This study develops an improved post-surgical quantitative magnetic resonance imaging (qMRI) analysis of the anterior cruciate ligament (ACL) through automation of metal artifact removal introduced by surgical micro-debris. Metal artifacts can cause magnetic field distortions, leading to areas of signal loss where there would otherwise be signal, influencing analysis of ACL healing. Magnetic resonance imaging data from 82 patients were analyzed six months after their initial bridge-enhanced ACL repair or ACL reconstruction and metal artifact regions were removed utilizing a two-step method involving discrete wavelet transformation and K-means clustering algorithm. The automatic segmentation framework was compared to manual segmentation results obtained by an expert in ACL and ACL graft segmentations and demonstrated strong agreement with the manual technique, obtaining a Dice coefficient of 0.81, precision of 0.81, and sensitivity of 0.82. Furthermore, the normalized signal intensity values between the automatic and manual techniques differed by 2%, falling within the predefined 5% equivalence margin as validated by the Two One-Sided Test. The results of this study demonstrate the algorithm’s effectiveness in producing accurate, reliable MRI tissue readings through automatic segmentation by removing metallic artifacts that distort ligament analysis.