Clinical nomogram using novel CT based radiomics predicts survival in non-small cell lung cancer patients treated with SBRT

Abstract

Introduction: Predicting survival in NSCLC is a goal of clinicians in guiding therapy, trialists in risk stratifying patients, and patients for prognosis counseling. Traditional risk calculators for survival use clinical and histopathologic data to predict survival. We propose incorporating the PHOM (persistent homology) score, the radiomic quantification of solid tumor topology, to predict overall survival. Methods: Patients diagnosed with stage I or II NSCLC and status post definitive SBRT treatment were selected (n = 554). The PHOM score was calculated on each patient's pre-treatment CT scan. PHOM score, age, sex, stage, KPS, CCI, and post-SBRT chemotherapy were predictors in the generated Cox proportional hazards models for overall and cancer-specific survival. Patients were split into high and low PHOM score groups by median value and compared using KM curves for overall survival and cumulative incidence curves for cause specific death. Optimized tertile PHOM risk groups were calculated and similarly compared for overall survival and cause-specific death. Internal validation was conducted with bootstrap resampling and calibration curves were checked. Finally, a nomogram to predict overall survival was generated and is publicly available at https://eashwarsoma.shinyapps.io/LungCancerTDATest/. Results: PHOM score was a significant predictor for overall survival (HR: 1.17, 95% CI: 1.07-1.28) and was the only significant predictor for cancer-specific survival (1.31, 95% CI: 1.11-1.56) in the multivariable Cox model. The median survival for the high PHOM group was 29.18 months (95% CI: 23.62-34.27), which was significantly worse compared to the low PHOM group (45.41 months, 95% CI: 40.08-51.78, p < 0.001). The high PHOM group had a significantly greater chance of cancer-specific death at post treatment month 65 (0.244, 95%CI: 0.192-0.296) compared to the low PHOM group (0.171, 95% CI: 0.123-0.218, p = 0.029). Nomograms for 1, 2, 5, and 8-year overall survival were successfully calibrated using the Cox model. Conclusions: The PHOM score is associated with cancer-specific survival and predictive of overall survival. Our developed nomogram can be used to inform clinical prognosis and assist in making post-SBRT treatment considerations.

gtexture: Haralick texture analysis for graphs and its application to biological networks

“…al., describing the co-occurrence of nuclear features in physical cell neighborhoods (Saito et al 2016). Recent interdisciplinary work has successfully extended different graph-based topological analyses to image derived point clouds and more recently to images themselves, including the use of cubical complexes to derive prognostic topological features from medical images (Lawson et al 2019;Hajij, Zamzmi, and Batayneh 2021;Somasundaram, Litzler, et al 2021;Somasundaram, Wadhwa, et al 2022).…”