Feasibility of ADC Histogram Analysis for Predicting of Postoperative Recurrence in Aggressive Spinal Tumors

Motivation: Risk stratification of spinal tumors is a major unmet clinical need for personalized therapy. Goal(s): To explore the feasibility of pretreatment whole-lesion apparent diffusion coefficient (ADC) histogram in predicting local recurrence of aggressive spinal tumors. Approach: 119 aggressive spinal tumor patients (median age, 40; range, 13-74 years) confirmed by pathological findings were enrolled and divided into recurrence/non-recurrence group. Results: As for the clinical model, Enneking staging and vertebral compression were independent predictors of recurrence. The ADC histogram model (AUC = 0.871) and the combined model (AUC = 0.884) performed better than the clinical prediction model (AUC = 0.704) with P-values <0.001. Impact: Future individualized follow-up protocols may benefit from incorporating the ADC histogram prediction model, allowing for better selection of patients with aggressive primary spinal tumors for appropriate clinical interventions.