also associates higher DeepLR scores with earlier lung cancer diagnosis.…”

“…[9][10][11][12][13][14] There are two major types of machine learning applications for lung cancer risk prediction: the first uses a computer-aided diagnosis approach in nodule detection, segmentation, and feature extraction; [15][16][17][18] the second uses manually defined regions of interest (ROIs) with expert crafted image features. [19][20][21] Recent advances from machine learning to deep learning allow the machine to learn from input data through multiple layers and automatically derive optimum highlevel features without the need for these to be derived by humans. [9][10][11] Since image processing of the entire chest volume is computationally intensive, most previous studies have been restricted to a few prespecified ROIs without analysing all identified lung nodules.…”

Peritumoral and intratumoral radiomic features predict survival outcomes among patients diagnosed in lung cancer screening

“…biomarkers. Our group 8,[15][16][17] and others [18][19][20] have utilized radiomics in the lung cancer screening setting to improve risk prediction and diagnostic discrimination. To date, there have been limited efforts to use radiomics to predict tumor behavior and patient outcomes in the lung cancer screening setting.…”

Radiomics Improves Cancer Screening and Early Detection

“…Going forward, it will be important to incorporate longitudinal image data, or delta radiomics, much as oncologists do in their decision processes. The temporal changes in radiomic features has great potential to inform changes in the nodule biology that have important diagnostic and pathologic consequences (40,41). It will also be important to incorporate quantitative biochemical information from serum or sputum in these models, as they clearly contain important orthogonal information (42,43).…”