Tumor burden in metastatic colorectal cancer quantified using deep learning models: Prognostic value and maintenance
Dania Al-Toma1, Ruby Kemna2, Mahsoem Ali2
1Department of Radiology and Nuclear Medicine, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands.
Introduction:
Total tumor number (TTN) and total tumor volume (TTV) reflect tumor burden and have been linked to outcomes in metastatic colorectal cancer (mCRC). We hypothesize that these measures can identify patients who benefit most from maintenance therapy. This exploratory analysis assessed the prognostic and predictive value of TTN and TTV in mCRC.
Methods:
Patients with liver and/or lung metastases from the CAIRO3 trial, which randomized between maintenance therapy and observation, were included. All lesions were counted, and their volumes were quantified using automated deep-learning segmentation models. Cox regression models were used to assess the prognostic value of TTN and TTV for progression-free (PFS) and overall survival (OS), as well as potential interactions with treatment arm (maintenance vs observation).
Results:
A total of 3989 metastatic lesions were segmented in 104 patients (median age, 64 years; 65% male). At randomization, median TTN was 10 and median TTV was 37 mL. Higher TTN and TTV were associated with shorter PFS (TTN p = 0.006; TTV p = 0.2) and OS (TTN p = 0.005; TTV p = 0.001). In multivariable analyses, both TTN and TTV were independently prognostic for PFS/OS. The 1-year PFS benefit of maintenance therapy was more pronounced in patients with lower TTV (Pinteraction=0.0002).
Discussion:
This exploratory analysis showed that a higher tumor burden, quantified by number or volume, was independently associated with poor outcomes. Patients with lower tumor burden, especially lower TTV, appeared to derive the greatest benefit from maintenance therapy, supporting their potential as predictive biomarkers.
