Quantification of the spatial distribution of primary tumors in the lung to develop new prognostic biomarkers for locally advanced NSCLC

Abstract

The anatomical location and extent of primary lung tumors have shown prognostic value for overall survival (OS). However, its manual assessment is prone to interobserver variability. This study aims to use data driven identification of image characteristics for OS in locally advanced non-small cell lung cancer (NSCLC) patients. Five stage IIIA/IIIB NSCLC patient cohorts were retrospectively collected. Patients were treated either with radiochemotherapy (RCT): RCT1* (n = 107), RCT2 (n = 95), RCT3 (n = 37) or with surgery combined with radiotherapy or chemotherapy: S1* (n = 135), S2 (n = 55). Based on a deformable image registration (MIM Vista, 6.9.2.), an in-house developed software transferred each primary tumor to the CT scan of a reference patient while maintaining the original tumor shape. A frequency-weighted cumulative status map was created for both exploratory cohorts (indicated with an asterisk), where the spatial extent of the tumor was uni-labeled with 2 years OS. For the exploratory cohorts, a permutation test with random assignment of patient status was performed to identify regions with statistically significant worse OS, referred to as decreased survival areas (DSA). The minimal Euclidean distance between primary tumor to DSA was extracted from the independent cohorts (negative distance in case of overlap). To account for the tumor volume, the distance was scaled with the radius of the volume-equivalent sphere. For the S1 cohort, DSA were located at the right main bronchus whereas for the RCT1 cohort they further extended in cranio-caudal direction. In the independent cohorts, the model based on distance to DSA achieved performance: AUCRCT2 [95% CI] = 0.67 [0.55–0.78] and AUCRCT3 = 0.59 [0.39–0.79] for RCT patients, but showed bad performance for surgery cohort (AUCS2 = 0.52 [0.30–0.74]). Shorter distance to DSA was associated with worse outcome (p = 0.0074). In conclusion, this explanatory analysis quantifies the value of primary tumor location for OS prediction based on cumulative status maps. Shorter distance of primary tumor to a high-risk region was associated with worse prognosis in the RCT cohort.

Using 3D deep features from CT scans for cancer prognosis based on a video classification model: A multi‐dataset feasibility study

“…Therefore, the 4‐feature signatures achieved a better generalization performance in head and neck cancer. Volume and TNM staging based signatures did not result in good performance on LUNG 4, which is consistent with published literature 52 …”

“…The LUNG 4 52 dataset consist of 322 advanced NSCLC or small cell lung cancer (SCLC) patients who received treatment at MAASTRO Clinic, The Netherlands. The 106 advanced cancer patients (TNM staging III, IIIa, and IIIb) for which clinical and survival information was available were included in this study—indices of included patients can be found in Table S1.…”

Radial Data Mining to Identify Density–Dose Interactions That Predict Distant Failure Following SABR

“…The inclusion of a link to anatomical location in this methodology would be interesting as little is known about tumour location and recurrence after SABR, as reports on disease spread to chest wall, mediastinum, bronchi, and vessels are limited to surgical cohorts ( 45 ). A quantitative assessment of location will provide more information than the tumour lobe location variable currently included in the models ( 46 , 47 ). Assessing specific anatomical locations such as ‘lungs only’ is a potential option to reduce spurious correlations but will lead to different amounts of data excluded dependent on location which could introduce bias.…”