Objective: To evaluate whether the deep learning (DL) segmentation methods from the six teams that participated in the IWOAI 2019 Knee Cartilage Segmentation Challenge are appropriate for quantifying cartilage lossin longitudinal clinical trials.Design: We included 556 subjects from the Osteoarthritis Initiative study with manually read cartilage volumescores for the baseline and 1-year visits. The teams used their methods originally trained for the IWOAI 2019challenge to segment the 1130 knee MRIs. These scans were anonymized and the teams were blinded to anysubject or visit identifiers. Two teams also submitted updated methods. The resulting 9,040 segmentations areavailable online.The segmentations included tibial, femoral, and patellar compartments. In post-processing, we extractedmedial and lateral tibial compartments and geometrically defined central medial and lateral femoral subcompartments. The primary study outcome was the sensitivity to measure cartilage loss as defined by the standardized response mean (SRM).Results: For the tibial compartments, several of the DL segmentation methods had SRMs similar to the goldstandard manual method. The highest DL SRM was for the lateral tibial compartment at 0.38 (the gold standardhad 0.34). For the femoral compartments, the gold standard had higher SRMs than the automatic methods at0.31/0.30 for medial/lateral compartments.Conclusion: The lower SRMs for the DL methods in the femoral compartments at 0.2 were possibly due to thesimple sub-compartment extraction done during post-processing. The study demonstrated that state-of-the-artDL segmentation methods may be used in standardized longitudinal single-scanner clinical trials for well-definedcartilage compartments.