This literature review showcases the development of an AI-powered algorithm for automatically measuring minimum joint space width (mJSW) in the medial and lateral compartments of the knee, which is a critical metric medical practitioner use for assessing osteoarthritis progression. Researchers developed an end-to-end pipeline combining a deep learning segmentation model with a computer vision algorithm to measure mJSW on anteroposterior knee radiographs. A dataset of 583 segmented images was used to train, validate, and test the deep learning model in addition to 330 independent images, which were used to validate the algorithm’s accuracy and compare it against human measurements. The model achieved high performance with a dice score of 0.92. The mean absolute error between human and AI measurements was 0.85 ± 1.20 mm, with a minimal mean error of 0.019 mm, which demonstrates no significant bias toward over- or underestimating mJSW. More notably, 73.2% of AI measurements were within 1 mm of human measurements.