Delta-radiomics features of ADC maps as early predictors of treatment response in lung cancer

Abstract

Objective: Investigate the feasibility of detecting early treatment-induced tumor tissue changes in patients with advanced lung adenocarcinoma using diffusion-weighted MRI-derived radiomics features.

Methods: This prospective observational study included 144 patients receiving either tyrosine kinase inhibitors (TKI, n = 64) or platinum-based chemotherapy (PBC, n = 80) for the treatment of pulmonary adenocarcinoma. Patients underwent diffusion-weighted MRI the day prior to therapy (baseline, all patients), as well as either + 1 (PBC) or + 7 and + 14 (TKI) days after treatment initiation. One hundred ninety-seven radiomics features were extracted from manually delineated tumor volumes. Feature changes over time were analyzed for correlation with treatment response (TR) according to CT-derived RECIST after 2 months and progression-free survival (PFS).

Results: Out of 14 selected delta-radiomics features, 6 showed significant correlations with PFS or TR. Most significant correlations were found after 14 days. Features quantifying ROI heterogeneity, such as short-run emphasis (p = 0.04_(pfs)/0.005_(tr)), gradient short-run emphasis (p = 0.06_(pfs)/0.01_(tr)), and zone percentage (p = 0.02_(pfs)/0.01_(tr)) increased in patients with overall better TR whereas patients with worse overall response showed an increase in features quantifying ROI homogeneity, such as normalized inverse difference (p = 0.01_(pfs)/0.04_(tr)). Clustering of these features allows stratification of patients into groups of longer and shorter survival.

Conclusion: Two weeks after initiation of treatment, diffusion MRI of lung adenocarcinoma reveals quantifiable tissue-level insights that correlate well with future treatment (non-)response. Diffusion MRI-derived radiomics thus shows promise as an early, radiation-free decision-support to predict efficacy and potentially alter the treatment course early.

Critical relevance statement: Delta-Radiomics texture features derived from diffusion-weighted MRI of lung adenocarcinoma, acquired as early as 2 weeks after initiation of treatment, are significantly correlated with RECIST TR and PFS as obtained through later morphological imaging.

Key points: Morphological imaging takes time to detect TR in lung cancer, diffusion-weighted MRI might identify response earlier. Several radiomics features are significantly correlated with TR and PFS. Radiomics of diffusion-weighted MRI may facilitate patient stratification and management.

Keywords: Diffusion-weighted MRI; Lung cancer; Non-small cell lung cancer; Radiomics; Tyrosine kinase inhibitors.

Fig. 1

Flowchart of the study. TKI, tyrosine-kinase inhibitors; PBC, platinum-based chemotherapy

Fig. 2

Hierarchical clustering heatmap of changes in feature expression at FU2. Rows signify patients, columns signify features. The color coding next to the heatmap indicates RECIST classification at the first follow-up CT (red: PD, blue: SD, and green: PR). Well visible are two distinct groups of patients, one with decreased expression of the first 6 features and an increase of the remaining, the second with the reversed pattern. The horizontal black bar defines the separation between cluster 1 (top) and cluster 2 (bottom)

Fig. 3

Kaplan–Meier estimators illustrating (a) PFS functions, (b) OS functions between the identified patient clusters from Fig. 2. Cluster 2 shows prolonged survival for both metrics as opposed to cluster 1, with PFS being significantly prolonged at p = 0.01 and OS showing a similar tendency at p = 0.06 after applying log-rank test. The OS function contains right-censored data of 22 patients lost to follow-up

Fig. 4

Expression changes between BL and follow-up imaging per group. G_IDN, gradient inverse difference normalized; SRE, short-run emphasis; G_SRE, gradient SRE; ZP, zone percentage; FU1, follow-up 1; FU2, follow-up 2. *p < 0.05, **p < 0.01

Fig. 5

ADC maps and feature maps showing differential expression of feature “ShortRunEmphasis” (SRE) on BL and FU2 imaging (brighter colors mean higher expression). a Patient with SD, TKI group (progression: 1039 days). Visible is an increase in SRE as a brightening especially in the center of the ROI; a similar effect is visible in (c) patient with PR, TKI (progression: 419 days). Opposed are (b) patient with PD, TKI group (progression: 56 days) with a visible decrease in SRE and (d) patient with PD, PBC group (progression: 40 days)