Abstract: Current studies on the evaluation of rock mass integrity in coal mine goafs mainly rely on the Rock Quality Designation (RQD) as the core parameter, lacking a multidimensional evaluation system that integrates parameters such as fracture development degree, spatial distribution characteristics, and RQD. Evaluating rock mass quality solely based on RQD cannot comprehensively represent the spatial distribution characteristics of fractures, leading to limitations in the reliability and universality of the evaluation results. To address this problem, a fuzzy comprehensive evaluation model of rock mass integrity based on combined weighting was proposed. The model extracted five key parameters, including fracture density, total length, maximum width, fracture rate, and RQD, from borehole television images using an improved YOLOv8 network model to establish a multidimensional evaluation indicator system for rock mass. The Analytic Hierarchy Process (AHP) and Entropy Weight Method (EWM) were used to determine the subjective and objective weights, respectively, and reasonable weight distribution was achieved through combined weighting. Membership functions were established for each indicator corresponding to the fracture development degrees, and fuzzy matrix operations were applied to achieve the classification of rock mass integrity level. A validation analysis was conducted using data from the 349–350 m depth interval of a coal mine goaf in Shandong Province. The results showed that the Fuzzy Comprehensive Evaluation model for rock mass integrity based on combined weighting was consistent with expert judgment results across 96.3% of the borehole depth intervals, outperforming the AHP method (94.9%) and EWM method (94.4%). This approach effectively improved the accuracy and reliability of the rock mass integrity evaluation.