We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Enhancing Immunotherapy Response Prediction in Metastatic Lung Adenocarcinoma: Leveraging Shallow and Deep Learning with CT-Based Radiomics across Single and Multiple Tumor Sites.
- Authors
Masson-Grehaigne, Cécile; Lafon, Mathilde; Palussière, Jean; Leroy, Laura; Bonhomme, Benjamin; Jambon, Eva; Italiano, Antoine; Cousin, Sophie; Crombé, Amandine
- Abstract
Simple Summary: Efficient prognostic tools for predicting progression-free survival (PFS) in metastatic lung adenocarcinoma (MLUAD) patients undergoing first-line immunotherapy are lacking. This study aimed to enhance prognostic accuracy by leveraging advanced machine-learning survival models and single- and multi-site radiomics data extracted from pre-treatment CT scans, and comparing them to traditional clinicopathological data analyzed using a Cox regression model. Conducted retrospectively on a cohort of 140 patients treated at our comprehensive cancer center, the study revealed significant correlations between various radiomics-based features and PFS, particularly regarding those data extracted from the largest tumor lesion per patient and those summarizing the radiomics profiles of all tumors per patient, as well as the radiophenotypic divergence across all metastases within each patient. Notably, Deepsurv, incorporating carefully selected clinicopathological and radiomics-based inputs, and GBM, utilizing all input variables, demonstrated superior prognostic performance in repeated cross-validation. Additionally, the integration of radiomics with shallow- and deep-learning models surpassed the predictive ability of conventional Cox models, whatever their clinicopathological or radiomics inputs, thereby enhancing prognostic capabilities in MLUAD patients undergoing immunotherapy. This study aimed to evaluate the potential of pre-treatment CT-based radiomics features (RFs) derived from single and multiple tumor sites, and state-of-the-art machine-learning survival algorithms, in predicting progression-free survival (PFS) for patients with metastatic lung adenocarcinoma (MLUAD) receiving first-line treatment including immune checkpoint inhibitors (CPIs). To do so, all adults with newly diagnosed MLUAD, pre-treatment contrast-enhanced CT scan, and performance status ≤ 2 who were treated at our cancer center with first-line CPI between November 2016 and November 2022 were included. RFs were extracted from all measurable lesions with a volume ≥ 1 cm3 on the CT scan. To capture intra- and inter-tumor heterogeneity, RFs from the largest tumor of each patient, as well as lowest, highest, and average RF values over all lesions per patient were collected. Intra-patient inter-tumor heterogeneity metrics were calculated to measure the similarity between each patient lesions. After filtering predictors with univariable Cox p < 0.100 and analyzing their correlations, five survival machine-learning algorithms (stepwise Cox regression [SCR], LASSO Cox regression, random survival forests, gradient boosted machine [GBM], and deep learning [Deepsurv]) were trained in 100-times repeated 5-fold cross-validation (rCV) to predict PFS on three inputs: (i) clinicopathological variables, (ii) all radiomics-based and clinicopathological (full input), and (iii) uncorrelated radiomics-based and clinicopathological variables (uncorrelated input). The Models' performances were evaluated using the concordance index (c-index). Overall, 140 patients were included (median age: 62.5 years, 36.4% women). In rCV, the highest c-index was reached with Deepsurv (c-index = 0.631, 95%CI = 0.625–0.647), followed by GBM (c-index = 0.603, 95%CI = 0.557–0.646), significantly outperforming standard SCR whatever its input (c-index range: 0.560–0.570, all p < 0.0001). Thus, single- and multi-site pre-treatment radiomics data provide valuable prognostic information for predicting PFS in MLUAD patients undergoing first-line CPI treatment when analyzed with advanced machine-learning survival algorithms.
- Subjects
ADENOCARCINOMA; PREDICTIVE tests; PREDICTION models; IMMUNOTHERAPY; RADIOMICS; COMPUTED tomography; TREATMENT effectiveness; METASTASIS; IMMUNE checkpoint inhibitors; DEEP learning; LUNG cancer; SURVIVAL analysis (Biometry); TREATMENT effect heterogeneity; PROGRESSION-free survival; ALGORITHMS; PROPORTIONAL hazards models
- Publication
Cancers, 2024, Vol 16, Issue 13, p2491
- ISSN
2072-6694
- Publication type
Article
- DOI
10.3390/cancers16132491